Llama 4 potentially will be announced on April 29 in LlamaCon
LLMS
-
AISuite Simplifies LLM Function Calling for Developers
By
–
Announcing new aisuite capability: Easy function calling with LLMs! Function calling (tool use) is an important capability for agentic workflows and other LLM applications, but is cumbersome for developers to use (left column in image). Our open-source aisuite package simplifies
-
LangMem: Long-term Memory Integration for AI Applications
By
–
We've seen a lot of interest in long term memory and have spent a lot of time thinking about the best way to incorporate it into apps We've tried to distill some of these learnings into helper functions (and helper agents!) `pip install langmem` -> check it out
-
Elon Musk Open-Source Grok Models for AI Humanity
By
–
@elonmusk Elon, if you want open AI for humanity, why not commit to open-sourcing all the Grok models? @xai
-
xAI Open-Source Debate: Full Code Release Beyond Grok Weights
By
–
@elonmusk Elon, if you want open-source AI for humanity, why not open-source all xAI models, not just Grok 1? And not just weights, but all the source code? @xai
-
Grok3 vs ChatGPT: Is it the best AI? Comparative test
By
–
I just tested #Grok3 vs #ChatGPT and the results are rather… Surprising → https://youtu.be/jDDBVJDbCf0 Is it the best AI in the world as @ElonMusk says? We answer the question in this comparison.
-
Essential Transformers Course and Smolagents Training Resources
By
–
A must-read along with the recent "smolagents" course! Fantastic work by @_lewtun
, @lvwerra and @Thom_Wolf
. It is packed with useful knowledge for working with transformers, even if dating from 2022. Particularly love the focus on data and training everything from the -
Evolution of AI prompt refinement and natural language interaction
By
–
Justement, plus maintenant. La grande majorité des IA disposent de refineurs pour traduire la demande de l'utilisateur en un prompt efficace. À terme, le but est d'être le plus transparent possible en permettant de s'exprimer de manière naturelle.
-
Grok3 Reaches Frontier Level: XAI Closes Gap Rapidly
By
–
3 major takeaways from #Grok3: 1XAI caught up at breakneck speed. In just 18 months, it has matched the frontier-level models. Maybe there is ‘no moat’ for model developers… but the only competition is from those who can brute-force billions of dollars on infrastructure spend.
-
32B model with 817 examples beats o1-preview on math reasoning
By
–
Less is More for Reasoning (LIMO): a 32B model fine-tuned with 817 examples can beat o1-preview on math reasoning! Do we really need o1's huge RL procedure to see reasoning emerge? It seems not.
Researchers from Shanghai Jiaotong University just demonstrated that carefully