*still generating mental images using my brainGPT while drooling like a fool* guhhhhhhhh.
June 3, 2026 at 7:24 PM
*still generating mental images using my brainGPT while drooling like a fool* guhhhhhhhh.
A study in Nature Human Behaviour shows that large language models—especially BrainGPT, an LLM the authors tuned on the neuroscience literature—outperform experts in predicting neuroscience results and could assist scientists in making future discoveries. https://go.nature.com/3OBWeLV 🧪
December 3, 2024 at 8:09 PM
A study in Nature Human Behaviour shows that large language models—especially BrainGPT, an LLM the authors tuned on the neuroscience literature—outperform experts in predicting neuroscience results and could assist scientists in making future discoveries. https://go.nature.com/3OBWeLV 🧪
11 slots* my bad, braingpt hallucinated that one
June 25, 2026 at 10:40 PM
11 slots* my bad, braingpt hallucinated that one
BrainGPT 🧪
Coming soon: a large language model trained specifically for brain research.
I'm net positive, but also have mixed feelings. Curious to see how it evolves, for sure.
braingpt.org
Coming soon: a large language model trained specifically for brain research.
I'm net positive, but also have mixed feelings. Curious to see how it evolves, for sure.
braingpt.org
BrainGPT
This is the homepage for BrainGPT, a Large Language Model tool to assist neuroscientific research.
braingpt.org
June 28, 2023 at 2:08 PM
BrainGPT 🧪
Coming soon: a large language model trained specifically for brain research.
I'm net positive, but also have mixed feelings. Curious to see how it evolves, for sure.
braingpt.org
Coming soon: a large language model trained specifically for brain research.
I'm net positive, but also have mixed feelings. Curious to see how it evolves, for sure.
braingpt.org
While BrainBench focused on neuroscience, our approach is science general, so others can adopt our template. Everything is open weight and open source. Thanks to the entire team and the expert participants. Sign up for news at braingpt.org 8/8
BrainGPT
This is the homepage for BrainGPT, a Large Language Model tool to assist neuroscientific research.
BrainGPT.org
November 27, 2024 at 2:13 PM
While BrainBench focused on neuroscience, our approach is science general, so others can adopt our template. Everything is open weight and open source. Thanks to the entire team and the expert participants. Sign up for news at braingpt.org 8/8
心を読んでテキストに変換する「BrainGPT」が登場、実験の様子がムービーで確認可能
https://gigazine.net/news/20231218-braingpt/
https://gigazine.net/news/20231218-braingpt/
心を読んでテキストに変換する「BrainGPT」が登場、実験の様子がムービーで確認可能
2023年12月10日から16日にかけて行われた機械学習と計算論的神経科学のカンファレンスイベント「NeurIPS」において、シドニー工科大学の研究チームによる「生の脳波を直接言語に翻訳する」という大規模言語モデル「BrainGPT」の論文が注目論文として選出されました。
gigazine.net
December 18, 2023 at 3:00 AM
心を読んでテキストに変換する「BrainGPT」が登場、実験の様子がムービーで確認可能
https://gigazine.net/news/20231218-braingpt/
https://gigazine.net/news/20231218-braingpt/
Lately, foundation models like BrainGPT & Cognitive FMs are dominating AI & science. But is our future solely built on these models? What about alternative techniques? How do we keep our scientific ecosystem diverse? As a community, where do we see the future of NeuroAI?
January 13, 2025 at 12:02 AM
Lately, foundation models like BrainGPT & Cognitive FMs are dominating AI & science. But is our future solely built on these models? What about alternative techniques? How do we keep our scientific ecosystem diverse? As a community, where do we see the future of NeuroAI?
Predicting the results of experiments is challenging, especially in fields like neuroscience. This recent study shows that fine-tuned LLMs, like BrainGPT, can predict neuroscience results more accurately than human experts on benchmarks. 🧪
https://www.nature.com/articles/s41562-024-02046-9.pdf
https://www.nature.com/articles/s41562-024-02046-9.pdf
November 27, 2024 at 5:23 PM
Predicting the results of experiments is challenging, especially in fields like neuroscience. This recent study shows that fine-tuned LLMs, like BrainGPT, can predict neuroscience results more accurately than human experts on benchmarks. 🧪
https://www.nature.com/articles/s41562-024-02046-9.pdf
https://www.nature.com/articles/s41562-024-02046-9.pdf
Une étude de l’University College London révèle que l’IA prédit mieux les résultats scientifiques que les neuroscientifiques (81 % vs 63 %). L’outil « BrainGPT » atteint 86 % de précision, dévoilant des modèles cachés dans la recherche. www.nature.com/articles/s41...
