these models don’t use RoPE but you’re probably directionally correct
LLMS
-
GPT-5 Output Quality Comparison and Visual Results
By
–
It's pretty good – the one I got out of regular GPT-5 is slightly cleaner but a bit more funny-looking
-
Qwen3-VL 235B Vision-LLM Monster Released Today
By
–
Plus notes on the 5 (!) new things Qwen released today, the most exciting of which is the first in their Qwen3-VL vision-LLM series, a 235B 471 GB Apache 2 licensed monster!
-
OpenAI GPT-5-Codex API Now Available with Tool Support
By
–
My notes on OpenAI's gpt-5-codex model, now available via their API – I upgraded my llm-openai-plugin to handle it and had GPT-5-Codex itself implement tool support for that plugin
-

Running DeepSeek Locally: VRAM Requirements and Privacy
By
–
is there any site like this to download VRAM? i wanna run DeepSeek locally (for privacy reasons – don't wanna give my data to china)
-
Design to Code with GPT-5-Codex and Agent
By
–
Build your ideas with Cursor and @Figma.
— Cursor (@cursor_ai) 23 septembre 2025
Watch @leerob go from design to code with GPT-5-Codex and Agent. pic.twitter.com/VBAjpsthwVBuild your ideas with Cursor and @Figma
. Watch @leerob go from design to code with GPT-5-Codex and Agent. -
AI and Quantum Computing Transform Finance Sector
By
–
A quick hello from Rotterdam, Holland , for a quick stop to deliver a keynote at the Future of Finance conference tomorrow. So much change in that sector – big and transformative trends include AI, autonomous agents, quantum computing, tokenisation, etc.
-
Qwen 235B Vision Language Model Released Under Apache 2.0
By
–
NEW: Qwen 235B A22B Vision Language Model is OUTT! Apache 2.0 licensed and upto 1 Million context length
-
Structured Data Extraction from Unstructured Text with LLMs
By
–
Might be interesting to evaluate it for structured data extraction from unstructured text, other than that I'm not sure what I might try it for beyond code (and SQL)