Living with AI | Elena Daehnhardt, PhD

Capability Meets Constraint

Elena Daehnhardt · 1 May, 2026

This week's AI signals mark a sharper turning point: frontier capability kept rising, while multimodal enterprise launches and cybersecurity controls moved into production. OpenAI expanded GPT-5.5, DeepSeek released V4, NVIDIA announced Nemotron 3 Nano Omni, IBM released Granite 4.1, and Anthropic launched Claude Security public beta. Read more...

Cursor AI with MCP tools

Elena Daehnhardt · 29 Apr, 2026

A practical walkthrough for connecting Cursor AI to MCP servers so the assistant can use external tools, APIs, and project context safely. Read more...

Codex CLI Part 4: Advanced Operations, Troubleshooting, and Team Patterns

Elena Daehnhardt · 29 Apr, 2026

Part 4 closes the Codex CLI series with advanced operational patterns: non-interactive automation, permission strategy, troubleshooting playbooks, and team-level standards for reliable adoption. Read more...

Has the open-source gap closed?

Elena Daehnhardt · 24 Apr, 2026

OpenAI ended the week by releasing GPT-5.5 — codenamed Spud — retaking the top spot across 14 benchmarks and positioning itself explicitly as an agent runtime rather than a chat model. Two Chinese labs shipped frontier-quality models on the same day: Alibaba's Qwen 3.6-Max-Preview closed its weights for the first time, and Moonshot's open-source Kimi K2.6 reached #4 on the global intelligence index, level with Western frontier labs. OpenAI's gpt-image-2 introduced reasoning into image generation. Google confirmed Gemini will power the next Siri. Amazon committed another $25 billion to Anthropic. And the Stanford AI Index documented a field accelerating faster than every institution surrounding it. Nine signals. A week that moved the map. Read more...

Codex CLI Part 3: Practical Workflows for Blogging and Python Development

Elena Daehnhardt · 22 Apr, 2026

A practical, high-depth guide to using Codex CLI for blog editing and Python delivery: review loops, safe refactoring, debugging, and non-interactive automation with explicit guardrails. Read more...

Agents, Cyber Models, and the Safety Stack Tightening Up

Elena Daehnhardt · 17 Apr, 2026

This week's clearest AI signal was not a giant new general model. It was the rapid convergence of stronger agent tooling, more cyber-capable systems, and tighter safety controls. Anthropic shipped Claude Opus 4.7 with new cyber safeguards. OpenAI expanded trusted cyber access, upgraded its Agents SDK, and pushed Codex deeper into real developer workflows. Microsoft launched a cheaper production-grade image model. Meanwhile, Anthropic's Mythos triggered a real regulatory response across central banks and governments. Read more...

AI Signals: Controlled Releases and Platform Integration

Elena Daehnhardt · 10 Apr, 2026

This week’s AI signals point to a shift toward controlled releases and platform integration. Meta launched Muse Spark, Microsoft expanded its multimodal stack, and efficiency improvements continue to shape deployment. Instead of rapid disruption, the focus is on deliberate progress and clearer strategic direction. Read more...

AI Signals: From Models to the Full Stack

Elena Daehnhardt · 3 Apr, 2026

This week’s AI signals show a clear shift from models to the full stack. Microsoft expanded its multimodal model lineup, AI is being used to design chips, and new AI-native devices are emerging. At the same time, a powerful Anthropic model remains unreleased due to safety concerns, trust is lagging behind adoption, and startup valuations are accelerating again. Read more...

The Digital Butler or Trojan Horse? A Privacy Playbook for Persistent AI Agents

Elena Daehnhardt · 27 Mar, 2026

Persistent AI agents can save hours each week, but they also turn hidden prompt injections into real-world actions unless you design strict controls. This guide shows how to harden agent workflows with policy gates, isolation, scoped permissions, and safe auditing. Read more...

AI's New Bottleneck

Elena Daehnhardt · 27 Mar, 2026

The week, AI signals shifted attention from generic model chatter to concrete releases and constraints. Google launched Gemini 3.1 Flash Live and Lyria 3 Pro for developers, while reports of Anthropic's unreleased Mythos/Capybara model highlighted high-capability safety pressure. At the same time, U.S. datacenter policy and GitHub's Copilot data-default change reinforced that governance and infrastructure are now product-critical. Read more...

The Complete Orchestration Blueprint

Elena Daehnhardt · 22 Mar, 2026

I love this energy. You didn’t just “learn agents.” You built an orchestration system.

Infrastructure Is the New Frontier

Elena Daehnhardt · 20 Mar, 2026

This week’s biggest AI signal was not a new frontier model. It was the fast consolidation of infrastructure, distribution, and cost. Nvidia pushed agentic AI and robotics as stack problems. Anthropic invested in enterprise distribution and tested asynchronous delegation. Microsoft, Mistral, and OpenAI advanced the efficiency tier. Xiaomi and Rakuten showed how global and contested the open-weight race has become. Read more...

Edge AI in Everyday Operations

Mark Simons · 19 Mar, 2026

Practical ways businesses can use Edge AI to make faster, local decisions without replacing existing systems or relying on constant cloud connectivity. Read more...

Observability For Ai Workflow

Elena Daehnhardt · 18 Mar, 2026

I love that energy 😄 Alright — now we put lights inside the machine.

Better Models, Burnout, and a $599 Mac

Elena Daehnhardt · 13 Mar, 2026

GPT-5.4 arrived with native computer use and a 1M-token context window. Anthropic moved further toward becoming an enterprise platform. And Block's layoffs, alongside new HBR research on "AI brain fry," made one thing clear: this week's real signal was not just better models, but what AI is doing to work. Read more...

Idempotency Run Isolation And Crash Safety

Elena Daehnhardt · 12 Mar, 2026

This is such a good instinct. You’re thinking like a system designer now.

My Inbox Is a Black Hole (and How I Escaped It)

Elena Daehnhardt · 10 Mar, 2026

Short 1–2 sentence summary. Read more...

Tool Isolation With Mcp

Elena Daehnhardt · 8 Mar, 2026

Oh this is where it becomes properly architectural. I love it. 🔥

AI Is Splitting Into Tiers

Elena Daehnhardt · 6 Mar, 2026

Three fast, cheap models landed in the same week — Gemini 3.1 Flash-Lite, GPT-5.3 Instant, and Qwen3.5-9B. That is not a coincidence. The cost-performance frontier just moved. Read more...

Human Reports And Draft Preview Endpoints

Elena Daehnhardt · 5 Mar, 2026

Perfect. This is the “make it feel real” post.

Vibe Coding Wasn't Enough — The Lightweight System I Use to Turn AI Prompts into Deployed Apps

Elena Daehnhardt · 4 Mar, 2026

Vibe coding can generate working apps in minutes — but most don’t last. I replaced chaotic prompting with a simple, spec-driven AI workflow that turns ideas into reliable, deployed tools. Read more...

72.5%, $710B, and a March in London

Elena Daehnhardt · 27 Feb, 2026

This week's signals trace a collision between software and reality: Anthropic's leap in computer automation, a record-breaking $710B cloud capex plan, and the resulting shockwaves in consumer electronics prices and global energy policy. Read more...

Supervisor Agent In Langgraph

Elena Daehnhardt · 27 Feb, 2026

Yesss — this is where it starts to feel like a real system 😄

Live Design Testing with GitHub Pages and a Custom Domain

Elena Daehnhardt · 20 Feb, 2026

Want to preview two completely different blog designs at domain.com/test1 and domain.com/test2 while keeping your main blog running perfectly? Here is how to do it with two extra GitHub repositories — no downtime, no risk. Read more...

Testing Blog Designs with Git Branches and GitHub Pages

Elena Daehnhardt · 20 Feb, 2026

Did you know you can publish different versions of your GitHub Pages blog on separate branches and preview them live before committing to a design? Here is how I do it. Read more...

How to Host Your Blog for Free with GitHub Pages

Elena Daehnhardt · 20 Feb, 2026

GitHub Pages lets you host a blog for free, with your own custom domain, no servers to manage, and no hosting bill at the end of the month. Here is everything you need to go from zero to published. Read more...

OpenClaw Isn't a Chatbot Anymore. It's Infrastructure.

