Jordan Taylor

@JordanTensor

Working on new methods for understanding machine learning systems and entangled quantum systems.

Brisbane

sites.google.com/view/jordanten…

Replies Reposts Media

Pinned
Jordan Taylor
@JordanTensor
May 17, 2024
I'm keen to share our new library for explaining more of a machine learning model's performance more interpretably than existing methods. This is the work of Dan Braun, Lee Sharkey and Nix Goldowsky-Dill which I helped out with during @MATSprogram: 🧵1/8
Lee Sharkey
@leedsharkey
May 17, 2024
Proud to share Apollo Research's first interpretability paper! In collaboration w @JordanTensor! ⤵️ publications.apolloresearch.ai/end_to_end_spa… Identifying Functionally Important Features with End-to-End Sparse Dictionary Learning Our SAEs explain significantly more performance than before! 1/
1
Jordan Taylor
@JordanTensor
Sep 3
Unfortunate news for monitorability. Some excerpts from the system card 🧵
Joseph Bloom
@JBloomAus
Sep 3
Replying to @JBloomAus
We found Astra can solve much more difficult problems in a single forward pass than past models, with a no-reasoning math time horizon of 30 minutes (!) compared to 4 minutes for GPT 5.6 Sol.
1
Jordan Taylor
@JordanTensor
May 21
There are a lot of pathways via which AI oversight is likely to degrade! Latent reasoning architectures, situational awareness, representational drift... We wrote a report ranking them. Here I'll go into some which worry me most 🧵
AI Security Institute (AISI)
@AISecurityInst
May 21
The safety of advanced AI systems increasingly depends on the ability to oversee them. Our new report examines today’s AI oversight landscape, finding many pathways likely to lead to its degradation.🧵
1
Jordan Taylor
@JordanTensor
May 1
Come work with me!
Joseph Bloom
@JBloomAus
May 1
(My team) Model Transparency at @AISecurityInst is hiring Research Engineers and Research Scientists! Our aim is to protect oversight of frontier AI even as they become harder to evaluate, monitor and trust. As capabilities scale, this is becoming a harder and more important
Jordan Taylor
@JordanTensor
Mar 30
Excited to see this!
7vik
@satvikgolechha
Mar 30
Research from Model Transparency @ UK AISI: we reproduce the Anthropic work "Natural Emergent Misalignment from Reward Hacking in Production RL" using OS models, RL environments, algorithms, and tooling + we share an unexpected result related to CoT faithfulness. 🧵 (1 of 7)