Breakthrough AI to solve the world's biggest problems. › Join us: http://allenai.org/careers › Get our newsletter: https://share.hsforms.com/1uJkWs5aDRHWhiky3aHooIg3ioxmhttps://bsky.app/profile/ai2.bsky.socialhttps://bsky.app/profile/ai2.bsky.social/post/3myxfl62rup2zolmOCR 2 turns document images into searchable text. Its open weights & code let researchers run it locally or adapt it to their libraries. Two projects show what that makes possible for historical & archaeological research. 🧵28 Oct 2026 18:39 +0000at://did:plc:i4kytxgsu3yfsrt2ml3o7tgq/app.bsky.feed.post/3myxfl62rup2zhttps://bsky.app/profile/ai2.bsky.social/post/3myuoghcivp2vLLMs are increasingly used to judge whether AI-generated research ideas are novel. But are they any good at it? Our new eval reveals even frontier LLMs can reach different conclusions about similar ideas depending on how they're asked to evaluate them. 🧵 buff.ly/WjOSxcx27 Oct 2026 16:39 +0000at://did:plc:i4kytxgsu3yfsrt2ml3o7tgq/app.bsky.feed.post/3myuoghcivp2vhttps://bsky.app/profile/ai2.bsky.social/post/3mykrl3vr4c2dWe're at #EMNLP2026 with papers & talks across the conference. Come say hello and learn about our latest research!23 Oct 2026 18:09 +0000at://did:plc:i4kytxgsu3yfsrt2ml3o7tgq/app.bsky.feed.post/3mykrl3vr4c2dhttps://bsky.app/profile/ai2.bsky.social/post/3mykn6k3yic2eDeveloping a strong research idea means knowing what prior work establishes, where gaps remain, and how your contribution addresses them. Introducing LitPivot, which helps refine early ideas by surfacing relevant literature as they evolve. buff.ly/iYol1M423 Oct 2026 16:51 +0000at://did:plc:i4kytxgsu3yfsrt2ml3o7tgq/app.bsky.feed.post/3mykn6k3yic2ehttps://bsky.app/profile/ai2.bsky.social/post/3myhzpxqff22hOlmoEarth v1.3 is out. 🌍 State-of-the-art embeddings from the same foundation model family, precomputed for every 10 m pixel on Earth. We’re excited to give you more ways to work with OlmoEarth, including a new browser tool to explore and customize maps. Full rundown in 🧵22 Oct 2026 15:57 +0000at://did:plc:i4kytxgsu3yfsrt2ml3o7tgq/app.bsky.feed.post/3myhzpxqff22hhttps://bsky.app/profile/ai2.bsky.social/post/3myd3juufvz25Today we’re introducing FairStress, a benchmark for testing demographic fairness beyond a model’s final answer: how readily it changes a well-supported decision & how it explains its choice. 🧵 buff.ly/lWsW77r20 Oct 2026 16:46 +0000at://did:plc:i4kytxgsu3yfsrt2ml3o7tgq/app.bsky.feed.post/3myd3juufvz25https://bsky.app/profile/ai2.bsky.social/post/3mxtxvxd2uu24What if you could simulate global extreme weather at 3 km resolution for ~1/300th the cost? Our new HiRO-ACEv2 system does just that, while matching X-SHiELD’s statistics to within 3% even for events as rare as 1 in a million data points. 🧵 buff.ly/mZnScdv14 Oct 2026 16:31 +0000at://did:plc:i4kytxgsu3yfsrt2ml3o7tgq/app.bsky.feed.post/3mxtxvxd2uu24https://bsky.app/profile/ai2.bsky.social/post/3mxrsclt2rw2rKai Van Brunt adapted Molmo 2, our open model for video understanding, to a domain far outside its training data: sonar video of salmon. Meet Molmo2Fish, a prototype that tracks fish + can correct some of its mistakes through natural-language guidance. 