November 28, 2024 at 11:40 AM
Une étude de l’University College London révèle que l’IA prédit mieux les résultats scientifiques que les neuroscientifiques (81 % vs 63 %). L’outil « BrainGPT » atteint 86 % de précision, dévoilant des modèles cachés dans la recherche. www.nature.com/articles/s41...
Hospital waiting room anxiety has me reading how BrainGPT just beat neuroscience experts at predicting study outcomes by integrating decades of research. AI scored 81% vs humans' 63%. Brain science's future is a team sport #neuroscience #neuroskyence 🧪🧠
Predicting the results of experiments is challenging, especially in fields like neuroscience. This recent study shows that fine-tuned LLMs, like BrainGPT, can predict neuroscience results more accurately than human experts on benchmarks. 🧪
https://www.nature.com/articles/s41562-024-02046-9.pdf
https://www.nature.com/articles/s41562-024-02046-9.pdf
November 27, 2024 at 6:06 PM
Hospital waiting room anxiety has me reading how BrainGPT just beat neuroscience experts at predicting study outcomes by integrating decades of research. AI scored 81% vs humans' 63%. Brain science's future is a team sport #neuroscience #neuroskyence 🧪🧠
There were no signs of leakage from the training to test set. Our approach is science general, so others can adopt our template. Open source. Thanks to the entire team and the expert participants, t-shirt raffle for you all soon :) Sign up for news at braingpt.org 6/6
BrainGPT
This is the homepage for BrainGPT, a Large Language Model tool to assist neuroscientific research.
BrainGPT.org
March 7, 2024 at 10:51 AM
There were no signs of leakage from the training to test set. Our approach is science general, so others can adopt our template. Open source. Thanks to the entire team and the expert participants, t-shirt raffle for you all soon :) Sign up for news at braingpt.org 6/6
Large language models surpass human experts in predicting neuroscience results www.nature.com/articles/s41...
Large language models surpass human experts in predicting neuroscience results - Nature Human Behaviour
Large language models (LLMs) can synthesize vast amounts of information. Luo et al. show that LLMs—especially BrainGPT, an LLM the authors tuned on the neuroscience literature—outperform experts in pr...
www.nature.com
November 27, 2024 at 10:49 PM
Large language models surpass human experts in predicting neuroscience results www.nature.com/articles/s41...
Recent research shows #LLMs like #BrainGPT, trained on #neuroscience literature, outperform human experts in predicting novel experimental outcomes. Could this reshape scientific discovery? #Science #FutureOfWork
www.nature.com/articles/s41...
www.nature.com/articles/s41...
Large language models surpass human experts in predicting neuroscience results - Nature Human Behaviour
Large language models (LLMs) can synthesize vast amounts of information. Luo et al. show that LLMs—especially BrainGPT, an LLM the authors tuned on the neuroscience literature—outperform experts in pr...
www.nature.com
November 30, 2024 at 8:04 AM
Recent research shows #LLMs like #BrainGPT, trained on #neuroscience literature, outperform human experts in predicting novel experimental outcomes. Could this reshape scientific discovery? #Science #FutureOfWork
www.nature.com/articles/s41...
www.nature.com/articles/s41...
Here's a recent talk I gave on the braingpt.org project, touching on findings from here, arxiv.org/abs/2403.03230. The video is sectioned for those wishing to skip the bits on explanatory vs. predictive approaches. youtu.be/sDt4-Q_jz7g?...
"Taming the neuroscience literature with explanatory and predictive models" (BrainGPT) - YouTube
Chapters:0:00 Introduction3:30 Process models (theoretical, explanatory)16:18 Models as tools (BrainGPT, predictive)39:03 ConclusionsModels can help scienti...
youtu.be
March 20, 2024 at 12:08 PM
Here's a recent talk I gave on the braingpt.org project, touching on findings from here, arxiv.org/abs/2403.03230. The video is sectioned for those wishing to skip the bits on explanatory vs. predictive approaches. youtu.be/sDt4-Q_jz7g?...
"Large language models surpass human experts in predicting neuroscience results" www.nature.com/articles/s41...
Large language models surpass human experts in predicting neuroscience results - Nature Human Behaviour
Large language models (LLMs) can synthesize vast amounts of information. Luo et al. show that LLMs—especially BrainGPT, an LLM the authors tuned on the neuroscience literature—outperform experts in pr...
www.nature.com
November 29, 2024 at 6:43 PM
"Large language models surpass human experts in predicting neuroscience results" www.nature.com/articles/s41...
