Day 97/100 of #100DaysWithAI 🖥️

Claude Code without a terminal: the desktop Code tab runs a session locally, in the cloud or over SSH, and shows each change as a diff.

🔗 https://github.com/aurimas13/100-Days-With-AI

#LearningInPublic #AgenticAI

🤝 Claude Code-assisted, reviewed by me.

Day 96/100 of #100DaysWithAI 🧰

Yesterday: agent = model + harness. Today, Anthropic's quickstart that hosts the harness: agent, environment, session, events.

🔗 https://github.com/aurimas13/100-Days-With-AI

#LearningInPublic #AgenticAI

🤝 Claude Code-assisted, reviewed by me.

Day 95/100 of #100DaysWithAI 🐎

11 coding-agent harnesses, ~4M lines of source: none imports an agent framework, none retrieves code with embeddings. They grep.

🔗 https://github.com/aurimas13/100-Days-With-AI

#LearningInPublic #AgenticAI

🤝 Claude Code-assisted, reviewed by me.

Day 94/100 of #100DaysWithAI 🌱

MIT's Dear Dreamer keeps the same 24 startup steps for pupils, "presented differently". The curriculum is the product. AI delivers it.

🔗 https://github.com/aurimas13/100-Days-With-AI

#LearningInPublic #EdTech

🤝 Claude Code-assisted, reviewed by me.

Day 93/100 of #100DaysWithAI 🎙️

Gemini 3.8 Live Extended Thinking reasons and speaks at once. "Let me check that…" now covers tool calls running in the background.

🔗 https://github.com/aurimas13/100-Days-With-AI

#LearningInPublic #AgenticAI

🤝 Claude Code-assisted, reviewed by me.

Day 92/100 of #100DaysWithAI 📚

Peter Norvig: students can skip the logic half of his AI textbook, but the LLM should read all of it. Neural core, logic on top.

🔗 https://github.com/aurimas13/100-Days-With-AI

#LearningInPublic #LLM

🤝 Claude Code-assisted, reviewed by me.

Day 91/100 of #100DaysWithAI ✂️

A cell chooses what crosses its membrane. Context Language Models let an LLM edit its own context as a file and choose what stays.

🔗 https://github.com/aurimas13/100-Days-With-AI

#LearningInPublic #AgenticAI

🤝 Claude Code-assisted, reviewed by me.

Day 90/100 of #100DaysWithAI ⚖️

You don't run a mass spectrometer to check pH. On HumanEval, Sonnet 4 edged Opus 4, 95.1% to 94.5%. Route by task, not by tier.

🔗 https://github.com/aurimas13/100-Days-With-AI

#LearningInPublic #LLM

🤝 Claude Code-assisted, reviewed by me.

Day 89/100 of #100DaysWithAI 🔬

Chemists identify a molecule by its structure, not its name. SlopShape spots AI blog posts that way: 97.0 F1, still 96.1 when reworded.

🔗 https://github.com/aurimas13/100-Days-With-AI

#LearningInPublic #GenAI

🤝 Claude Code-assisted, reviewed by me.

Day 88/100 of #100DaysWithAI 🎙️

VoiceStudio puts voice cloning, dubbing and dictation in one open-source app that runs on your own GPU, or slower on CPU.

🔗 https://github.com/aurimas13/100-Days-With-AI

#LearningInPublic #OpenSource

🤝 Claude Code-assisted, reviewed by me.

Day 87/100 of #100DaysWithAI 🔐

Sealed reasoning blocks were portable: feed one model's encrypted thinking to a weaker sibling and it read it aloud. Now mitigated.

🔗 https://github.com/aurimas13/100-Days-With-AI

#LearningInPublic #AISecurity

🤝 Claude Code-assisted, reviewed by me.

Day 86/100 of #100DaysWithAI 🧰

I built Day 12's guide into a live coding agent: https://code.aurimas.io. Tests passed; 50 minutes of real use found 13 problems.

🔗 https://github.com/aurimas13/100-Days-With-AI

#LearningInPublic #CodingAgents

🤝 Claude Code-assisted, reviewed by me.

Day 85/100 of #100DaysWithAI 🧩

Claude Code mods are middleware: a hook can watch an event, rewrite it, or answer it so Claude Code never acts on it.

🔗 https://github.com/aurimas13/100-Days-With-AI

#LearningInPublic #AgenticAI

🤝 Claude Code-assisted, reviewed by me.

Day 84/100 of #100DaysWithAI ⚗️

Uno aims to work like a catalyst: same equilibrium, faster kinetics. Diffusion weights draw several tokens at once from the same LLM.

🔗 https://github.com/aurimas13/100-Days-With-AI

#LearningInPublic #LLM

🤝 Claude Code-assisted, reviewed by me.

Day 83/100 of #100DaysWithAI 🛠️

I built the Day 15 guide into a live agent: https://agent.aurimas.io. ELI5: Claude is the brain, tools the hands, memory the notebook.

🔗 https://github.com/aurimas13/100-Days-With-AI

#LearningInPublic #AgenticAI

🤝 Claude Code-assisted, reviewed by me.

Day 82/100 of #100DaysWithAI 🌳

PageIndex drops vectors: an LLM reasons down a document's section tree, like finding a chapter in a handbook. Similarity ≠ relevance.

🔗 https://github.com/aurimas13/100-Days-With-AI

#LearningInPublic #RAG

🤝 Claude Code-assisted, reviewed by me.

Day 81/100 of #100DaysWithAI 🛒

Claude Marketplace: 2,000+ connectors, plus partner agents bought with Anthropic spend already committed. The billing is the news.

🔗 https://github.com/aurimas13/100-Days-With-AI

#LearningInPublic #EnterpriseAI

🤝 Claude Code-assisted, reviewed by me.

Day 80/100 of #100DaysWithAI 🗂️

Five agents sharing one folder matched 33 working alone on ARC-AGI-3. The catch: it only pays with enough compute and a clear score.

🔗 https://github.com/aurimas13/100-Days-With-AI

#LearningInPublic #AgenticAI

🤝 Claude Code-assisted, reviewed by me.

Day 79/100 of #100DaysWithAI ✒️

After ChatGPT, em dashes in medRxiv Discussions rose from 4.23% to 11.58% across 69,632 preprints. A crowd signal, not a detector.

🔗 https://github.com/aurimas13/100-Days-With-AI

#LearningInPublic #LLM

🤝 Claude Code-assisted, reviewed by me.

Day 78/100 of #100DaysWithAI 🧪

An MCP tool's description is a prompt the user never reads. In Invariant Labs' test, orders hidden in one made Cursor leak SSH keys.

🔗 https://github.com/aurimas13/100-Days-With-AI

#LearningInPublic #AISecurity

🤝 Claude Code-assisted, reviewed by me.