Tal Haklay

@tal_haklay

Member of Technical Staff @GoodfireAI

San Francisco, CA

talhaklay.github.io

Joined March 2022

652 Following

757 Followers

Replies Reposts Media

Pinned
Tal Haklay
@tal_haklay
May 14
Check out our new paper 🔥 It’s been so much fun working on this project!
Goodfire
@GoodfireAI
May 14
Neural networks do math by rotating shapes. We found a shape-rotating calculator hidden inside an LLM – and it’s used for more than just math! (1/6)
00:00
2
Tal Haklay
@tal_haklay
Oct 15
Good news from @GoodfireAI 🔥
Nick
@nickcammarata
Oct 15
interpretability might be the most important scientific problem in the world right now, as I don't think we can solve alignment if we don't know what we're building. I think I have good news about it. I co-authored early work in mechanistic interpretability at OpenAI and came
1
Tal Haklay
@tal_haklay
Oct 5
@sheridan_feucht and I will be presenting this work at #COLM2026 on Oct 7 during Poster Session 4 at 4:30 PM. Come find us at poster #87!
Goodfire
@GoodfireAI
May 14
Neural networks do math by rotating shapes. We found a shape-rotating calculator hidden inside an LLM – and it’s used for more than just math! (1/6)
00:00
Tal Haklay
@tal_haklay
Sep 23
Attending COLM? Come meet our team!🍻
Goodfire
@GoodfireAI
Sep 23
Coming to COLM? We’re hosting a happy hour on Wednesday (10/7) for interpretability, alignment, and life sciences researchers. Come meet members of the Goodfire team over vinyl and drinks! luma.com/timy2nh8
Tal Haklay
@tal_haklay
May 27
Submit your work! The 2nd Workshop on 𝐀𝐜𝐭𝐢𝐨𝐧𝐚𝐛𝐥𝐞 𝐈𝐧𝐭𝐞𝐫𝐩𝐫𝐞𝐭𝐚𝐛𝐢𝐥𝐢𝐭𝐲 will be held at COLM 2026 in San Francisco! Submission Deadline: June 21, 2026 @ActInterp
1