Top all-time · #17258
EvolutionaryScale
Company blog · evolutionaryscale.ai/blogaiscience
EvolutionaryScale is the company blog at evolutionaryscale.ai, writing about ai and science. Since 2024, 4 different Hacker News readers have linked it 6 times, most often “ESM3: Simulating 500M years of evolution with a language model”. No feed was found, so read it on the site itself.
Too few sampled comments (3) to say how often HN recommends it.?
Why HN links it
HN readers link EvolutionaryScale's posts on ESM3, a multimodal generative protein language model. The comments cite it as an example of AI producing original work, and one quotes its description.
Summarised by Claude from a sample of 3 HN comments that link here. Each comment is marked recommending, critical or neutral (citing without judging); how this works.
ESM3. Enabling scientists to understand, imagine, and create proteins.
Most-linked posts?
- /papers/esm3-simulating-500-million-years-of-evolution-with-a-language-model2 people · 2 mentions · first linked 2024-06-25
- ESM3: Simulating 500M years of evolution with a language model2 people · 2 mentions · first linked 2024-06-25
What Hacker News says?
There are many LLMs that are producing original "thought". ESM3: https://www.evolutionaryscale.ai/blog/esm3-release AlphaProof/AlphaGeometry2: https://deepmind.google/discover/blog/ai-solves-imo-problems... MatPilot discovering new materials: https://arxiv.org/abs/2411.08063 Then of course NVidia Omniverse with their digital-twin learning. https://blog.google/technology/ai/google-ai-big-scientific-b...
Comment linking /blog/esm3-release
on “YC is wrong about LLMs for chip design”Submitted ESM3: Simulating 500M years of evolution with a language model as a story · 34 points
HN discussionShow HN: We trained a bidirectional masked generative model on protein sequence, structure and function. ESM3 work over tokenized representations of multiple modalities and can generate proteins with high fidelity and controllability. ESM3 further improves with feedback using alignment methods similar to Reinforcement Learning from Human Feedback (RLHF) applied in LLMs. We have prompted ESM3 to generate fluorescent…
Comment linking /papers/esm3-simulating-500-million-years-of-evolution-with-a-language-model
on “ESM3 – a multimodal generative protein language model”Submitted Show HN: ESM C, setting a new state of the art for protein language models as a story · 11 points
HN discussionWe trained a bidirectional masked generative model on protein sequence, structure and function. ESM3 work over tokenized representations of multiple modalities and can generate proteins with high fidelity and controllability. ESM3 further improves with feedback using alignment methods similar to Reinforcement Learning from Human Feedback (RLHF) applied in LLMs. We have prompted ESM3 to generate fluorescent proteins…
Comment linking /papers/esm3-simulating-500-million-years-of-evolution-with-a-language-model
on a deleted threadSubmitted ESM3 – a multimodal generative protein language model as a story · 11 points
HN discussion