Jacob Morrison

233 posts

Jacob Morrison banner
Jacob Morrison

Jacob Morrison

@jacobcares

PhD student @uwnlp @uwcse, research @allen_ai @ai2_allennlp

Seattle Katılım Nisan 2009
542 Takip Edilen488 Takipçiler
Sabitlenmiş Tweet
Jacob Morrison
Jacob Morrison@jacobcares·
I'm so excited that we're finally releasing Tülu 3, our new post-training recipe! We're releasing models built on top of Llama 3.1 base (OLMo coming soon!), all of our datasets, a (73 page!) paper, new evaluations, and all of our code.
Jacob Morrison tweet media
Ai2@allen_ai

Meet Tülu 3 -- a set of state-of-the-art instruct models with fully open data, eval code, and training algorithms. We invented new methods for fine-tuning language models with RL and built upon best practices in the community to scale synthetic instruction and preference data. Demo, GitHub, technical report, and models below 👇

English
1
16
91
12.6K
Jacob Morrison retweetledi
Mark Histed
Mark Histed@HistedLab·
This is only true for people who understand neither science nor economics. The NIH budget for this year is FIFTY times larger than OpenAI’s $1B pledge. The foundation of US science & innovation is public funding. The private sector cannot replace it. US science is being killed
Mark Histed tweet media
English
15
69
531
19.1K
Nathan Lambert
Nathan Lambert@natolambert·
A few facts, while the dust is settling. Ai2 still is... - releasing open models, folks want to, and it's actually required in the NSF grant - using substantial compute to do so from said grant - funded additionally by FFST (new funding body) on top of NSF, for work in open models Overall I'm confident in Ai2 doing great work this year.
English
22
49
635
57.8K
Nathan Lambert
Nathan Lambert@natolambert·
The NSF grant is 4 years long btw, just started.
English
3
1
76
8.2K
Saurabh Shah
Saurabh Shah@saurabh_shah2·
@natolambert Oh! sorry! yes, of course me leaving was my choice, as it is everyone else's I was under the impression that Ai2 had lost/limited funding to build open models. Sorry if i was mistaken, meant no harm
English
1
0
7
786
Kyle Lo
Kyle Lo@kylelostat·
Today I'm saying farewell to @allen_ai. I'm so proud of our team & grateful to have shared fully-open Olmo, Dolma, olmOCR, Molmo, etc with the world I know the team is more committed than ever to advancing open-source & open-science. Forever rooting for my dear friends 🫶
Kyle Lo tweet mediaKyle Lo tweet mediaKyle Lo tweet mediaKyle Lo tweet media
English
53
13
486
25.3K
Luca Soldaini 🎀
Luca Soldaini 🎀@soldni·
After 4yrs, today is my last day at @allen_ai It was an honor to work on Olmo, Dolma, olmOCR, Tulu, Molmo & other fully-open artifacts 🫡 Reception has been amazing & their adoption makes me SO PROUD 🥹 Team is super committed to open recipes; can't wait to see what's next!!!!
Luca Soldaini 🎀 tweet media
English
68
9
581
32K
Saurabh Shah
Saurabh Shah@saurabh_shah2·
Hacker houses are the adult version of going to Starbucks in high school so you can hangout w people with your laptop open and call it “studying”
English
2
0
35
2.9K
Jacob Morrison retweetledi
Peter Henderson
Peter Henderson@PeterHndrsn·
I feel this urgency too. But this is all so utterly avoidable with good policymaking. No one should be left behind because they didn't accumulate capital in 2026. There are so many people who aren't plugged into these conversations or are simply not in a position to do anything about it. Single mothers and fathers working three jobs to make ends meet cannot possibly work harder to accumulate capital. They already work hard enough as it is. People in this position should not be "left behind." There should be no "permanent underclass,” as many are worried about. Even if you're somewhat better off. People also shouldn't have to work themselves to the detriment of their health and families to shield against future labor impacts. They should be able to trust that their government will think ahead and make good policy.
Peter Henderson tweet media
English
8
42
334
26K
Jacob Morrison retweetledi
Teng Xiao
Teng Xiao@TengX6·
🚀 New work: Meta-Reinforcement Learning with Self-Reflection LLM agents shouldn't just solve problems. They should learn from their own attempts. Most current RL methods optimize single independent trajectories. Each attempt starts from scratch, with no mechanism to improve across attempts. But intelligent systems should get better after trying once. This raises a fundamental question: How do we train models to learn from their own attempts? We believe Meta-Reinforcement Learning may be a key paradigm for training future LLM agents, enabling models to adapt and improve across attempts and environments. In this work we introduce MR-Search, a training paradigm built around: 🧠 In-Context Meta-Reinforcement Learning 🪞 Self-Reflection 🔁 Learning to learn at test time 📄 Paper: arxiv.org/abs/2603.11327 💻 Code: github.com/tengxiao1/MR-S…
English
11
49
300
48.6K
Jacob Morrison retweetledi
Yanhong Li
Yanhong Li@YanhongLi2062·
very excited this is finally out!!!!!!!! 🚀 ✨ Olmo Hybrid: From Theory to Practice ✨ we explore hybrid language models that mix attention with linear RNN layers (Gated DeltaNet). turns out these hybrid models can be more expressive than pure transformers and linear RNNs while still scaling efficiently! paper, models, and training logs are all released
Ai2@allen_ai

