Olmo 3: Charting a path through the model flow to lead open-source AI(allenai.org)

368 points by mseri 11 months ago | 120 comments

Ai2 blog post announcing Olmo 3, an open-source language model family released with its full development pipeline, or "model flow".

Open-sourcing AstaBrief, the fast report-generation model in Asta(allenai.org)

20 points by malshe 23 days ago | 3 comments

Ai2 blog post announcing the open-source release of AstaBrief, a fast report-generation model used in its Asta research assistant, with model and data links.

OpenAI's new "Orion" model reportedly shows small gains over GPT-4(the-decoder.com)

24 points by tiime 1 year ago | 12 comments

GPT-OSS 120B Runs at 3000 tokens/sec on Cerebras(cerebras.ai)

20 points by samspenc 11 months ago | 12 comments

How easy is it for a developer to "sandbox" a program?(kristaps.bsd.lv)

44 points by zdw 1 year ago | 39 comments

Emacs Lisp shorthands as namespacing system(andreyorst.gitlab.io)

78 points by gjvc 3 years ago | 15 comments

Strands Decider: Why Not an Encoder?(brooker.co.za)

33 points by surprisetalk 12 days ago | 1 comments

Marc Brooker's blog post explaining why the strands-decider-2B classifier uses a modified decoder LLM rather than a BERT-style encoder, comparing five designs.

Strands Harness(strandsagents.com)

129 points by zuckerborg0101 1 month ago | 89 comments

Blog post on the Strands Agents site announcing Strands Harness, a new component of the Strands AI agent framework.

ChatGPT agent: bridging research and action(openai.com)

650 points by Topfi 1 year ago | 445 comments

OpenAI's July 2025 announcement of ChatGPT agent, which uses its own computer and agentic tools to research and complete tasks for users.

StableLM: A new open-source language model(stability.ai)

1412 points by davidbarker 3 years ago | 474 comments

Stability AI blog post announcing the release of StableLM, the first models in its open-source language model suite.

OpenAI O3-Mini(openai.com)

915 points by johnneville 1 year ago | 861 comments

OpenAI's announcement of o3-mini, a cost-efficient reasoning model available in ChatGPT and the API, strong in science, math, and coding.

Notes on OpenAI's new o1 chain-of-thought models(simonwillison.net)

641 points by loganfrederick 2 years ago | 566 comments

Simon Willison's blog post with notes on OpenAI's o1-preview and o1-mini models, covering chain-of-thought training, API details, hidden reasoning tokens and examples.