Tootfinder

GPT-5 Thinking in ChatGPT is shockingly good at search and demonstrates the potential of combining tool calling with chain-of-thought reasoning (Simon Willison/Simon Willison's Weblog)
https://simonwillison.net/2025/Sep/6/research-goblin/

GPT-5 Thinking in ChatGPT (aka Research Goblin) is shockingly good at search
“Don’t use chatbots as search engines” was great advice for several years... until it wasn’t. I wrote about how good OpenAI’s o3 was at using its Bing-backed search tool back …

TIL that chatgpt signs HTTP requests with RFC 9421 signatures, which initially seems over the top, until you consider the scope of what agentic systems might end up doing.
https://fedi.simonwillison.net/@simon/114973107878476323

Anthropic prices Claude Sonnet 4.5 at $3/1M input and $15/1M output tokens, same as Sonnet 4, cheaper than Opus at $15/$75 but higher than GPT-5 at $1.25/$10 (Simon Willison/Simon Willison's Weblog)
https://simonwillison.net/2025/Sep/29/claude-sonnet-4-5/

Claude Sonnet 4.5 is probably the “best coding model in the world” (at least for now)
Anthropic released Claude Sonnet 4.5 today, with a very bold set of claims: Claude Sonnet 4.5 is the best coding model in the world. It’s the strongest model for building …

DeepMind: video models like Veo 3 could become general purpose foundation models for vision, like LLMs for text, using zero-shot "chain-of-frames" reasoning (Simon Willison/Simon Willison's Weblog)
https://simonwillison.net/2025/Sep/27/v…

Video models are zero-shot learners and reasoners
Fascinating new paper from Google DeepMind which makes a very convincing case that their Veo 3 model - and generative video models in general - serve a similar role in …

HUGE https://fedi.simonwillison.net/@simon/115019864847481812

Alibaba releases the Qwen3-VL vision models, the Qwen3Guard "safety moderation" models, and three closed-weight models, including Qwen3-Max with 1T parameters (Simon Willison/Simon Willison's Weblog)
https://simonwillison.net/2025/Sep/23/qwen3-vl/

A new Artificial Analysis benchmark, focusing on OpenAI's gpt-oss-120b, shows how open-weight LLMs exhibit inconsistent performance across hosting providers (Simon Willison/Simon Willison's Weblog)
https://simonwillison.net/2025/Aug/15/inconsistent-performance/…

Open weight LLMs exhibit inconsistent performance across providers
Artificial Analysis published a new benchmark the other day, this time focusing on how an individual model—OpenAI’s gpt-oss-120b—performs across different hosted providers. The results showed some surprising differences. Here’s the …

GPT-5 hands-on: it exudes competence but doesn't feel like a dramatic leap ahead of other LLMs, and the pricing is aggressively competitive with other providers (Simon Willison/Simon Willison's Weblog)
https://simonwillison.net/2025/Aug/7/gpt-5/

GPT-5: Key characteristics, pricing and model card
I’ve had preview access to the new GPT-5 model family for the past two weeks (see related video) and have been using GPT-5 as my daily-driver. It’s my new favorite …