My full piece on the models, including various pelicans on bicycles and detailed notes on running them on my own laptop using @lmstudio and @ollama – and via API using @openrouter and @cerebras
CODE
-
Understanding torch.compile: Common misconceptions explained
By
–
Whoever wrote that seems to not understand fundamentally what torch.compile does, or why it does it.
-
DDP Gradient Bucketing and Activation Checkpointing Optimization
By
–
I'm sorry, this makes no sense.
– Gradient bucketing is literally part of DDP
– DDP is a networking thing, obs you don't compile that
– Activation checkpointing works fine once hooks are disabled during tracing (ofc) -
Claude Opus 4.1 Launches on Poe Platform
By
–
Claude Opus 4.1 is now on Poe! Anthropic’s best model for real-world coding and reasoning offers a clear upgrade in understanding and remembering context for more accurate, helpful conversations on your most complex topics. (1/2)
-
Claude Opus 4.1 Now Available Across All Platforms
By
–
Claude Opus 4.1 is available at https://
poe.com/Claude-Opus-4-1 and across all platforms. You can also use this model in your favorite coding tools via our new API. (2/2) -
GPT OSS Tool Enables AI Research Paper Analysis
By
–
Introducing GPT OSS for understanding research papers 🚀
— alphaXiv (@askalphaxiv) 5 août 2025
Highlight any section of a paper to ask questions and “@” other papers for quick context, comparisons, and benchmark references pic.twitter.com/9BGeZspAb2Introducing GPT OSS for understanding research papers Highlight any section of a paper to ask questions and “@” other papers for quick context, comparisons, and benchmark references
-
GPT-OSS Builds Video Game Using Tool Integration and Chain-of-Thought
By
–
Want to see our open models in action? Watch how gpt-oss builds a video game—using tools step-by-step within chain-of-thought reasoning
-
OpenAI Updates System Prompt Architecture with Developer Tools
By
–
Not new, but the system prompt is now an automated list of relevant info (name, date, tools). The "developer" prompt is the old system prompt. https://
github.com/openai/harmony -
RAG vs Fine-tuning: Information vs Behavior Model Adaptation
By
–
@corbtt @dvdcrbt can give concrete examples, but from my experience, they enable completely different things. RAG/search really just gives the model *info* to work with. Fine-tuning changes the *behavior* of the model.
-
GPT-OSS Chat Template Special Tokens Analysis
By
–
Wow gpt-oss has a very interesting chat template Special tokens for "channel" (analysis, commentary, final) and "constrain". Still pretty ChatML-like!