So it seems like there is a “thought” output from the model before the “response” output, essentially having it do CoT that way and removing the “thought” part
LLMS
-
Powerful and economical reasoning model, OpenAI IDE speculation
By
–
In short: They have released a specialized model for reasoning tasks (math, code etc.) with crazy performance on these tasks, and especially 80% cheaper and faster. My little finger tells me that OpenAI will soon launch its own IDE… like cursor 😉 ……..
-
OpenAI Project Strawberry: New AI Step-by-Step Reasoning Approach
By
–
OpenAI has revealed details of Project Strawberry, what it claims is a more general approach to teaching to AI solve problems with step-by-step reasoning. Outside experts say it is an important new direction for AI but note that challenges remain:
-
Tier 5 API User Unable to Access New Model in List
By
–
Any tier 5 API users seeing this in their model list? I'm not seeing it when running:
curl https://
api.openai.com/v1/models -H "Authorization: Bearer $OPENAI_API_KEY" @openai is this expected? Do I just have to be a bit more patient?… 😀 -
OpenAI Releases o1 Model With Advanced Reasoning Capabilities
By
–
… and now it's out https://
bloomberg.com/news/articles/
2024-09-12/openai-releases-o1-model-with-reasoning-capabilities?srnd=phx-technology
… -
Fine-tuned o1 Achieves Gold Medal in IOI Programming Competition
By
–
screenshot of eval results in the tweet above and more in the blog post, but worth especially noting: a fine-tuned version of o1 scored at the 49th percentile in the IOI under competition conditions! and got gold with 10k submissions per problem.
-
OpenAI Releases o1: Advanced Reasoning Model with Notable Limitations
By
–
here is o1, a series of our most capable and aligned models yet: https://
openai.com/index/learning
-to-reason-with-llms/
… o1 is still flawed, still limited, and it still seems more impressive on first use than it does after you spend more time with it. -
OpenAI Launches o1 Models for General-Purpose AI Reasoning
By
–
but also, it is the beginning of a new paradigm: AI that can do general-purpose complex reasoning. o1-preview and o1-mini are available today (ramping over some number of hours) in ChatGPT for plus and team users and our API for tier 5 users.
-
New AI Model Launched and Available for Testing Today
By
–
announce and roll out on same day? nice! don’t see it yet in my model picker, but looking forward to try!
-
OpenAI Develops Internal Voice Capability for AI Thinking
By
–
Some people have an internal voice when they think. OpenAI is now catching up to you.