Introducing Olmo Hybrid, a 7B fully open model combining transformer and linear RNN layers. It decisively outperforms Olmo 3 7B across evals, w/ new theory & scaling experiments explaining why. 🧵

English
3
19
152
19.6K
Jacob Morrison retweetledi
Kyle Lo
Kyle Lo@kylelostat·
our new Olmo Hybrid model combines attention with linear RNN layers 🍣training efficiency is crazy good. the model reaches same MMLU score as Olmo 3 in 50% of the tokens. also see this in many other tasks as always: weights, data, ckpts, training code, etc. all fully open
Kyle Lo tweet media
Ai2@allen_ai

Introducing Olmo Hybrid, a 7B fully open model combining transformer and linear RNN layers. It decisively outperforms Olmo 3 7B across evals, w/ new theory & scaling experiments explaining why. 🧵

English
5
8
69
6.2K
Jacob Morrison retweetledi
Ai2
Ai2@allen_ai·
Introducing Olmo Hybrid, a 7B fully open model combining transformer and linear RNN layers. It decisively outperforms Olmo 3 7B across evals, w/ new theory & scaling experiments explaining why. 🧵
Ai2 tweet media
English
17
129
785
168.3K
Kyle Lo
Kyle Lo@kylelostat·
someone's openclaw agent is spam emailing our team w generated questions about olmo, pls stop 🙄
English
4
1
50
8.6K
Jacob Morrison retweetledi
Dean W. Ball
Dean W. Ball@deanwball·
Think about the power Hegseth is asserting here. He is claiming that the DoD can force all contractors to stop doing business of any kind with arbitrary other companies. In other words, every operating system vendor, every manufacturer of hardware, every hyperscaler, every type of firm the DoD contracts with—all their services and products can be denied to any economic actor at will by the Secretary of War. This is obviously a psychotic power grab. It is almost surely illegal, but the message it sends is that the United States Government is a completely unreliable partner for any kind of business. The damage done to our business environment is profound. No amount of deregulatory vibes sent by this administration matters compared to this arson.
Secretary of War Pete Hegseth@SecWar

This week, Anthropic delivered a master class in arrogance and betrayal as well as a textbook case of how not to do business with the United States Government or the Pentagon. Our position has never wavered and will never waver: the Department of War must have full, unrestricted access to Anthropic’s models for every LAWFUL purpose in defense of the Republic. Instead, @AnthropicAI and its CEO @DarioAmodei, have chosen duplicity. Cloaked in the sanctimonious rhetoric of “effective altruism,” they have attempted to strong-arm the United States military into submission - a cowardly act of corporate virtue-signaling that places Silicon Valley ideology above American lives. The Terms of Service of Anthropic’s defective altruism will never outweigh the safety, the readiness, or the lives of American troops on the battlefield. Their true objective is unmistakable: to seize veto power over the operational decisions of the United States military. That is unacceptable. As President Trump stated on Truth Social, the Commander-in-Chief and the American people alone will determine the destiny of our armed forces, not unelected tech executives. Anthropic’s stance is fundamentally incompatible with American principles. Their relationship with the United States Armed Forces and the Federal Government has therefore been permanently altered. In conjunction with the President's directive for the Federal Government to cease all use of Anthropic's technology, I am directing the Department of War to designate Anthropic a Supply-Chain Risk to National Security. Effective immediately, no contractor, supplier, or partner that does business with the United States military may conduct any commercial activity with Anthropic. Anthropic will continue to provide the Department of War its services for a period of no more than six months to allow for a seamless transition to a better and more patriotic service. America’s warfighters will never be held hostage by the ideological whims of Big Tech. This decision is final.

English
544
2.8K
13.6K
1.2M

Keşfet

@natolambert @saurabh_shah2 @kylelostat @allen_ai @BaileyKuehl3 @soldni @elonmusk @BarackObama