I released LLM 0.32a0 this morning, a major backwards-compatible refactor of my LLM Python library and CLI tool for working with language models – the new changes should help LLM work better with reasoning models and other new frontier capabilities
LLMS
-
Claude Opus 4.7 leads GPT-5.5 on 6 of 10 benchmarks by category
By
–
On the 10 benchmarks where both OpenAI and Anthropic report scores, here's the split: Claude Opus 4.7 leads on 6. GPT-5.5 leads on 4. But the leads aren't random. They cluster by category. And that changes what "winning" means entirely.
-
GPT-5.5 vs Claude Opus 4.7: The real benchmark story
By
–
GPT-5.5 shipped 7 days after Claude Opus 4.7. Everyone picked a winner based on headlines. I looked at every benchmark both labs published. The real story isn't what most people are reporting:
-
LLMs Cannot Replace Decades of Regulated Experience
By
–
SAS’ Tom Roehm: “AI is everywhere. Yes, LLMs are powerful… But here’s what they can’t do — they can’t scrape decades of lived experience or inherit judgment forged from working in regulated environments. They can’t feel the weight of decisions where being ‘mostly right’ isn’t
-
ChatLLM Unifies Multiple LLMs in Single Platform
By
–
GPT-5.5, Opus-4.7, DeepSeek-V4, Kimi-2.6… all in one place on ChatLLM by Abacus AI
— Abacus.AI (@abacusai) 29 avril 2026
No more jumping between tools.
You just type what you want to build, and it actually happens.
That’s the shift. pic.twitter.com/b5malOZhIfGPT-5.5, Opus-4.7, DeepSeek-V4, Kimi-2.6… all in one place on ChatLLM by Abacus AI No more jumping between tools.
You just type what you want to build, and it actually happens.
That’s the shift. -
Google AI Models Lag Behind Competitors, User Warns
By
–
Don’t use Google models, currently they’re way behind the others for most things
-
OSS Models Key to Cost-Effective DeepAgents in 2026
By
–
big theme of 2026 – cost of closed models is too high! really excited to make deepagents work exceptionally well with OSS models
-
Embedding Layers in Small Models: Architecture and Training Optimization
By
–
Did you know that the embedding layer can contain 63% of total model parameters? In this talk, I present unique challenges of small models from architecture (don't build giant embedding layers) to post-training (how to fix doom looping) ↓ Slides in the comments ↓
-
Configuring AI Agent with GLM5 Model via Baseten
By
–
After switching into the new directory (`cd lc-docs`) I'm going to set the name of my agent, and the model to use This is done in deepagents.toml I'm going to use @Zai_org GLM5 model, served via @baseten