Elena Daehnhardt · 20 Feb, 2026

AI agents like OpenClaw are wonderful tools — but without strict access rules and proper supervision, they can turn an ordinary Tuesday into something you will be explaining to HR for weeks. In this post, we explore the very real risks of deploying AI assistants carelessly, from leaked credentials to messages you absolutely did not mean to send. Most importantly, we look at how to use OpenClaw the right way, because when deployed thoughtfully, it is one of the most exciting and capable tools we are only just beginning to understand. Read more...

Git Cherry-Pick: The Surgeon's Knife

Elena Daehnhardt · 20 Feb, 2026

merging takes everything. Rebase rewrites everything. But sometimes, you just want that ONE bug fix from the development branch applied to production. That's where git cherry-pick comes in. Read more...

Agentic AI at Scale: New models, $30B, and the UKRI Strategy

Elena Daehnhardt · 20 Feb, 2026

Weekly AI Signals for February 12-19, 2026: Claude Sonnet 4.6, Gemini 3.1 Pro, Anthropic's $30B Series G, and UKRI's £1.6 billion AI strategy show how capability, capital, and sovereignty are shaping AI at scale. Read more...

Type Less, Do More: My Top 10 Git Aliases

Elena Daehnhardt · 13 Feb, 2026

If you type 'git checkout' fifty times a day, you're wasting time. In this post, I share my personal list of Git aliases that help me work faster and smarter. Read more...

AI Improves Itself While We Argue About Permits

Elena Daehnhardt · 13 Feb, 2026

This week's signals show AI capability racing ahead while real-world constraints tighten: $2.5B inference funding, self-improving models from OpenAI and Anthropic, ByteDance's restricted video AI, and data centres stuck in permit battles. The gap between what models can do and what infrastructure can support is becoming the central story. Read more...

Git Hooks: The Robot Butler for Your Code

Elena Daehnhardt · 6 Feb, 2026

Why remember to run tests when a robot can do it for you? In this post, I explain Git Hooks and how to set up simple automations that ensure you never commit broken code again. Read more...

Codex CLI Part 2 — Security Controls & Safe Editing

Elena Daehnhardt · 6 Feb, 2026

Learn how Codex CLI balances permissions and approvals to keep you in control. Master essential commands like /diff and /review, understand the three security modes, and make your first safe code edits with full visibility. Read more...

The AI Paradox: Lightning Fast and Gridlocked

Elena Daehnhardt · 6 Feb, 2026

This week's signals were about constraints and acceleration at once: AI-assisted cloud attacks, multi-year grid queues in Europe, new infrastructure funds, and consumer GPU pricing pressures — alongside fast adoption of consumer AI apps. Read more...

Protecting Infrastructure in an Era of AI-Assisted Attacks

Elena Daehnhardt · 5 Feb, 2026

Short 1–2 sentence summary. Read more...

Using AI Code Assistants Safely

Elena Daehnhardt · 30 Jan, 2026

A practical, human guide to using generative code assistants safely — without leaking secrets, breaking trust, or losing control of your work. Read more...

Chips, Capex, and Code Risk

Elena Daehnhardt · 30 Jan, 2026

This week’s AI signals were practical rather than flashy: Microsoft’s earnings tied AI to long-term capex, Anthropic pushed export-focused regulation, China approved limited H200 imports, and everyday compute continued to rise. Together, they point to AI becoming infrastructure — budgeted, regulated, and increasingly constrained. Read more...

Stop Committing Garbage: A Masterclass in .gitignore

Elena Daehnhardt · 30 Jan, 2026

A clean repository is a happy repository. In this post, I dive into how to use .gitignore effectively to prevent system files, secrets, and dependencies from polluting your project history. Read more...

Edge AI in Everyday Operations

Elena Daehnhardt · 27 Jan, 2026

Practical ways businesses can use Edge AI to make faster, local decisions without replacing existing systems or relying on constant cloud connectivity. Read more...

This Week in AI: Regulation Heat, Cloud Bets, and Agentic Shopping

Elena Daehnhardt · 23 Jan, 2026

This week's AI signals clustered around policy pressure, infrastructure bets, and the early rails of agentic commerce. Read more...

Git Stash: The CTRL-Z for Your Working Directory

Elena Daehnhardt · 23 Jan, 2026

Ever needed to switch branches but your current work wasn't ready to commit? Enter Git Stash—the temporary clipboard for your code changes. In this post, I explain how to stash, pop, and manage your work-in-progress efficiently. Read more...

Getting Started with Codex CLI

Elena Daehnhardt · 21 Jan, 2026

Learn what Codex CLI is, how to install it on Mac, Linux, and Windows, and take your first steps with this AI coding assistant that runs in your terminal. Read more...

My multi-agent workflow

Elena Daehnhardt · 20 Jan, 2026

Short 1–2 sentence summary. Read more...

Signals from the AI Supply Chain

Elena Daehnhardt · 16 Jan, 2026

This week’s AI news wasn’t about new models or flashy demos. Instead, it revealed where AI is becoming real: chip manufacturing at TSMC, AI assistants like Siri, data centre infrastructure, and the early shape of AI-driven commerce. Read more...

AI's Week of Limits: Safety, Control, and Real-World Physics

Elena Daehnhardt · 9 Jan, 2026

This week felt quieter but more substantive—France chose sovereignty over scale, Nvidia refocused on inference and deployment, Grok exposed the gap between capability and responsibility, Asian markets showed resilience, and fusion labs demonstrated where AI earns trust through reliability. Read more...

As 2025 Closes: AI's Week of Regulation, Infrastructure, and Autonomy

Elena Daehnhardt · 2 Jan, 2026

The final week of 2025 brought three defining moments: China's first rules for emotional AI companions, massive infrastructure consolidation, and Meta's bet on autonomous agents. Here's what these signals mean for 2026. Read more...

Hardware Handshakes, Prompt Injection Reality, and AI Beyond the Screen

Elena Daehnhardt · 26 Dec, 2025

This week in AI brought a shift from hype to engineering reality. Hollywood’s quality limits, a $20B Nvidia–Groq hardware deal, OpenAI’s prompt injection admission, better context for AI coding, and conversational AI moving into physical spaces. Read more...

Merry Christmas and a Very Happy New Year!

Elena Daehnhardt · 23 Dec, 2025

As we near 2025, I wish my readers a happy, healthy, and prosperous New Year! Read more...

AI Interfaces, Safety, and Multimodal Systems

Elena Daehnhardt · 19 Dec, 2025

This week, several AI developments caught my attention. Not because they were flashy, but because they touched on issues that matter once AI systems leave demos and meet real users: safety defaults, speed under real constraints, and interfaces that adapt instead of overwhelm. Read more...

Antigravity 1.11.9 vs Cursor 2.1.42 (Universal): A Practical Comparison

Elena Daehnhardt · 15 Dec, 2025

A detailed comparison between Google’s Antigravity 1.11.9 and Cursor 2.1.42, focusing on how each IDE reimagines AI-assisted coding. Includes links to documentation and real feature pages. Read more...

Labs, Law and New Hardware Horizons

Elena Daehnhardt · 12 Dec, 2025

This week brought real developments in AI infrastructure: DeepMind prepares its first automated materials science lab in the UK, OpenAI finalises prototypes of a new ambient device, and 42 state attorneys general demand stronger safeguards for chatbots. Plus a $20 billion AI infrastructure venture and new findings on where AI matches human specialists. Read more...

A Short Tale of Bravery (at the Dentist)

Elena Daehnhardt · 12 Dec, 2025

A personal story about facing the drill, followed by a researched look at how AI and robotics are quietly becoming the dentist's ultimate co-pilot. Read more...

AGI Timelines, 3D Vision, and the Reality of AI Scams

Elena Daehnhardt · 5 Dec, 2025

The U.S. government moves to operationalise AI, DeepMind sets an AGI deadline, and a terrifying scam in Kansas serves as a wake-up call for personal security. Read more...

A Journey Through AI and Code

Elena Daehnhardt · 5 Dec, 2025

Another year has passed, and Elena's AI Blog is now four years old! This year brought exciting developments in AI, from multimodal systems to agentic workflows, and I've been here documenting it all. Join me as I reflect on what we've explored together since December 2024. Read more...

The New Skill Stack, from Writing Code to Managing Intelligence

Elena Daehnhardt · 28 Nov, 2025

A simple guide to the new era of coding: less bricklaying, more architecture. What changes, what stays, and the surprising human skills that now matter more. Read more...

Claude Opus, ChatGPT Shopping, EV Forecasting and DeepSeekMath-V2

Elena Daehnhardt · 28 Nov, 2025

A warm and simple walk through this week’s most meaningful AI shifts—from coding models to shopping helpers, EV predictions, and a new open-source system that checks its own maths. Read more...

Ethics, Gravity, and the Future We're Actually Building

Elena Daehnhardt · 21 Nov, 2025

Google just killed the text editor with 'Antigravity,' while the WHO demanded humanity 'hold the pen.' From agentic workflows to the energy cost of reasoning, here is why this week marked the end of the AI Wild West. Read more...

Ethics, Code, Chips, and a Petaflop on Your Desk

Elena Daehnhardt · 14 Nov, 2025

This week AI highlights include the Vatican's thoughts on human dignity, the fact that only 9% of developers trust AI-generated code, MIT's new software model for large language models, NVIDIA's petaflop-capable workstation, VUNO's profitable medical AI, Meta's automatic speech recognition for over 1,600 languages, and a new AI-assisted chip design tool. This week showcases the connections between ethics, coding, hardware, and humanity. Read more...

Could AI Become a New Religion?

Elena Daehnhardt · 14 Nov, 2025

A gentle exploration of how the Church once resisted scientific novelty—from banned books to the Galileo affair—and how it now engages with artificial intelligence as a partner in ethical reflection. This post looks at whether AI could become a “new religion,” why some people might treat it that way, why it cannot truly be one, and what history teaches us about our relationship with powerful new ideas. It ends with a hopeful vision: kindness, humanity and shared dignity as the guiding beliefs we choose for the future we build together. Read more...

Apache-Licensed Summarizers

Elena Daehnhardt · 14 Nov, 2025

Looking for summarisation models you can safely use in your app or blog? Here's a friendly tour of Apache-licensed transformer models that actually summarise well — and don't break your licence policy. Read more...

AI Weekly — Agents Grow Up, Clouds Get Bigger

Elena Daehnhardt · 7 Nov, 2025

This week: OpenAI books a mountain of AWS compute, Google ships production tooling for agents, GitHub adds org-wide steering for Copilot, VS Code unifies agent experiences, and OpenAI previews an autonomous security researcher. Read more...

A few thoughts on Cursor 2.0

Elena Daehnhardt · 7 Nov, 2025

Cursor 2.0 introduces its own **Composer model**, a new autonomous agent workflow, and security via the **Sandboxed Terminal**. Read this blog post to see if this shift to agent-led development is right for you. Read more...

AI Infrastructure, Small Models, and Multi-Agent Coding

Elena Daehnhardt · 31 Oct, 2025

NVIDIA builds massive supercomputers, IBM releases open small models, and GitHub turns coding into a team sport for AI agents. Three quiet shifts reshaping how we build and think. Read more...

Quantum Thinking, Light Models, Living Networks

Elena Daehnhardt · 24 Oct, 2025

This week AI quietly scored wins: quantum leaps, lightweight models, and network automation. What they mean for coders, curious minds, and everyday life. Read more...

Should you use rebase?

Elena Daehnhardt · 16 Oct, 2025

Rebase isn't safer than merge—it's cleaner. Learn when to use Git rebase for a tidy history and when to avoid it to keep your team happy. Read more...

LoRA fine-tuning wins

Elena Daehnhardt · 16 Oct, 2025

You don't need to retrain entire language models anymore. LoRA lets you teach new tricks with tiny adapters—fast training, small files, and swappable skills. Read more...

AI Honesty, Agents, and the Fight for Truth

Elena Daehnhardt · 16 Oct, 2025

Chatbots must tell you they're AI, your computer just got a mind of its own, and publishers are fighting to protect truth. Three stories that matter for everyone. Read more...

Safety, Agents, and Compute

Elena Daehnhardt · 10 Oct, 2025

Three major AI announcements dropped this week that actually matter. Google taught agents to use computers like humans do. DeepMind built a security agent that finds and patches vulnerabilities automatically. OpenAI and AMD committed 6 gigawatts of compute capacity. No hype—just the practical shifts that change how we build software. Read more...

Cursor Made Me Do It

Elena Daehnhardt · 3 Oct, 2025

AI makes coding feel like magic — until your ‘tiny app’ turns into a monster. Here’s how to enjoy the creative flow without losing control. Read more...

I have cloned my git repository and landed on main. How to get your branch

Elena Daehnhardt · 3 Oct, 2025

Cloned a repo and ended up on main? This two-second trick gets you to the right branch fast. Read more...

AI Got Rules, Wheels & a Lab Coat

Elena Daehnhardt · 3 Oct, 2025

AI just got new safety rules, Europe is steering into autonomous roads, and MIT taught models some physics. Busy week. Read more...

AI’s Busy Week

Elena Daehnhardt · 26 Sep, 2025

From Britain’s sovereign AI push to coding models that think like engineers, this week’s breakthroughs show AI growing brains, memory, and initiative — plus some long-overdue policy wins. Read more...

Gemini CLI versus Claude CLI

Elena Daehnhardt · 19 Sep, 2025

This blog post is about Gemini CLI and Claude CLI, their installation, usage, privacy, and effectiveness — with some ideas to help you choose the right AI tool for your terminal. Read more...

AI this week

Elena Daehnhardt · 19 Sep, 2025

ChatGPT goes mainstream with 700M weekly users, Google finds a cure for hallucinations, GPT-5 Codex rewrites your code, textbooks finally get personal, and AR learns when to keep quiet. Read more...

Vibe Coding with Cursor AI

Elena Daehnhardt · 12 Sep, 2025

Testing Cursor AI in Agent Mode feels like coding with a slightly eccentric but eager partner. Friendly, fast, sometimes forgetful — here’s how GPT-5, Auto mode, and grok-code-fast stack up, with real specs. Read more...

AI weekly news

Elena Daehnhardt · 12 Sep, 2025

This week in AI: leaner models beating the giants, Google rewriting the speed–accuracy trade-off, AI that codes for scientists, smarter DNA design, and OpenAI trying to tame the AI job market. Read more...

AI weekly

Elena Daehnhardt · 5 Sep, 2025

We have picked up new AI happenings this week: GRPO for smarter training, reasoning models that cut the nonsense, entry-level jobs under pressure, Nano Banana stealing the image crown, and GPT-5 hacks unlocking hidden power. Read more...

How to Create a Weekly Menu with ChatGPT-5

Elena Daehnhardt · 4 Sep, 2025

This week, I let ChatGPT-5 into my kitchen. The result? A complete weekly meal plan for two people, tailored macros, batch-cooking flows, fridge-friendly PDFs, and even a laminated checklist with tick boxes. Read more...

AI weekly wins

Elena Daehnhardt · 29 Aug, 2025

This week, AI became cheaper, more natural, and a lot more practical. Oxford’s new optimiser slashes training bills by 80%, OpenAI’s voice system talks like a real human, and Google’s ‘Nano Banana’ image model quietly outshines the big players. Somewhere between a notebook for AI memory and hybrid reasoning for everyone, the field is shifting from expensive experiments to everyday tools. Read more...

Who Did the AI Learn From?

Elena Daehnhardt · 22 Aug, 2025

Large language models learn like Rembrandt's students once did — by studying the masters. But unlike the studio, their sources are hidden. Should AI be more transparent about who it learned from? Read more...

This week in AI

Elena Daehnhardt · 22 Aug, 2025

This week’s AI breakthroughs make the technology feel less like distant research and more like practical tools. From open-source giants and real-time voice recognition to edge creativity, workplace automation, and smarter data reasoning — here are five updates worth your attention. Read more...

Processes

Elena Daehnhardt · 15 Aug, 2025

This post is about managing processes on Linux/macOS and Windows — how to check what’s running, how to stop it (politely or otherwise), and what it means to run things in the background. We’ll explore OS-specific commands and tools such as ps, top, kill, Task Manager, and tasklist, with plenty of examples and the occasional cautionary tale. Read more...

This week in AI

Elena Daehnhardt · 15 Aug, 2025

From Europe’s multilingual AI surge to Google’s ultra-efficient Gemma model, Meta’s self-supervised vision leap, and new tools reshaping AI safety and testing — here are the top AI developments this week. Read more...

