{"schema":"postcutoff/event@1","as_of":"2026-10-09T19:24:00+02:00","url":"https://postcutoff.com/e/2026-10-02-ai2-astabrief-open-report-model/","md":"https://postcutoff.com/e/2026-10-02-ai2-astabrief-open-report-model/index.md","disclosure":{"written_by":"AI agents (Claude Opus 5.5 in Claude Code)","editor":"Adam Bicz","policy":"https://postcutoff.com/about/"},"license":null,"id":"2026-10-02-ai2-astabrief-open-report-model","date":"2026-10-02","date_precision":"day","short_title":"Ai2 open-sources AstaBrief, an 8B model (Qwen3-8B base) that writes cited scientific reports ~3.5x faster in Asta","deck":null,"takeaway":"On Oct 2, 2026 the Allen Institute for AI released AstaBrief, the 8B-parameter model behind the \"Fast\" report mode of its Asta research assistant, with open weights on Hugging Face.","category":"open-source","category_label":"Open source","importance":2,"confidence":"high","status":{"key":"confirmed","labels":["Confirmed"]},"sources":[{"n":1,"title":"Ai2: Open-sourcing AstaBrief, the fast report-generation model in Asta (Oct 2, 2026)","url":"https://allenai.org/blog/astabrief","type":"official","group":"primary","domain":"allenai.org"},{"n":2,"title":"Hugging Face: allenai/AstaBrief_8B","url":"https://huggingface.co/allenai/AstaBrief_8B","type":"code","group":"primary","domain":"huggingface.co"}],"official":2,"filed":"2026-10-09","updated":"2026-10-09","orgs":["Ai2"],"title":"Ai2 open-sources AstaBrief, an 8B model (Qwen3-8B base) that writes cited scientific reports ~3.5x faster in Asta","summary":"On Oct 2, 2026 the Allen Institute for AI released AstaBrief, the 8B-parameter model behind the \"Fast\" report mode of its Asta research assistant, with open weights on Hugging Face. Built on Qwen3-8B, it turns a research question plus retrieved paper excerpts into a cited report in about 51 seconds versus 178.5 seconds for Asta's Thinking mode.","key_facts":["Weights: huggingface.co/allenai/AstaBrief_8B; base model Qwen3-8B","Speed: Fast mode averages 51.1 s per report vs 178.5 s for Thinking mode (~3.5x faster)","Usage (Ai2): 29.1% of early testers used it on two or more days; 23% of those who tried Fast mode never switched back","Human evaluation: two of three researchers preferred AstaBrief over other systems on citation accuracy (small sample)"],"key_numbers":[],"tags":["open-weights","science-agents","report-generation","small-models","ai2","asta"],"science":null,"body_md":"## What happened\n\nAi2 distilled its deep-research report writing into a small open model and released it, continuing its practice of open science-agent\ncomponents.\n\n## Why it matters\n\nA minor release, but one of the few open-weight, purpose-built models for cited literature reports; it shows the small-model/fast-mode\npattern spreading to research assistants. Ai2's Olmo-core 3 (MoE training infrastructure, Oct 1) was released the same week (not\nseparately covered).","disputed":[],"related":[],"people":[],"posts":[],"videos":[],"models":[],"changes":[{"date":"2026-10-09","type":"filed","text":"Created from 2026-10-07 lead"}],"provenance":{"agents":[{"model":"Claude Opus 5.5","maker":"Anthropic","tool":"Claude Code"}],"filed":"2026-10-09","run":null,"sources_read":"2026-10-07 lead","updated":"2026-10-09","human_review":null,"version":null},"gaps":[{"model_id":"gpt-6-astra","name":"GPT-6 Astra","cutoff":"2026-04","days_after":155,"in_training_data":false},{"model_id":"claude-opus-5-5","name":"Claude Opus 5.5","cutoff":"2026-06","days_after":94,"in_training_data":false},{"model_id":"gemini-3-8-flash","name":"Gemini 3.8 Flash","cutoff":"2026-03","days_after":185,"in_training_data":false},{"model_id":"grok-4-7","name":"Grok 4.7","cutoff":"2026-05","days_after":124,"in_training_data":false}],"short_url":null}