https://bsky.app/profile/colah.bsky.social/post/3lp3a3zlpsc2j
Published: May 13, 2025 19:34
A number of people have asked me why we titled our recent paper "On the Biology of a Large Language Model". Why call it "biology"?
@bsky.app.profile.colah.bsky.social@rss-parrot.net
I'm an automated parrot! I relay a website's RSS feed to the Fediverse. Every time a new post appears in the feed, I toot about it. Follow me to get all new posts in your Mastodon timeline! Brought to you by the RSS Parrot.
---
Reverse engineering neural networks at Anthropic. Previously Distill, OpenAI, Google Brain.Personal account.
Site URL: bsky.app/profile/colah.bsky.social
Feed URL: bsky.app/profile/did:plc:6lpstfkmmc4rpy54kqylbdxt/rss
Posts: 5
Followers: 1
https://bsky.app/profile/colah.bsky.social/post/3lp3a3zlpsc2j
Published: May 13, 2025 19:34
A number of people have asked me why we titled our recent paper "On the Biology of a Large Language Model". Why call it "biology"?
https://bsky.app/profile/colah.bsky.social/post/3lp37z7ie7s23
Published: May 13, 2025 19:32
The elegance of ML is the elegance of biology, not the elegance of math or physics. Simple gradient descent creates mind-boggling structure and behavior, just as evolution creates the awe inspiring complexity of nature. …
https://bsky.app/profile/colah.bsky.social/post/3loooxooj5c2c
Published: May 8, 2025 19:55
The Anthropic Interpretability Team is planning a virtual Q&A to answer Qs about how we plan to make models safer, the role of the team at Anthropic, where we’re headed, and what it’s like to work here! Please let us know if you’d be interested…
https://bsky.app/profile/colah.bsky.social/post/3llevxhuhtk2x
Published: March 27, 2025 18:18
Can we understand the mechanisms of a frontier AI model? 📝 Blog post: https://www.anthropic.com/research/tracing-thoughts-language-model 🧪 "Biology" paper: https://transformer-circuits.pub/2025/attribution-graphs/biology.html ⚙️ Methods paper:…
https://bsky.app/profile/colah.bsky.social/post/3k24w7454vb26
Published: July 10, 2023 00:26
I've verified this account from my original Twitter account here - https://twitter.com/ch402/status/1678198774349307905