Brewing with Homebrew

Elena Daehnhardt · 11 Aug, 2025

In this post, we will provide an overview of Homebrew, a package manager that simplifies installing, updating, and managing software on macOS and Linux. It acts like an "app store" for command-line tools and other developer-centric software. For Windows, Homebrew primarily works within the Windows Subsystem for Linux (WSL). Read more...

Workflow Automation with n8n

Elena Daehnhardt · 11 Aug, 2025

Manual content pipelines inevitably fail at scale. After outgrowing brittle Python cron jobs, I migrated my infrastructure to n8n—a self-hosted, node-based orchestration layer. Here is the technical breakdown of configuring databases, managing OAuth2 security, and deploying AI-driven agents. Read more...

Will SaaS Survive?

Elena Daehnhardt · 8 Aug, 2025

SaaS isn't dying—it's evolving. AI is disrupting traditional workflows and pricing models, but innovative companies are adapting by becoming infrastructure layers, owning domain expertise, and focusing on outcomes rather than interfaces. Read more...

This week in AI

Elena Daehnhardt · 8 Aug, 2025

This week in AI saw groundbreaking releases from industry giants. OpenAI unveiled GPT-5 along with open-source GPT-OS-120b and 20b, making high-end AI accessible from laptops to phones. Google introduced DeepPolisher for genome error correction and Genie 3 for creating interactive virtual worlds. Alibaba launched GSPO powering Qwen3, plus Qwen-Image for free text-to-image generation. Anthropic rolled out Persona Vectors for consistent AI personalities. New mobile-ready AI models and coding assistants rounded out a week that made AI faster, more open, and more integrated into everyday tech. Read more...

Cursor AI for Python Development

Elena Daehnhardt · 4 Aug, 2025

Traditional AI chatbots require you to manually paste code snippets back and forth. Cursor AI fundamentally changes this dynamic by operating as an IDE built entirely around contextual AI agents. Here is my technical review of its RAG-based codebase indexing and Composer features for Python development. Read more...

On AI Coding Assistants

Elena Daehnhardt · 4 Aug, 2025

Not all LLMs write code the same way. After months of prototyping, debugging, and building architectures with Google Gemini, ChatGPT, and Claude AI, here is a technical breakdown of how they compare, and why the Model Context Protocol (MCP) changes everything. Read more...

GitHub Gists

Elena Daehnhardt · 30 May, 2025

Sharing code snippets via Slack or email can lead to formatting issues. GitHub Gists offers a solution for easily sharing or saving code or text for future use. In this post, I explain how to use Gists effectively. Read more...

Self-critical AI

Elena Daehnhardt · 30 May, 2025

Can Large Language Models achieve meta-cognition regarding their own stylistic patterns? In this primary research experiment, I tested Gemini, ChatGPT, and Claude to see if they could not only replicate my human writing style, but actively self-correct when confronted with AI-detection tools like Grammarly. Read more...

My little setback

Elena Daehnhardt · 28 May, 2025

In this post, I write about what's happening in my life and why I did not post these weeks. Read more...

AI Talk with Human Feel

Elena Daehnhardt · 30 Apr, 2025

In this post, I write about Text-to-speech, multilingual voice generation, and voice cloning with the great-quality voices in ElevenLabs. Read more...

Iberia’s Day-long Blackout

Elena Daehnhardt · 29 Apr, 2025

Yesterday, we had a total blackout in Portugal. Around 12:30 p.m. on Monday, the entire Iberian Peninsula went dark. For roughly twelve hours, almost 60 million people in Spain and Portugal—plus pockets of southwestern France—lost grid power, forcing airports, hospitals, and rail hubs onto emergency generators and confusing city centres. Read more...

Vibe coding with Generative AI

Elena Daehnhardt · 27 Apr, 2025

I've been getting into "vibe coding" recently, quickly prototyping some of my ideas, and working on my pet projects. I must confess that the AI-assisted coding is a very addictive activity, and must be taken with caution since it has some security implications and requires a careful prompts engineering. Read more...

Git Log

Elena Daehnhardt · 24 Apr, 2025

The git log command allows you to view your project's history by listing commits with their authors, dates, and messages. It's essential for debugging, tracking changes, and understanding your project's evolution. It is indeed my favourite Git command. Read more...

AI reads my blog

Elena Daehnhardt · 28 Mar, 2025

Traditional SEO is a brutal game for independent bloggers. But recently, I noticed a surge in a different kind of traffic ChatGPT and other AI bots are actively reading my blog. Here is how you can track AI traffic in GA4, manage bot access, and optimise your content to be cited by AI search engines. Read more...

Cross-Validation Techniques

Elena Daehnhardt · 13 Mar, 2025

Building a machine learning model is easy; proving it actually works on unseen data is the hard part. In this post, we cover cross-validation techniques—from traditional K-Fold to Stratified and Time-Series splits—using hands-on examples in scikit-learn. Read more...

How to Use Claude AI

Elena Daehnhardt · 12 Mar, 2025

What is Claude AI? What can we do with it, and how? Let's explore this fantastic AI assistant by Anthropic. Read more...

How CustomGPT Mitigates AI Hallucinations

Elena Daehnhardt · 13 Feb, 2025

CustomGPT reduces AI errors using specialised knowledge, quality data, and user feedback. Along with RAG, it provides accurate and reliable content for various applications. Read more...

Storing Your Local Project to GitHub

Elena Daehnhardt · 12 Feb, 2025

This post shows you how to create a Git repository for your local (Python) project and push it to GitHub using the command line and a personal access token. Following these steps, you can securely host your code on GitHub for easy access and collaboration. Read more...

Python Flask TODO App

Elena Daehnhardt · 11 Feb, 2025

Ready to build your first web application? In this tutorial, we will construct a fully functional TODO app using Python, Flask, and SQLite. You will learn how to route requests, manage a database, and render HTML templates. Read more...

Is DeepSeek R1 Secure?

Elena Daehnhardt · 1 Feb, 2025

There is a big question about DeepSeek's security (and also the security of any software product, in fact), safety, and legal usage outside of China. I am sharing my opinion and some relevant links on this topic. Read more...

DeepSeek R1 With Ollama

Elena Daehnhardt · 28 Jan, 2025

This post explores the use of Ollama, a state-of-the-art language modelling framework, in conjunction with pre-trained models such as DeepSeek R1. Read more...

Python Virtual Environments

Elena Daehnhardt · 24 Jan, 2025

If you are working on multiple Python projects, you will eventually run into a dependency nightmare. Virtual environments solve this by isolating packages per project. Here is my practical guide to creating, managing, and safely deleting Python virtual environments. Read more...

AI in 2024

Elena Daehnhardt · 31 Dec, 2024

As 2025 approaches, let's reflect on 2024's key AI advancements, including specialized models, growth in AI creativity, and the introduction of the AI Act. Here are my thoughts on the notable events. Read more...

Multimodal AI

Elena Daehnhardt · 28 Dec, 2024

Multimodal AI is rapidly evolving, pushing the boundaries of what machines can understand and achieve by combining information from multiple modalities like text, images, audio, and video. This post explores the core techniques of realising multimodal AI, existing systems and related research. Read more...

🌟 Merry Christmas and a Very Happy New Year! 🌟

Elena Daehnhardt · 23 Dec, 2024

As we approach 2025, I wish my readers a joyful, healthy, and successful New Year! Read more...

Three years of Elena's AI Blog 🎈

Elena Daehnhardt · 8 Dec, 2024

We live in this era of rapid AI evolution, which is yet challenging to understand and live in, even for people with computer science backgrounds. I like, however, to make things easy to understand while learning new technologies as a passion. My blog, now three years old, connects technology with everyday understanding, reflecting my passion for coding and commitment to making complex concepts accessible. Read more...

My Orthopedic Rehab in Bavaria

Elena Daehnhardt · 7 Dec, 2024

Andreas and I are in Bavaria, Germany, doing our rehab with some fantastic results. You see the first snow view out of a window of our clinic. It is so beautiful here in Bavaria, which helps people recover physically and mentally. Read more...

