Email or username:

Password:

Forgot your password?
Simon's posts Post Back to profile
Simon Willison

Here's everything I've figured out about the new OpenAI o1 family of models so far simonwillison.net/2024/Sep/12/

12 September at 22:41 | Open on fedi.simonwillison.net
3 comments
Simon Willison

And a new release of LLM that adds support for those models - for anyone lucky enough to have a tier 5 OpenAI API account at least llm.datasette.io/en/stable/cha

0.16 (2024-09-12) OpenAI models now use the internal self.get_key() mechanism, which means they can be used from Python code in a way that will pick up keys that have been configured using llm keys set or the OPENAI_API_KEY environment variable. #552. This code now works correctly: import llm print(llm.get_model("gpt-4o-mini").prompt("hi")) New documented API methods: llm.get_default_model(), llm.set_default_model(alias), llm.get_default_embedding_model(alias), llm.set_default_embedding_model(). #553 Support for OpenAI’s new o1 family of preview models, llm -m o1-preview "prompt" and llm -m o1-mini "prompt". These models are currently only available to tier 5 OpenAI API users, though this may change in the future. #570
12 September at 23:26 | Open on fedi.simonwillison.net
Jonathan Moore

@simon o1 gets my unbirthday question which none of OpenAI's other models have: "Do all people have the same number of unbirthdays?"

chatgpt.com/share/66e3652c-7ae

12 September at 23:46 | Open on mastodon.social
ijm

@simon the "Limit additional context in retrieval-augmented generation (RAG)" and "Hidden reasoning tokens" seem to be contradictory, or at least at odds: reduce the context, but you cannot use any reasoning tokens that came up while deciding what was and wasn't relevant.
I've been trying to find ways to improve rag index vectors, effectively trying to extract some internal state from a model as a sort-of pre-compiled version of the text - and these hidden reasoning tokens seem to be exactly related to what I'm looking for, but nope we're not allowed to see'm !

@simon the "Limit additional context in retrieval-augmented generation (RAG)" and "Hidden reasoning tokens" seem to be contradictory, or at least at odds: reduce the context, but you cannot use any reasoning tokens that came up while deciding what was and wasn't relevant.
I've been trying to find ways to improve rag index vectors, effectively trying to extract some internal state from a model as a sort-of pre-compiled version of the text - and these hidden reasoning tokens seem to be exactly related...

13 September at 15:34 | Open on mathstodon.xyz
Go Up