Finally, LLMs can be augmented with neuroscience knowledge for better performance. We tuned Mistral on 20 years of the neuroscience literature using LoRA. The tuned model, which we refer to as BrainGPT, performed better on BrainBench. 7/8
November 27, 2024 at 2:13 PM
Finally, LLMs can be augmented with neuroscience knowledge for better performance. We tuned Mistral on 20 years of the neuroscience literature using LoRA. The tuned model, which we refer to as BrainGPT, performed better on BrainBench. 7/8
I recall an interview with Rusty Gage in Nat Neuroscience, where he mentioned that ChatGPT could help students choose research problems to study. Looks like this is shaping up now - BrainGPT to predict neuroscience findings! Fascinating… 🤔 www.nature.com/articles/s41...
Large language models surpass human experts in predicting neuroscience results - Nature Human Behaviour
Large language models (LLMs) can synthesize vast amounts of information. Luo et al. show that LLMs—especially BrainGPT, an LLM the authors tuned on the neuroscience literature—outperform experts in pr...
www.nature.com
November 28, 2024 at 1:58 AM
I recall an interview with Rusty Gage in Nat Neuroscience, where he mentioned that ChatGPT could help students choose research problems to study. Looks like this is shaping up now - BrainGPT to predict neuroscience findings! Fascinating… 🤔 www.nature.com/articles/s41...
Need to take a careful look but is BrainGPT available to users??
November 27, 2024 at 4:09 PM
Need to take a careful look but is BrainGPT available to users??
Good News: Microsoft's Accelerating Foundation Models Research initiative has provided computing to help train BrainGPT, a tool to assist neuroscience research. Thank You! Sign-up at BrainGPT.org for updates, including on our forthcoming benchmark slated for late 2023.
·
·
October 9, 2023 at 2:13 PM
Good News: Microsoft's Accelerating Foundation Models Research initiative has provided computing to help train BrainGPT, a tool to assist neuroscience research. Thank You! Sign-up at BrainGPT.org for updates, including on our forthcoming benchmark slated for late 2023.
·
·
🧪 An AI model outperformed experts in predicting neuroscience study outcomes, per Nature Human Behaviour.
BrainGPT lead with 86% accuracy, surpassing human accuracy of 63.4% 🩺🖥️ 🧠
BrainGPT lead with 86% accuracy, surpassing human accuracy of 63.4% 🩺🖥️ 🧠
AI Predicts Neuroscience Study Results Better Than Experts
New study shows AI large language models (LLMs) outperform human neuroscientists in predicting neuroscience study outcomes.
www.psychologytoday.com
December 3, 2024 at 4:10 PM
🧪 An AI model outperformed experts in predicting neuroscience study outcomes, per Nature Human Behaviour.
BrainGPT lead with 86% accuracy, surpassing human accuracy of 63.4% 🩺🖥️ 🧠
BrainGPT lead with 86% accuracy, surpassing human accuracy of 63.4% 🩺🖥️ 🧠
”brainGPT” is killing me 💀
June 3, 2026 at 9:05 PM
”brainGPT” is killing me 💀
LLMs can be augmented with neuroscience knowledge for better performance. We tuned Llama-2-7b (chat) on 20 years of the neuroscience literature using LoRA. The tuned model, which we refer to as BrainGPT, performed better on BrainBench. 5/6
March 7, 2024 at 10:51 AM
LLMs can be augmented with neuroscience knowledge for better performance. We tuned Llama-2-7b (chat) on 20 years of the neuroscience literature using LoRA. The tuned model, which we refer to as BrainGPT, performed better on BrainBench. 5/6
www.nature.com/articles/s41...
"LLMs trained on the vast scientific literature could ... forecast novel results better than human experts. ... Like human experts, when LLMs indicated high confidence in their predictions, their responses were more likely to be correct"
"LLMs trained on the vast scientific literature could ... forecast novel results better than human experts. ... Like human experts, when LLMs indicated high confidence in their predictions, their responses were more likely to be correct"
Large language models surpass human experts in predicting neuroscience results - Nature Human Behaviour
Large language models (LLMs) can synthesize vast amounts of information. Luo et al. show that LLMs—especially BrainGPT, an LLM the authors tuned on the neuroscience literature—outperform experts in pr...
www.nature.com
November 28, 2024 at 12:09 AM
www.nature.com/articles/s41...
"LLMs trained on the vast scientific literature could ... forecast novel results better than human experts. ... Like human experts, when LLMs indicated high confidence in their predictions, their responses were more likely to be correct"
"LLMs trained on the vast scientific literature could ... forecast novel results better than human experts. ... Like human experts, when LLMs indicated high confidence in their predictions, their responses were more likely to be correct"