
Ted Moskovitz
@ted_moskovitz
Followers
1K
Following
3K
Media
32
Statuses
299
scaling RL at @AnthropicAI. previously: @GatsbyUCL and @GoogleDeepMind
London, UK
Joined October 2019
RT @Aaditya6284: Excited to share this work has been accepted as an Oral at #icml2025 -- looking forward to seeing everyone in Vancouver, a….
0
5
0
RT @andy_l_jones: Anthropic's hosting a social in NYC in mid-June for quants interested in a career jump. Sign up link below!. I was a quan….
0
5
0
RT @SWC_Neuro: @alinagbnva, Lars Rollik, Jasvin Kaur, @ted_moskovitz, Joseph Cohen, @EmmettJThompson, Troy Margrie, @ClopathLab & @Stephens….
0
1
0
RT @_rockt: Fascinating new paper on learning dynamics of in-context learners: "Strategy Coopetition Explains the Emergence and Transience….
0
13
0
New work led by @Aaditya6284! This was a really fun and interesting project, and I think there are a lot of cool insights to be had on the interplay between in-context and in-weights learning on the circuit level.
Transformers employ different strategies through training to minimize loss, but how do these tradeoff and why?. Excited to share our newest work, where we show remarkably rich competitive and cooperative interactions (termed "coopetition") as a transformer learns. Read on 🔎⏬
0
1
10
RT @neilhoulsby: And I am excited to announce that I have joined Anthropic, Switzerland! 🇨🇭. Anthropic is setting up a new office in Zurich….
0
23
0
RT @Jack_W_Lindsey: If you’re interested in interpretability of LLMs, or any other AI safety-related topics, consider applying to Anthropic….
0
25
0
RT @janleike: Apply to join the Anthropic Fellows Program!. This is an exceptional opportunity to join AI safety research, collaborating wi….
0
84
0
Was really lucky to help out on this project at the end of my PhD—huge congrats to @Aaditya6284 @AlbertSYue @djstrouse @louvishh on getting it over the line!.
Math reasoning benchmarks keep getting saturated…. Excited to introduce HARD-Math: Human-Annotated Reasoning Dataset for Math. Consisting of 4,780 short answer problems, based on the AHSME, AMC, & AIME contests, HARD-Math still poses a challenge for frontier LLMs. Read on 🔎⏬
0
1
14
RT @AnthropicAI: Claude 3.5 Haiku is now available on our API, Amazon Bedrock, and Google Cloud's Vertex AI. Haiku is fast and particularl….
0
381
0
RT @oh_that_hat: We finally formalize the RASP-L conjecture in this work!. - theoretical guarantee on generalization for C-RASP tasks.- val….
0
10
0
RT @AnthropicAI: New Anthropic research: Evaluating feature steering. In May, we released Golden Gate Claude: an AI fixated on the Golden….
0
189
0
RT @Jack_W_Lindsey: Really excited to share our work on crosscoders, a generalization of sparse autoencoders that allows us to identify sha….
0
41
0
RT @oh_that_hat: We taught Claude how to use a computer and it is 🤯! This is a concrete glimpse into the future where every computer task c….
0
8
0
RT @pujaarajan: Thrilled to have been part of the team that helped bring computer use capabilities to Claude!.
0
63
0
RT @TrentonBricken: Excited this small update is out! . We explore using dictionary learning features as classifier….
0
15
0
RT @ZoubinGhahrama1: I moved from Toronto to the London with @geoffreyhinton as one of the founding faculty of the @GatsbyUCL Unit. A few y….
0
19
0
RT @Jack_W_Lindsey: Recently at @CogCompNeuro I led a tutorial on sparse autoencoders for LLM interpretability. For anyone interested, here….
0
45
0
RT @GatsbyUCL: 👋 Attending #ICML2024 in 🇦🇹 next week?.Don't forget to check out work involving our researchers!
0
12
0