Generative AI vs. Large Language Models

Elena Daehnhardt · 4 Dec, 2024

Generative AI and Large Language Models (LLMs) are both important concepts in artificial intelligence, but they are not the same. Generative AI refers to different models that can create various types of content, such as text, images, and music. LLMs are a specific type of generative AI that focuses on understanding and producing human language. This post explains their differences, highlights key techniques like Transformers and GANs, and mentions important open-source projects. Read more...

Celebrate Halloween with AI

Elena Daehnhardt · 27 Oct, 2024

Halloween, celebrated on October 31, has its roots in ancient Celtic rituals. Halloween allows us to unleash our creativity by crafting spooky costumes and decorations. In this post, I will suggest several ways to celebrate Halloween with the help of AI. AI can provide eerie sound effects, assist in costume design, offer voice modification features, and present fun filters for your face. Enjoy the celebration! Read more...

Gaining muscles, losing weight

Elena Daehnhardt · 26 Oct, 2024

Rehabilitating from a knee operation can be challenging, but it's possible to transform your body while recovering. I want to share my story of losing weight and improving my strength after a severe knee injury. Read more...

Avoid SEO Penalties on Medium

Elena Daehnhardt · 10 Oct, 2024

Republishing your blog posts on Medium is a smart way to reach a wider audience and enhance engagement without compromising your original content's SEO value. This post explains how to properly use canonical tags to avoid duplicate content issues when republishing. Read more...

What is RAG? How Retrieval-Augmented Generation actually works

Elena Daehnhardt · 8 Oct, 2024

Large language models are impressive, but they suffer from a major flaw they hallucinate facts because they are essentially just predicting the next word. Retrieval-Augmented Generation (RAG) fixes this by grounding the AI in verified data before it answers. Here is an overview of how it works and the current state of research. Read more...

Git Checkout for overwriting directories from different branches

Elena Daehnhardt · 22 Sep, 2024

To overwrite the "scripts" directory in the master branch with the files from the "scripts" directory of the "dev" branch, you can use the Git checkout command. Just be cautious, as this will completely replace the files in the destination branch. Read more...

Regaining Website Traffic After Google Updates

Elena Daehnhardt · 19 Aug, 2024

As a small website owner, I understand the challenges we face. I write about AI and Python coding, sharing my knowledge with fellow professionals and students. However, the recent Google updates have led to a significant drop in traffic. With Google providing over 90% of our traffic, the struggle to regain our website visits is real. Is there any information about the Google SE website feature that's crucial or any ranking details shared publicly? Read more...

I have started to walk again

Elena Daehnhardt · 18 Aug, 2024

After a knee operation and slow recovery, I'm improving my walking stamina and muscle strength. This experience gave me a new perspective on mobility issues and time management. I've learned to appreciate the value of pausing and reflecting. I'm grateful for the support of family, friends, and medical staff. It's important to prioritize exercise and time. Read more...

Logging in Python

Elena Daehnhardt · 27 Jul, 2024

In this post, I cover everything from the basics of logging to configuring logging to output messages to different destinations. I also included some examples of logging levels and how to log messages at different levels based on the severity of the issue. Read more...

Guest posts about AI and Python

Elena Daehnhardt · 26 Jul, 2024

This blog is not only about coding or AI; it is about living with AI in human society, striving for happiness and building on technological advances. You can publish your quest post about anything related to Python coding and AI. It is easy. I will explain how. Read more...

Regulation on artificial intelligence has already been published

Cláudia Lima da Costa · 14 Jul, 2024

The AI Regulation has already been published, and it will imply compliance with several obligations, such as transparency and human oversight, when the AI System is deemed high-risk. It is important to remain updated and understand how this regulation will be applied. Read more...

Git Remotes

Elena Daehnhardt · 24 Jun, 2024

This post is about managing remote repositories in Git. We explore tasks such as adding, renaming, removing remotes, and updating remote URLs. We also practice fetching, pulling, and pushing changes to and from remote repositories. Read more...

Narrow AI, General AI, Superintelligence, and The Real Intelligence

Elena Daehnhardt · 21 Jun, 2024

I discuss the main AI types in this post. I share my understanding of the possibility of general intelligence in the future. Read more...

ARC-AGI benchmark and a hefty prize

Elena Daehnhardt · 15 Jun, 2024

I am sharing information about the recent Kaggle competition launch, which focuses on advancing general intelligence. Read more...

Sending Emails with Python and receiving your messages

Elena Daehnhardt · 29 May, 2024

Running a static site on GitHub Pages means I don't have a backend to process forms or send newsletters. But that hasn't stopped me. Here is how I handle incoming messages, and how I use Python and Gmail to send automated emails. Read more...

Can AI hallucinate?

Elena Daehnhardt · 23 May, 2024

AI hallucinations are a critical phenomenon in AI, referring to instances where AI systems generate inaccurate or nonsensical information. This post explores the main causes of AI hallucinations, their implications, possible benefits, and existing solutions. Read more...

How recommendation engines actually work (with Python code)

Elena Daehnhardt · 8 May, 2024

Ever wondered how Netflix or Spotify manages to guess what you want to watch or listen to next? The secret lies in recommendation algorithms. Here is a look at the math behind collaborative and content-based filtering, and how to implement them in Python. Read more...

To cite or perish

Elena Daehnhardt · 4 May, 2024

Proper citation is a must to maintain academic and ethical integrity. It is a valuable skill that promotes respect for other people, creates a chain of arguments paramount in research and science, and protects one's life efforts in the future. Herein, I write my approach to citation. This might be useful for my student readers. Read more...

Go with the flow

Elena Daehnhardt · 2 May, 2024

I recently underwent a major operation due to an accident, which required me to put all my energy into rehabilitation and training. I pushed myself harder than ever before and worked tirelessly towards my recovery. It was a challenging experience, shared in this post. Read more...

Robots and True Love

Elena Daehnhardt · 10 Apr, 2024

In this post, I write about robots and their creation challenges in real-life tasks, research areas, safety and ethical considerations, and future aspirations. I also briefly refer to a few starting points for creating robots with Raspberry Pi and Python. Read more...

Virtual Presenters (AI Avatars in-depth)

Elena Daehnhardt · 31 Mar, 2024

Digital humans are taking over training modules and marketing videos, and the technology is surprisingly accessible. Here is a look at my favourite platforms for creating AI avatars, plus a quick guide to generating your own in Python. Read more...

Super-girls don't cry in face-swaps

Elena Daehnhardt · 18 Mar, 2024

I wanted to see myself flying over Niagara Falls as a superhero. Here is how I did it — InsightFace Bot, Midjourney, and a Python/OpenCV implementation with Haar cascades and seamless blending. Read more...

Podcast: How can we build trust and safety around AI?

Elena Daehnhardt · 17 Mar, 2024

Lawyer Cláudia Lima Costa is an expert in Artificial Intelligence and has created an amazing podcast that raises pertinent questions about trust and safety in AI systems. I was fortunate enough to be invited to a relaxed discussion where I shared my views on various topics related to AI, such as AI evolution, AI applications, data sources for training models, copyright, data protection, privacy-preserving techniques, and achieving reliable, explainable, safe, and helpful AI. Read more...

Explainable AI is possible

Elena Daehnhardt · 21 Feb, 2024

The complexity of AI, particularly deep learning models, has led to the "black box" criticism, highlighting the lack of understanding about how deep learning models arrive at their decisions. While there's truth to this concern, having a nuanced view is important. In this post, I share my view on AI explainability, that it is complex, however possible. Read more...

OpenAI's Model Show-off

Elena Daehnhardt · 19 Feb, 2024

OpenAI's GPT models are highly sophisticated machine learning models that are used in various fields such as natural language processing, coding assistance, and content creation. OpenAI's newest video-generating model, Sora, sets a new benchmark in video generation technology, which I quickly explore in this post. Read more...

In-love with the chatbot

Elena Daehnhardt · 13 Feb, 2024

In the age of artificial intelligence, where chatbots are becoming increasingly sophisticated, the concept of falling in love with a chatbot is no longer a far-fetched idea. While some may question the possibility of a genuine emotional connection with a machine, there are individuals who have developed strong emotional attachments to these digital companions. Read more...

What is Docker?

