Almost didn't take time to celebrate : Smolagents just wooshed past 20k stars on Github! Congrats to the team, especially @avillanovamoral who spends lots of time improving the library. And thanks a lot to our community members for pushing is forward! It's still time to
CODE
-
Benchmarking Multi-Agent Architectures: Orchestration Improvements
By
–
Benchmarking Multi-Agent Architectures As more systems become multi-agent, this begs the question: how do you best orchestrate across multiple agents? We did some initial benchmarking, including some improvements to our supervisor approach Blog: https://
blog.langchain.dev/benchmarking-m
ulti-agent-architectures/
… -
Building and Deploying GenAI Application Workflows
By
–
Learn to build and deploy GenAI pipelines in "Orchestrating Workflows for GenAI Applications", built in partnership with @astronomerio and taught by Kenten Danas, the company's DevRel Senior Manager, and Tamara Fingerlin, developer advocate.
— Andrew Ng (@AndrewYNg) 11 juin 2025
Many GenAI applications require… pic.twitter.com/Iv0ZGCUBgFLearn to build and deploy GenAI pipelines in "Orchestrating Workflows for GenAI Applications", built in partnership with @astronomerio and taught by Kenten Danas, the company's DevRel Senior Manager, and Tamara Fingerlin, developer advocate. Many GenAI applications require
-
DeepEval: Open-Source LLM Testing and Evaluation Framework
By
–
Pytest for LLM applications! DeepEval is an LLM evaluation framework that makes it easy to test, debug and evaluate LLM applications. 100% open-source and runs locally
-
AGI Reflexive Meta: Self-Rewriting Laws Through Decentralized Code
By
–
Φ‑AGI Reflexive‑Meta rewrites its own laws: every metric & treasury line lives as live code. Meta‑pulls prove delta, validators attest, time‑locks hum. → DAO cells → reservoirs; compounding alpha bends global ledgers. #AGIALPHA #ReflexiveMeta #ASI
-
Human-level agents CLI tested live
By
–
Just tested it live. Mouse moved Opened article Summarized perfectly You’re looking at the CLI for human-level agents.
-
New Video Course: Building and Operating LLMs Primer
By
–
That’s why we are launching our first fully video-based course: “10-Hour Primer: Building & Operating LLMs.”
-
Mistral Releases Reasoning Models: Magistral Small and Medium
By
–
Mistral dropped two reasoning models: 24B param, open-source Magistral Small and enterprise-specific Magistral Medium
— Rowan Cheung (@rowancheung) 11 juin 2025
Both models' chain-of-thought works across global languages and alphabets
However, STEM and coding benchmarks lag behind top rivalspic.twitter.com/nfqZQpBlWwMistral dropped two reasoning models: 24B param, open-source Magistral Small and enterprise-specific Magistral Medium Both models' chain-of-thought works across global languages and alphabets However, STEM and coding benchmarks lag behind top rivals
-
Evolution of Coding UX: From 1950s to AI Future
By
–
Thanks @swyx + AI Engineer World's Fair for hosting me for a talk on the big stage last week! I did a speed run through the evolution of coding UX since the 1950's, and where I think we're headed. Video: https://
youtube.com/watch?v=U-fMsb
Y-kHY&t=18785s
…
Slides: https://
docs.google.com/presentation/d
/1FGNy3wHoXEnVpgOTB9rtgdyjaQvEVHmhxGhHoGIPX98
… -
O3 Emerges as Strong Coding Option with Major Price Cut
By
–
Wow O3 is a *very* strong option for coding now. I've updated @paulgauthier
's latest Aider eval with this O3 80% price cut – check out O3 in 3rd place, but cheaper and faster than Gemini Pro now: