Myra Deng
@myra_deng
Followers
1K
Following
954
Media
10
Statuses
98
aligning models @goodfireAI, prev @stanford and @twosigma
Joined January 2018
RT @GoodfireAI: Arc Institute trained their foundation model Evo 2 on DNA from all domains of life. What has it learned about the natural w….
0
16
0
RT @GoodfireAI: Adversarial examples - a vulnerability of every AI model, and a “mystery” of deep learning - may simply come from models cr….
0
24
0
RT @GoodfireAI: New research! Post-training often causes weird, unwanted behaviors that are hard to catch before deployment because they on….
0
44
0
🗓️ Mark your calendars for August 26 and join us for a #GenSF meetup covering mechanistic interpretability in modern AI models. Our Partner @whoisnnamdi will moderate a fireside chat with leaders from Lightspeed-backed companies with @AnthropicAI’s Researcher @Jack_W_Lindsey
0
0
16
RT @jack_merullo_: Could we tell if gpt-oss was memorizing its training data? I.e., points where it’s reasoning vs reciting? We took a quic….
0
50
0
RT @GoodfireAI: AI already accelerates materials R&D, but understanding what models learn about structure-property relationships could yiel….
0
9
0
RT @zhengdongwang: I wrote some fiction in the style of AI 2027. It combines the parts of AI 2027 and AI as Normal Technology that resonat….
0
8
0
Just wrote a piece on why I believe interpretability is AI’s most important frontier - we're building the most powerful technology in history, but still can't reliably engineer or understand our models. With rapidly improving model capabilities, interpretability is more urgent,
0
0
16
I knew Claude was from New England.
0
0
14
Has anyone used any good AI shopping assistants? I’ve tried @shopondaydream, deep research but couldn’t get either to work for me. Maybe this is a sign to stop buying clothes :/.
1
1
10
RT @GoodfireAI: (1/7) New research: how can we understand how an AI model actually works? Our method, SPD, decomposes the *parameters* of n….
0
87
0
RT @leedsharkey: A few months ago, we published . Attribution-based parameter decomposition -- a method for decomposing a network's paramet….
0
22
0
RT @GoodfireAI: New research update! We replicated @AnthropicAI's circuit tracing methods to test if they can recover a known, simple trans….
0
53
0
>be you.>work in HFT .>have existential dread .>see this tweet, wonder if your skills could be better used to make AGI safe.>apply to attend our happy hour, meet the @GoodfireAI team.>build safe AGI.
>be you.>work in HFT shaving nanoseconds off latency or extracting bps from models.>have existential dread.>see this tweet, wonder if your skills could be better used making AGI.>apply to attend this party, meet the openai team.>build AGI.
5
14
284