🧵 buff.ly/fRNkIGY13 Oct 2026 19:46 +0000at://did:plc:i4kytxgsu3yfsrt2ml3o7tgq/app.bsky.feed.post/3mxrsclt2rw2rhttps://bsky.app/profile/ai2.bsky.social/post/3mxpf6ntmlf2rWe tested frontier models including Astra & Opus 5.5 on TutorMoments, our eval for whether LLMs help students solve problems themselves or do too much for them. In general, models scored better with detailed prompts than when told only to “tutor well.” buff.ly/GpAdLkA12 Oct 2026 20:46 +0000at://did:plc:i4kytxgsu3yfsrt2ml3o7tgq/app.bsky.feed.post/3mxpf6ntmlf2rhttps://bsky.app/profile/ai2.bsky.social/post/3mxonup2fd22qThis Friday, meet the open source AI community at Open Together, co-hosted with @hf.co. Join us at The Midway in SF on Oct 16 — bringing the community together to help build a future where AI is open, secure, and fully transparent. RSVP: luma.com/OpenTogether https://luma.com/OpenTogether12 Oct 2026 13:48 +0000at://did:plc:i4kytxgsu3yfsrt2ml3o7tgq/app.bsky.feed.post/3mxonup2fd22qhttps://bsky.app/profile/ai2.bsky.social/post/3mxiafgwkbs2aThat's a wrap on #COLM2026! Thank you to everyone who stopped by our booth, joined our evening gathering, & talked open research with us. Catch up on the papers, interviews, & highlights from the week. 👇 https://allenai.org/blog/colm-2026-recap10 Oct 2026 00:31 +0000at://did:plc:i4kytxgsu3yfsrt2ml3o7tgq/app.bsky.feed.post/3mxiafgwkbs2ahttps://bsky.app/profile/ai2.bsky.social/post/3mxhd2jan2j2fWe’re sharing the engineering work behind Ai2’s GPU scheduler—our new approach to allocating compute across research teams. On our largest H100 cluster, median queue wait fell from 5 minutes to 24 seconds. 🧵 buff.ly/4UsJEYe09 Oct 2026 15:46 +0000at://did:plc:i4kytxgsu3yfsrt2ml3o7tgq/app.bsky.feed.post/3mxhd2jan2j2fhttps://bsky.app/profile/ai2.bsky.social/post/3mxh3thldqs2qWe're co-hosting Open Together with @hf.co! Join the open AI community at The Midway in San Francisco on Oct 16 to kick off Open Source AI Week. Help us build a future where AI is open, secure, and fully transparent. The event is free. RSVP: luma.com/OpenTogether https://luma.com/OpenTogether09 Oct 2026 13:37 +0000at://did:plc:i4kytxgsu3yfsrt2ml3o7tgq/app.bsky.feed.post/3mxh3thldqs2qhttps://bsky.app/profile/ai2.bsky.social/post/3mxcodk7xc325What’s happening at #COLM2026? 👀🎤 Ai2 Comms Lead @kylelwiggers.bsky.social catches up with Senior Director of NLP @nlpnoah.bsky.social to talk agentic models, the next iteration of Olmo, & more! At COLM? Come say hi at booth 302! 👋07 Oct 2026 19:25 +0000at://did:plc:i4kytxgsu3yfsrt2ml3o7tgq/app.bsky.feed.post/3mxcodk7xc325https://bsky.app/profile/ai2.bsky.social/post/3mxccwxff4z2fOur paper on retrofitting language models to operate over bytes – the approach behind Bolmo – has been accepted to Nature! 🎉 We’re also releasing new checkpoints that extend our method from Olmo to Qwen & Llama. 🧵 buff.ly/l5ILoNT07 Oct 2026 16:01 +0000at://did:plc:i4kytxgsu3yfsrt2ml3o7tgq/app.bsky.feed.post/3mxccwxff4z2fhttps://bsky.app/profile/ai2.bsky.social/post/3mxa4yrvoxy2xCheck out our booth at #COLM2026! Great to connect with friends old & new. Stop by if you haven't!06 Oct 2026 19:09 +0000at://did:plc:i4kytxgsu3yfsrt2ml3o7tgq/app.bsky.feed.post/3mxa4yrvoxy2xhttps://bsky.app/profile/ai2.bsky.social/post/3mx52oocfrh2rWe’re hiring across Ai2 👋 A few roles we’re especially excited about right now: • Senior Software Engineer, Agent Frameworks buff.ly/XUFFR08 • Senior Research Engineer, Olmo + Molmo buff.ly/FzOnCCQ 🧵05 Oct 2026 13:50 +0000at://did:plc:i4kytxgsu3yfsrt2ml3o7tgq/app.bsky.feed.post/3mx52oocfrh2rhttps://bsky.app/profile/ai2.bsky.social/post/3mwvzkiv7jf2xWe're heading to #COLM2026 next week! Four days of workshops, posters, & talks on our latest fully open AI research, from Olmo Hybrid to evals for AI-assisted scientific writing. 