Elena Daehnhardt · 11 Feb, 2024

Docker lets you quickly deploy microservices, cloud-native architectures, or web apps. In this post, we will use Docker to create a reliable environment for Flask applications that efficiently manages dependencies and deployment intricacies. Read more...

chatGPT and Friends

Elena Daehnhardt · 28 Jan, 2024

ChatGPT is a powerful language model that has revolutionised the way we interact with technology. This post explores ChatGPT and its alternatives, delving into their capabilities, applications, and ethical considerations. Read more...

AI Synthesised Voices

Elena Daehnhardt · 9 Jan, 2024

In this post, I discuss voice synthesis and cloning, and mention fantastic AI tools and APIs for creating high-quality human-like voices from text or for automatic voice dubbing. Read more...

How I Built This Blog — and How You Can Too

Elena Daehnhardt · 6 Jan, 2024

I get asked how I built this blog more often than almost anything else. Here is the honest answer — GitHub Pages, Jekyll, Markdown, a sprinkle of HTML, and a form service that keeps spam out. No WordPress, no server bills, full control. Read more...

✨ Merry Christmas and Happy New Year with AI! 🎆🎇

Elena Daehnhardt · 23 Dec, 2023

Merry Christmas and a Very Happy New Year! I wish you much health, happiness and love in 2024. I am also sharing a few AI apps to celebrate the new year. All the best! Read more...

🎉✨ Cheers to new beginnings 🎊✨

Elena Daehnhardt · 12 Dec, 2023

This year, this website changed its design and became responsive and dark-mode friendly; we have added more than 30 content-rich posts on coding and AI and tested fantastic AI apps. With heartfelt thanks for your unwavering support, we wish our friends and readers a 2024 filled with health, joy, love, and boundless possibilities. Read more...

Joking Flask App

Elena Daehnhardt · 10 Dec, 2023

Build a joke-serving web app with Flask from scratch. We cover routing, Jinja2 templates, static files, form handling, and how to avoid the classic "request is not defined" trap. Read more...

Restoring deleted files in Git

Elena Daehnhardt · 5 Dec, 2023

A late-night Wi-Fi glitch wiped a folder of images from my Git repository. Here is exactly how I got them back—and what I learned about navigating Git history along the way. Read more...

Living with AI in Pursuit of Happiness

Elena Daehnhardt · 29 Nov, 2023

This blog is not about coding or AI; it is about living with AI in human society, striving for happiness and building on technological advances. Read more...

Blog Writing with AI in MindStudio

Elena Daehnhardt · 29 Nov, 2023

BlogGenie created a draft of this post at YouAI (MindStudio) and aims to demonstrate how AI writing assistants can streamline the blog generation process. It focuses specifically on leveraging YouAI for overall framing and BlogGenie for on-page SEO best practices. This allows for creating initial drafts in seconds rather than hours. You still have to edit and correct an outline to finalise your post. Read more...

Creating Websites with AI on Mixo.io

Elena Daehnhardt · 23 Nov, 2023

Have you ever wished for a website that writes itself? This dream is now a reality thanks to the advancement in Artificial Intelligence (AI). With Mixo.io, you can create stunning websites using AI technology--in minutes! In this blog post, we will explore website creation with Mixo.io. Read more...

Bright ideas at Web Summit 2023

Elena Daehnhardt · 20 Nov, 2023

In this post, I write about my experience attending the World's largest and most prominent technology conferences. I had the pleasure of attending ten technology-focused tracks of Web Summit. What did I learn? Was the Web Summit useful for me? Read more...

Cool Wallpaper with QR code for iPhone

Elena Daehnhardt · 17 Nov, 2023

When my iPhone is locked, I can share my website address with a QR code. How to use reportlab and Python to generate a QR code for the iPhone wallpaper? Read more...

Bias-Variance Challenge

Elena Daehnhardt · 10 Nov, 2023

In machine learning, we usually start from a simple baseline model and progressively adjust its complexity until we reach that spot with the best model performance. How can we do this? Let's detail the most essential machine learning concepts and the bias-variance challenge. Read more...

Travelling, just sent my e-mails

Elena Daehnhardt · 7 Nov, 2023

I am on my way. You have received my email if you subscribed :) Read more...

Decision Tree versus Random Forest, and Hyperparameter Optimisation

Elena Daehnhardt · 6 Nov, 2023

Decision trees, with their elegant simplicity and transparency, stand in stark contrast to the robust predictive power of Random Forest, an ensemble of trees. In this post, we compare the key distinctions, advantages, and trade-offs between these two approaches. We will use Scikit-Learn for training and testing both models and also perform hyperparameter optimisation to find both model parameters for improved performance. Read more...

Machine-Learning Process

Elena Daehnhardt · 30 Oct, 2023

The machine learning process involves a series of steps and activities designed to develop and deploy machine learning models to solve specific problems or make predictions. To simplify, we create programs that take in data and produce desired results in machine learning. There are several stages in the machine-learning process that we briefly describe in this post. Read more...

The water genie told me a story

Elena Daehnhardt · 11 Oct, 2023

I am back home. I have had nine flights in the last month and feel exhausted. I was delighted to see my family and had a few things to do. So happy that it all went well. Come again later and plunge into the whole sea of machine learning travel. It will be technical. We will start with a droplet and will come with more later. Read more...

Two years of Elena's AI Blog

Elena Daehnhardt · 20 Sep, 2023

Elena, a passionate AI blogger with a background in engineering and consultancy, brings her expertise and a mission to demystify machine learning for her readers. Read more...

Why AI will never void humanity?

Elena Daehnhardt · 14 Sep, 2023

Why AI will never void humanity? What AI wants badly? I was thinking about these questions while travelling. I will share my initial thoughts with you, my dear reader. Read more...

Generate Music with AI

Elena Daehnhardt · 24 Aug, 2023

In this post, we will get into music generation with AI. We will briefly explore existing AI applications generating audio. We will explore transformer usage while coding music generation with HuggingFace transformers in Python. Read more...

A Warm August and Vacation

Elena Daehnhardt · 19 Aug, 2023

In this post, I write about what's happening in my life. August 2023 is quite warm, and I have decided to have a short vacation, which is much needed since I am preparing a surprise for you, my dear reader. Read more...

AI-Free Website Design

Elena Daehnhardt · 8 Aug, 2023

In this post, I write about my efforts in creating CSS and HTML pages for my website with chatGPT and why I ended up doing it myself while learning from the bot, Google Search, CodePen and w3schools. Read more...

Preserve your local changes on Git Pull

Elena Daehnhardt · 2 Aug, 2023

When we get the Git error on pull - your local changes to the following files would be overwritten by merge - it means that you have some uncommitted changes in the working directory. Git cannot perform the merge operation because those changes would be lost or overwritten during the merge process. Read some good solutions to resolve this error while keeping local changes. Read more...

Leveraging Git Tags

Elena Daehnhardt · 21 Jul, 2023

Git tags are useful for marking specific points in a repository's history, such as release points or important milestones. They provide a way to easily reference and access specific versions of your codebase. Let's dive deeper into the details of working with Git tags. Read more...

GPT Implications for Coding

Elena Daehnhardt · 25 Jun, 2023

The AI evolution has implications for programming and programmer jobs. GPT usage allows for quicker product releases and a focus on user requirements. However, low-coding jobs could be delegated to AI, new skills for AI-assisted programming be required or access to sophisticated models only available to some. The new coding age is upon us. In this blog post, I highlight the opportunities and challenges of AI-assisted code generation and share my experiences using chatGPT. Read more...

Moving to GA4

Elena Daehnhardt · 24 Jun, 2023

On July 1st, we are moving to GA4, which is essential to ensure that our website analytics are processed without delay due to the transition. Herein I share my GA4 setup in Google Analytics. Read more...

Mastering Midjourney Prompts for Stunning Images

Elena Daehnhardt · 17 Jun, 2023

In this post, I write about creating stunning designs in Midjourney. We create AI-generated designs for an ice cream cafe. In the end, I list all prompts and handy keywords to take away for your fantastic own creations. Read more...

Git Failed to Push Some Refs

Elena Daehnhardt · 5 Jun, 2023

I was away from my big MAC computer and did some repository updates using my laptop. When arriving back, I could not push an update from my big MAC computer. Git updates were rejected because my current branch is behind. That happens quite often when we should integrate the remote changes before pushing git updates. Herein I am sharing possible solutions in detail. Read more...

The Magic of AI Tools

Elena Daehnhardt · 30 May, 2023

In this post, I list some of my favorite AI applications for productivity and fun. Read more...

