We first fine-tune the model to follow instructions, stay within guardrails, and keep language consistent. Then we run on‑policy RL to improve search accuracy and tool efficiency while preserving those behaviors.
LLMS
-
New Research: SFT+RL Pipeline Boosts Search-Augmented AI Accuracy
By
–
We've published new research on how we post-train models for accurate search-augmented answers. Our SFT + RL pipeline improves search, citation quality, instruction following, and efficiency. With Qwen models, we match or beat GPT models on factuality at a lower cost.
-
Using LLMs to Generate Safe Runnable Code
By
–
I want an LLM to generate code for me which I can then safely run somewhere without worrying about it breaking anything
-
Discovering Novel LLM Experts via Task-Capability Coevolution
By
–
Most LLM development still optimizes one model at a time. So this paper from Sakana AI proposes AC/DC (Assessment Coevolving with Diverse Capabilities), where models and tasks evolve together. The main idea is
-
GPT-Image-2 Prompt Generation and DALL-E 3 Comparison
By
–
Presumably GPT-imagegen-2 (aka ChatGPT Images 2.0 aka gpt-image-2) works as a tool which the models generate prompts for? I wish we could see those prompts, like back in the DALL-E 3 days https://
simonwillison.net/2023/Oct/26/ad
d-a-walrus/
… -
AI Acts as World-Class Research Assistant for Arcane Trivia
By
–
… this is your standard citation.” It’s really weird to have a spiky, tireless research gopher who is literally world class on what even specialists would usually describe as arcane trivia.
-
Claude Opus Analyzes Document via Screenshot After PDF Fetch Fails
By
–
Opus ratholes for a few minutes but can’t successfully locate the document I was alluding to. I find a link in my ancient notes. Opus fails to fetch PDF for technical reasons. I provide screen grab. Opus then *immediately* highlights two sentences and says ~ “Yep, I get why…
-
LLM Opus 4.7 Successfully Surveys AML KYC Law Enforcement Guidelines
By
–
An anecdote for you from LLM land: I sent Opus 4.7 out to do a literature survey of various government law enforcement internal guidelines w/r/t AML and KYC usage in prosecutions. It was much more successful at finding these docs than I would have expected. I then told it:
-
Qwen3 27B Delivers Impressive Image Generation at 16.8GB
By
–
The new Qwen3.6-27B just gave me definitely the best pelican riding a bicycle I've had from a 16.8GB model file!