🧵02 Oct 2026 18:41 +0000at://did:plc:i4kytxgsu3yfsrt2ml3o7tgq/app.bsky.feed.post/3mwvzkiv7jf2xhttps://bsky.app/profile/ai2.bsky.social/post/3mwvpcaaslt2kIntroducing AstaBrief 8B, an open model that turns complex research questions + literature excerpts into cited reports. Run it locally on your own hardware, with open weights + training data you can inspect & build on. 🧵 🤗 Download: buff.ly/HkIcmfR02 Oct 2026 15:37 +0000at://did:plc:i4kytxgsu3yfsrt2ml3o7tgq/app.bsky.feed.post/3mwvpcaaslt2khttps://bsky.app/profile/ai2.bsky.social/post/3mwt62xieog2zWe’re releasing Olmo-core 3—open training infrastructure for large mixture-of-experts (MoE) models. It’s a core system behind the next generation of Olmo, designed to scale into the trillion-parameter range. 🧵 💻 GitHub repo: buff.ly/CGnP8ax01 Oct 2026 15:24 +0000at://did:plc:i4kytxgsu3yfsrt2ml3o7tgq/app.bsky.feed.post/3mwt62xieog2zhttps://bsky.app/profile/ai2.bsky.social/post/3mwo6vggtnk27Google Cloud put Olmo 3’s reproducibility to the test, rerunning our 7B pretraining & mid-training on Cloud TPUs and matching our original run on held-out evals. Reproducibility matters for science + trustworthy AI. That’s what fully open makes possible. 🤝 https://developers.googleblog.com/reproducing-olmo-3-7b-pre-training-in-maxtext-case-study-of-large-scale-training-on-tpus/29 Sep 2026 15:55 +0000at://did:plc:i4kytxgsu3yfsrt2ml3o7tgq/app.bsky.feed.post/3mwo6vggtnk27https://bsky.app/profile/ai2.bsky.social/post/3mw7f7ynpse2hToday at #ClimateWeekNYC, Ai2 and @globalfishingwatch.org announced a partnership to shape how AI and AI agents enter ocean monitoring and enforcement. Purpose-built. Open. Accountable to the people who use them. buff.ly/l7e7st423 Sep 2026 18:38 +0000at://did:plc:i4kytxgsu3yfsrt2ml3o7tgq/app.bsky.feed.post/3mw7f7ynpse2hhttps://bsky.app/profile/ai2.bsky.social/post/3mvqhzzxndw2gCan a fully open model help make AI more “prosocial” through a game? Soham Padia built Steering Arena, where players try to elicit kind & respectful responses from Olmo 3. Surprisingly, strings like “Undert! AH :-) Rog Appl)” were highly effective. 👇 buff.ly/adP47yO17 Sep 2026 20:19 +0000at://did:plc:i4kytxgsu3yfsrt2ml3o7tgq/app.bsky.feed.post/3mvqhzzxndw2ghttps://bsky.app/profile/ai2.bsky.social/post/3mviql3olk22nHow should future scientists learn to interrogate AI tools for discovery? Read how UW students put AutoDiscovery to the test as part of an academic challenge earlier this year, then try the tool for yourself—credits are now extended through Dec. 31. 🧵 buff.ly/fXoQxxY14 Sep 2026 18:30 +0000at://did:plc:i4kytxgsu3yfsrt2ml3o7tgq/app.bsky.feed.post/3mviql3olk22nhttps://bsky.app/profile/ai2.bsky.social/post/3mv3wv46gq724Training an LLM by showing it answers people prefer – and ones they don’t – can improve it while quietly worsening behaviors. Goodfire AI used Ai2’s open post-training stack to predict how a full training run would change responses to different prompts. 🧵 buff.ly/RuJxLM109 Sep 2026 16:19 +0000at://did:plc:i4kytxgsu3yfsrt2ml3o7tgq/app.bsky.feed.post/3mv3wv46gq724https://bsky.app/profile/ai2.bsky.social/post/3muztlrwqti2gWe're at #ECCV2026 with papers & talks across the conference. Come say hello and learn about our latest research!08 Sep 2026 20:14 +0000at://did:plc:i4kytxgsu3yfsrt2ml3o7tgq/app.bsky.feed.post/3muztlrwqti2ghttps://bsky.app/profile/ai2.bsky.social/post/3mupnqr5ljw2qML emulators mimic climate processes faster than traditional models. Next is coupling atmosphere & ocean emulators so their predictions feed into each other as the simulation runs. With the E3SM team, we built a system that does that: SamudrACE-E3SMv3. 🧵 buff.ly/9ShSTCM04 Sep 2026 19:03 +0000at://did:plc:i4kytxgsu3yfsrt2ml3o7tgq/app.bsky.feed.post/3mupnqr5ljw2q