New: o3-deep-research and o4-mini-deep-research! We're excited to bring OpenAI's deep research models to Poe. Now you can tackle complex research tasks and then switch to other models for writing, coding, and media generation all in one chat. (1/3)
LLMS
-
o4-mini and o3 Deep Research Models with Web Search Capabilities
By
–
Both models can also pull external context through web search. We suggest starting with o4-mini-deep-research first. If you aren't happy with the result, switch to o3-deep-research. (2/3)
-
Gemini 2.5 Pro Now Offers Free Tier Access Again
By
–
Heh but you're out of date already because Gemini 2.5 Pro has a free tier again 😉
-
Accidental Use of o3-pro Instead of 4o
By
–
I hate when I accidentally use o3-pro when I meant to use 4o
-
Gemini 2.5 Pro Now Available in Free API Tier
By
–
Gemini 2.5 Pro is back in the free tier of the API, have a great weekend : )
-
Claude 4 Upgrade: Cline Team Delivers Major Improvements
By
–
Switch to Claude 4! From what I understand, the Cline team has made some big improvements and now it works better than 3.7.
-
Current AI Reasoning and Memory Capabilities Still Insufficient
By
–
i don't think either one is good enough already (reasoning or memory)
-
Prompt Engineering for Shopping Deal Evaluation with LLMs
By
–
The prompt was “is this a good deal?” (Prompting is really not that hard for most requests) And it is an interesting case where hallucinations don’t matter that much (though I didn’t find any). Most online shopping guides are out of date, riddled with conflict-of-interest & odd)
-
Learning to reason with LLMs: o1 blog post analysis
By
–
[i] Learning to reason with LLMs (the o1 blog post)
-
Two Major AI Breakthroughs: Reasoning and Test-Time Compute
By
–
the way i see it, the last twelve months of AI research can be summed up in just two big breakthroughs: [i] reasoning ('test-time compute') – new ways to train models that can use more tokens to generate better answers. they mostly rely on RL with verifiable rewards [ii]