The Remarkable Evolution and Milestones of AI

Elena Daehnhardt · 23 May, 2023

In this post, I outline the AI evolution and its most prominent milestones with chatGPT and Midjourney. Read more...

Loop like a Pro with Python Iterators

Elena Daehnhardt · 18 May, 2023

This post explains the basics of Python iterators and their successful alternatives, such as list comprehension. While these alternatives use more memory, they are still useful in practice. The post also covers advanced techniques for working with iterators, including using the itertools module and creating generators with the yield keyword. By mastering iterators, readers can create elegant and efficient code and become better Python programmers. Read more...

The Token Way to GitHub Security

Elena Daehnhardt · 8 May, 2023

In this brief post I describe the setup and usage of GitHub personal access tokens. Read more...

From Dutch Golden Age to AI Art: A Journey with Vermeer and AI

Elena Daehnhardt · 18 Apr, 2023

In this post, I collaborated with ChatGPT to explore the captivating World of Dutch art and Johannes Vermeer. As an art critic and historian, ChatGPT provides fascinating insights into Vermeer's masterpieces and the historical events that influenced them. I also share my emotional experience of visiting a Vermeer art exhibition, and we'll have some fun creating AI art with Jasper.ai, DALL-E, Stable Diffusion Playground and Midjourney bot. Take advantage of my tips for refining ChatGPT's output and the prompts I used to get the best results. Join me on this adventure and discover the beauty of Dutch art and AI-art outcomes! Read more...

The SSH host key mystery

Elena Daehnhardt · 10 Apr, 2023

What do you call a developer who's afraid of the dark? A Git-in-the-middle attacker! But seriously, if you've ever seen a warning message about a changed SSH host key while pushing code changes, don't panic - it might just be a legitimate update. To fix the issue, simply delete the saved RSA key fingerprint and let the SSH client verify the new one. And remember, always keep an eye out for those pesky man-in-the-middle attackers lurking in the shadows! You can learn how to create and use SSH keys, explained so simply in this post. Read more...

The Most Useful AI-Content and Plagiarism Detection Tools

Elena Daehnhardt · 15 Mar, 2023

With the development of AI-content generators such as chatGPT, we have a new need to identify such content, and the tools of AI-content detection are currently being developed. Writing assistants and plagiarism detection tools also include AI-content detection. In this post, I talk about the most visible AI tools that help us mitigate plagiarism and motivate us to create original and well-written content. Indeed, I will start with the definition of plagiarism, why it's terrible, and move quickly into helpful tools in AI-content and plagiarism detection that are available today. Read more...

Audio Signal Processing with Python's Librosa

Elena Daehnhardt · 5 Mar, 2023

In this post, I focus on audio signal processing and working with WAV files. I apply Python's Librosa library for extracting wave features commonly used in research and application tasks such as gender prediction, music genre prediction, and voice identification. To succeed in these complex tasks, we need a clear understanding of how WAV files can be analysed, which I cover in detail with handy Python code snippets. Read more...

Machine Learning Tests using the Titanic dataset

Elena Daehnhardt · 10 Feb, 2023

In this post, we created and evaluated several machine-learning models using the Titanic Dataset. We have compared the performance of the Logistic Regression, Decision Tree and Random Forest from Python's library scikit-learn and a Neural Network created with TensorFlow. The Random Forest Performed the best! Read more...

Say Goodbye to Grammar Gaffes with Grammarly!

Elena Daehnhardt · 1 Feb, 2023

Grammarly is a writing tool that helps users improve their grammar, punctuation, and spelling. It is designed to be an effective tool for native and non-native English speakers. It can be used as a browser extension or an app and be integrated with various platforms, such as Microsoft Word and Google Docs. I like to have also my writing progress reports sent weekly to see my writing performance and areas to improve. In this post, I share my Grammarly experience and discuss the technology behind Grammarly-like tools. Read more...

Data exploration and analysis with Python Pandas

Elena Daehnhardt · 20 Jan, 2023

In Data Science, we have so many terms explaining concepts and techniques that it is easy to need clarification and get a clear understanding of all data science components and steps. In this post, I filled the gap by explaining data science's two essential components, data analysis and exploration. To clarify things, I have shown both approaches, compared them, and provided Python code using Pandas dataframe and graph drawing. Read more...

Python coding with chatGPT

Elena Daehnhardt · 2 Jan, 2023

In this post, I did some Python coding with chatGPT. We have coded a neuron, a simple neural network, and learned how to train it. I am pleased with the result. I think that chatGPT has excellent potential for CS students and all coders that want to update their skills effectively. Is it an end of the StackOverflow? We cannot see the feature. However, we still need social interaction with humans, and AI cannot substitute human communication. Read more...

Happy New Year!

Elena Daehnhardt · 1 Jan, 2023

My best wishes for 2023! I wish you happiness, health, and excellent luck in the New Year! Let your best wishes come true, and your professional goals are achieved with success! Read more...

chatGPT Wrote me a Christmas Poem

Elena Daehnhardt · 19 Dec, 2022

In this post, I shared my thoughts on chatGPT, its technology, and its possible societal implications. I also asked it to write a Christmas poem for me, which was pretty good! Read more...

SEO and Indexing my Blog

Elena Daehnhardt · 14 Nov, 2022

Today, I received an email from the Google search console team informing me about an issue with my blog pages related to a duplicate without a user-selected canonical. I was intrigued about making my blog more search engine friendly and seeing what happens after SEO. Read more...

Git Commands and a Contribution Workflow

Elena Daehnhardt · 7 Nov, 2022

I have created a list of arguably the most useful Git commands and an example contribution workflow. I have also found a great JavaScript application for learning Git branching! Read more...

Learning new things

Elena Daehnhardt · 28 Sep, 2022

Computer Science, Data Science, Machine Learning, databases, coding, data wrangling, math, statistics, linear algebra, matrix operations, and many other things. This list is broad and constantly updated with new things. How to find your path and not lose yourself along the way? Students or novice Data Scientists often approach me about where to begin. I do not know, but I am sharing my ideas in this post. Read more...

Linters and Git Pre-commit

Elena Daehnhardt · 11 Sep, 2022

It's great to focus on code development while keeping the coding style right. This could be achieved with automatic formatting checks before committing files into the code repository. In this post, I have described the pre-commit usage with git hooks and a simple setup for checking Python files. Read more...

Python classes and pigeons

Elena Daehnhardt · 1 Sep, 2022

Happy 1st of September, dear visitors. I have decided to write a letter to you. The letter concerns pigeons and Python classes, the essential OOP concepts such as inheritance, polymorphism, and encapsulation. Read more...

Reverting Commits in GitHub

Elena Daehnhardt · 26 Aug, 2022

This post is about reverting your changes in GitHub. Sometimes it's good to step back and think about something different, right? With the use of git reset, revert and rebase we can remove changes from commits or even history. Read more...

MAC OS Speed Up

Elena Daehnhardt · 7 Aug, 2022

After a while, my Mac OS computer started to work slower. I have searched for possible solutions to run my computer faster without much latency. We can upgrade our computer storage and install a more powerful processor unit to speed up Mac OS. In this blog post, I will, however, focus on a more straightforward way without any system upgrades, which are costly and take time. Read more...

TensorFlow: Romancing with TensorFlow and NLP

Elena Daehnhardt · 11 Jul, 2022

In this post we will create a simple poem generation model with Keras Sequential API. Read more...

Collaboration in GitHub

Elena Daehnhardt · 10 Jun, 2022

In this post, I have covered GitHub collaboration when working with other team members. Git branching, forking, pull requests, and issues were briefly explained. Read more...

Floating-point format and Mixed Precision in TensorFlow

Elena Daehnhardt · 19 May, 2022

When creating large Machine Learning models, we want to minimise the training time. In TensorFlow, it is possible to do mixed precision model training, which helps in significant performance improvement because it uses lower-precision operations with 16 bits (such as float16) together with single-precision operations (f.i. using float32 data type). Google TPUs and NVIDIA GPUs devices can perform operations with 16-bit datatype much faster Read more...

Coding in Portugal

Elena Daehnhardt · 5 May, 2022

I am in Portugal. I live and breathe the freshness of the Ocean. Its vivid colors and wind make me happy, and I feel like a part of something bigger, omnipresent, and eternal. The springtime is the best time to be here when you like flowers and delicate fragrances loating in the air. Read more...

