Non, ça ne sera pas ouvert, c'est pour mon usage, mais je pense que d'ici peu de temps, je vais construire un outil pour permettre à quiconque d'installer très facilement sa propre IA sur son puissant ordinateur, d'autres le feront peut-être avant moi, sinon moi je le ferais.
AI
-
Debugging with Ephemeral Crabbox Sessions
By
–
Whenever I investigate a bug, I let codex recreate the exact state in an emphemeral crabbox, verify the bug, fix it, verify the fix. No messy state because local system might be polluted, and no slowdown because I run 10 sessions in parallel. http://
crabbox.sh -
Context Awareness Unlocks Smarter Research
By
–
The bigger unlock is context awareness. You can bring:
→ Multiple tabs
→ Documents
→ Images Into one query. That means the system understands your entire research flow, not isolated searches. This is what Chrome’s AI Mode is aiming for, and it changes how we learn and -
Claude Mythos vs Gemini 3.1 Pro accuracy gap widens dramatically
By
–
What is even more impressive is just how wide the gap between Claude Mythos and Gemini 3.1 Pro becomes when moving from a 50% success rate to an 80% success rate. Mythos doesn't just work "longer" – above all, it works significantly more accurately! That is the truly impressive
-
Lighter and Faster Language Models
By
–
Sparser, Faster, Lighter Transformer-Based Language Models Paper:
-
Excited speculation about next AI model’s 8-hour workday at 80% success
By
–
Holy sh*t! That jump! So the next model after Mythos will work a whole 8 hour work day at 80% success rate, I assume.
-
New RAG Approach ‘Blockify’ Improves Search Efficiency
By
–
Naive RAG vs. Blockify!
— Akshay 🚀 (@akshay_pachaar) 9 mai 2026
There's a new RAG approach that:
– cuts corpus size by 40x.
– reduces tokens per query by 3x.
– improves vector search relevance by 2.3x.
Blockify GitHub: https://t.co/R0LSWC1V8a https://t.co/xNuoXSBj7E pic.twitter.com/ibwgORIHIbNaive RAG vs. Blockify! There's a new RAG approach that: – cuts corpus size by 40x.
– reduces tokens per query by 3x.
– improves vector search relevance by 2.3x. Blockify GitHub: https://
github.com/iternal-techno
logies-partners/blockify-agentic-data-optimization
… -
Claude Code Adds /radio Command for Lo-Fi Coding Beats
By
–
Claude Code adds a /radio command for Lo-Fi coding beats 🤯pic.twitter.com/ukxlWz19l4
— Charly Wargnier (@DataChaz) 9 mai 2026Claude Code adds a /radio command for Lo-Fi coding beats
-
Supercharged Coding with GitHub Copilot, ChatGPT and OpenAI
By
–
Supercharged Coding with #GenAI — From vibe coding to best practices using GitHub Copilot, ChatGPT, and OpenAI: http://
amzn.to/3VBH2Su v/ @PacktDataML 𝓚𝓮𝔂 𝓕𝓮𝓪𝓽𝓾𝓻𝓮𝓼: Discover how GitHub Copilot, ChatGPT, and the OpenAI API can boost your coding productivity Push -
The Environmental Impact of AI: Understanding Data Center Water Usage
By
–
How AI uses water!#AI #artificialintelligence #energysecurityke #waterusage #AIdatacenter #datacenter@PawlowskiMario @chidambara09 @Ym78200 @CurieuxExplorer @efipm @bigfundu @sayedflah @Ronald_vanLoon @cyngn @belindabeibi @odisseiaalfa @DigitalColmer @MyCompanionsAI… pic.twitter.com/L6r5gfMwDA
— Amitav Bhattacharjee (@bamitav) 9 mai 2026How AI uses water! #AI #artificialintelligence #energysecurityke #waterusage #AIdatacenter #datacenter @PawlowskiMario @chidambara09 @Ym78200 @CurieuxExplorer @efipm @bigfundu @sayedflah @Ronald_vanLoon @cyngn @belindabeibi @odisseiaalfa @DigitalColmer @MyCompanionsAI