You still need a bit of knowledge in any reasoning, just to guide you in where to look. For instance, you'll do better search on geopolitics if you know a bit about the general trends. Qwen just demonstrated that this base level of knowledge can be attained in a very compact
@aymericroucher
-
4B model rivals 120B on knowledge, ideal for agentic core
By
–
It's crazy that a 4B model can match GPT-OSS-120B **even on knowledge benchs** like MMLU and GPQA! Knowledge was long a limitation of smol models ; not anymore. This 4B could be a good candidate for the "agentic core" model described by @karpathy
-
Anthropic acquires Vercept, xAI focuses on computer use agents for 2026
By
–
– Anthropic acquires Vercept
– xAI's MacroHard heavily focuses on Computer use 2025 was the year of agents in CLI
2026 is shaping up to be the year of computer use agents. -
Top AI models stay close in a fast-moving packed peloton
By
–
Funny how the top models from different labs stay within a tiny distance from each other. The peloton is moving extremely fast, but stays quite packed, no breakaway so far. And that is despite large differences, e.g. in available compute. What's the forcing function that makes
-
Encouragement to build with smolagent’s CodeAgent and propose improvements
By
–
Nice work!
Don't hesitate to build a bit with smolagent's CodeAgent if you're interested in code-actions agents, I'm less involved now but would still love to look at what improvements you could propose! -
Custom Taalas hardware runs Llama-3.1-8B at 17k tokens per second
By
–
Custom hardware from Taalas runs Llama-3.1-8B, at 17k tokens per second
17k Absolutely insane (For the record Cerebras is crazy good and they're at 2k on the same model)
And latency is very low too! Their chatbot is here: https://
chatjimmy.ai It's genuinely a eerie -
Hugging Face Icon Now Available in Font Awesome
By
–
Tell your vibe-coding tool: you can now use the @huggingface icon in Font Awesome ! I posted the original request for addition in early 2025: thanks to the Font Awesome team for following up!
-
From March 2025 to Feb 2026: AI writes all code
By
–
Devs, march 2025: Amodei is insane, no way AI writes all our code next year
Devs, feb 2026: -
Kill conditions for agent orchestrators to stop error loops
By
–
Interesting!
One thing that I have to always do: whenever a Claude Code starts to go wrong, I kill it, because when they fill their context with error logs and wrong ideas, they tend to keep digging their hole.
A good agent orchestrator would have "kill conditions" to just -
LeCun: child perceives more visual data than LLM
By
–
This is false: LeCun does the calculation in a video, I need to find it: a child in their first 4 years of life perceives more visual data than the largest LLM trainings use.