An agent must be trained for a specific task, just like human employees.
CODE
-
Essential LLM Concepts: Tokenization, Attention, and Sampling
By
–
key topics to learn how llms work, all it takes is < 2 years if you have cs foundation > tokenization and embeddings
> positional embeddings (absolute, rope, alibi)
> self attention and multihead attention
> transformers
> qkv
> sampling params: temperature, top-k top-p
> kv -
Codex CLI /review: AI-powered code review feature launched
By
–
✨ New in Codex CLI: /review
— Romain Huet (@romainhuet) 19 septembre 2025
You can now get a code review on your local changes, and GPT-5-Codex was specifically trained to investigate issues. 🔍
Try it out on your projects! https://t.co/uFlHcaHvx3New in Codex CLI: /review You can now get a code review on your local changes, and GPT-5-Codex was specifically trained to investigate issues. Try it out on your projects!
-
End of Code Claude, retention of Codex, AI lifespan 2-3 months
By
–
I just canceled my Code Claude subscription, sorry @AnthropicAI. And I'm keeping Codex for now with the @OpenAI subscription at €250/month. The king is dead, long live the king. The lifespan of a leading AI model is therefore 2-3 months before being caught up. Interesting
-
Tool Loop Implementation Guide for AI Agents
By
–
Anyhoo, here's what I wrote quite some time ago… https://
claudette.answer.ai/toolloop.html -
Rebranding LLM Library as Agentic Framework for Market Traction
By
–
I wonder if https://
claudette.answer.ai would have more traction if you labeled it an "agentic framework though – that seems to be the name that other competitors are settling on, I'm seriously considering rebranding my LLM Python library -
Sub-Agent Pattern in Claude: Context Window Job Dispatch
By
–
That's pretty much the sub-agent pattern, as seen in Claude Code and Claude Research and friends – the parent LLM can dispatch a job to a sub-agent which then works on it as part of its own fresh context window and passes the result back up when it's done
-
Getting Started with JAX GPU: Tutorials and Resources
By
–
Wow. I had no idea jax GPU had come so far. Is there a tutorial that teaches how to use these features of jax? How would one get started?
-
LLM Library Gets Tool Calling for Agentic Framework
By
–
I added tool calling to my LLM CLI/Python library a few months ago which upgraded it to an "agentic framework", but I'm only now ready to admit that's what it is because I didn't like using the term agents!