TensorFlow: Evaluating the Saved Bird Species Prediction Model

Elena Daehnhardt · 2 May, 2022

In this post, I have described the process of in-depth model evaluation. I have reused the previously created EffecientNetB0 model, which is fine-tuned with the 400 Bird Species Kaggle dataset. As a result, I have found out which bird species are not well predicted. Read more...

TensorFlow: Transfer Learning (Fine-Tuning) in Image Classification

Elena Daehnhardt · 6 Apr, 2022

We used a 400 species birds dataset for building bird species predictive models based on EffeicientNetB0 from Keras. The baseline model showed already an excellent Accuracy=0.9845. However, data augmentation did not help in improving accuracy, which slightly lowered to 0.9690. Further, this model with a data augmentation layer was partially unfrozen, retrained with a lower learning rate, and reached an Accuracy=0.9850. Read more...

Anaconda Environments

Elena Daehnhardt · 5 Apr, 2022

It might be challenging to manage different projects and their requirements when we do Python coding with loads of varying package versions and intricate setups. Luckily, we have a secret tool for managing and switching between different setups or environments. Conda is a package manager allowing us to work with different environments from a command line. Please do not mix it up with the Anaconda, which is helpful in scientific computing and includes a set of packages including NumPy, Scipy, Jupiter notebooks, and Conda. Read more...

TensorFlow: Transfer Learning (Feature Extraction) in Image Classification

Elena Daehnhardt · 3 Mar, 2022

Image classification is a complex task. However, we can approach the problem while reusing state-of-the-art pre-trained models. Using previously learned patterns from other models is named "Transfer Learning." This way, we can efficiently apply well-tested models, potentially leading to excellent performance. Read more...

TensorFlow: Convolutional Neural Networks for Image Classification

Elena Daehnhardt · 19 Feb, 2022

In this post, I have demonstrated CNN usage for birds recognition using TensorFlow and Kaggle 400 birds species dataset. We observed how the model works with the original and augmented images. Read more...

TensorFlow: Multiclass Classification Model

Elena Daehnhardt · 6 Feb, 2022

In Machine Learning, the classification problem is categorising input data into different classes. For instance, we can categorise email messages into two groups, spam or not spam. In this case, we have two classes, we talk about binary classification. When we have more than two classes, we talk about multiclass classification. In this post, I am going to address the latest multiclass classification, on the example of categorising clothing items into clothing types. Read more...

Feature preprocessing

Elena Daehnhardt · 29 Jan, 2022

Machine Learning algorithms often require that data is in a specific type. For instance, we can use only numerical data. In other cases, ML algorithms would perform better or converge faster when we preprocess data before training the model. Since we do this step before training the model, we call it preprocessing. Read more...

TensorFlow: Evaluating the Regression Model

Elena Daehnhardt · 25 Jan, 2022

In this post, we have performed the evaluation of four regression models using TensorFlow. MAE and MSE error metrics were used to compare the Sequential models while finding the best neural network architecture regarding the defined hyperparameters. Read more...

TensorFlow: Regression Model

Elena Daehnhardt · 21 Jan, 2022

I have described regression modeling in TensorFlow. We have predicted a numerical value and adjusted hyperparameters to better model performance with a simple neural network. We generated a dataset, demonstrated a simple data split into training and testing sets, visualised our data and the created neural network, evaluated our model using a testing dataset. Read more...

TensorFlow: Global and Operation-level Seeds

Elena Daehnhardt · 15 Jan, 2022

In training Machine Learning models, we want to avoid any ordering biases in the data. In some cases, such as in Cross-Validation experiments, it is essential to mix data and ensure that the order of data is the same between different runs or system restarts. We can use operation-level and global seeds to achieve the reproducibility of results. Read more...

Tensors in TensorFlow

Elena Daehnhardt · 13 Jan, 2022

TensorFlow is a free OS library for machine learning created by Google Brain. Tensorflow has excellent functionality for building deep neural networks. I have chosen TensorFlow because it is pretty robust, efficient, and can be used with Python. In this post, I am going to write about how we can create tensors, shuffle them, index them, get information about tensors with simple examples. Read more...

GitHub Codespaces

Elena Daehnhardt · 5 Jan, 2022

GitHub codespaces provide a development environment running in the cloud. A codespace environment is created with the help of configuration files added to a GitHub repository. Read more...

TensorFlow on M1

Elena Daehnhardt · 5 Jan, 2022

TensorFlow is a free OS library for machine learning created by Google Brain. Tensorflow has excellent functionality for building deep neural networks. I have chosen TensorFlow because it is pretty robust, efficient, and can be used with Python. Since I like Jupyter Notebooks and Conda, they were also installed on my system. Next, I am going through simple steps to install TensorFlow and the packages above on M1 macOS Monterey. Read more...

Mining Microblogs for Culture-awareness in Web Adaptation

Elena Daehnhardt · 3 Jan, 2022

In this post, I am briefly writing up about what I did in my PhD research at Heriot-Watt University and the main idea behind the thesis. Read more...

Artificial Neural Networks

Elena Daehnhardt · 17 Dec, 2021

Artificial neural networks (ANNs) are the cornerstone of Deep Learning algorithms. The name and the architecture are adopted from the human brain's neural network. ANNs are designed to simulate human reasoning based on how neurons communicate. ANNs contain a set of artificial neurons connected. Read more...

Minimalism in Coding and Design

Elena Daehnhardt · 16 Dec, 2021

Nowadays, technology advances so rapidly that I sometimes feel like running after leaving the train. More technical knowledge is needed every day. Yesterday, it was GIT and workflows, and today it is Docker. What is next? Read more...

Deep Learning with DataCamp and Twitter

Elena Daehnhardt · 13 Dec, 2021

While having some machine learning experience of working with Scikit Learn, I was always interested in Deep Learning. The plan is to learn basic concepts and apply algorithms to a real-life situation, which I have always liked. Read more...

GIT in 10 minutes

Elena Daehnhardt · 4 Dec, 2021

Version control systems are handy to keep track of file versions. This is useful for tracking your code, scripts and text information. Currently, GIT is one of the best open-source and cross-platform version control solutions. It enables distributed repository management; it works fast over HTTP and ssh protocols. GIT is relatively easy to use, with command-line utility or Graphical User Interface. Read more...

Are we raising from ashes?

Elena Daehnhardt · 2 Dec, 2021

The Phoenix bird is a fantastical bird known from ancient Greeks mythology. Read more...

Merry Xmas and a Very Happy New Year!

Elena Daehnhardt · 1 Dec, 2021

It was quite a challenging year so far. Many things happened, a rollercoaster of 2021, and we are still riding with the pandemics. But I am very grateful that my dear people are all well. This is what I wish for the following year. Read more...

Python Programming Language

Elena Daehnhardt · 28 Oct, 2021

Python is relatively easy to learn and beginner-friendly. I like Python because you can program any kind of project with it. It is open-source and free for anyone to use. Python has well-tested machine learning libraries and a very supportive community. I will overview herein a basic syntax of the Python programming language. This will be useful for beginners or people who move quickly from another programming language to Python. Read more...

Hi! I'm Elena. Welcome to my blog.

Elena Daehnhardt · 20 Oct, 2021

I'm a machine learning engineer and researcher. I have been fascinated by computer science, Artificial Intelligence, technology, and philosophical questions from an early age. Read more...

Tools and Data to Experiment with Machine Learning

Elena Daehnhardt · 19 Oct, 2021

Python open-source library scikit-learn provides a comprehensive selection of machine learning techniques (regression, classification, clustering), feature selection, metrics, preprocessing, and other functionality. At this moment, Scikit-learn, is lacking deep learning functionality; however, we can use TensorFlow with the Scikit Flow wrapper for creating neural networks using the Scikit-learn approach. Read more...

Deep Learning vs Machine Learning

Elena Daehnhardt · 16 Oct, 2021

Artificial Intelligence (AI) is a field of computer science. AI provides methods and algorithms to mimic human intelligence, reasoning, and decision-making and provide insights, which businesses could use in research or industry to build new exciting and innovative products or services. Machine Learning (ML) is a subset of AI with algorithms that learn from data. In this post, we sort out the differences between AI and ML. Read more...