Roma Patel

Why they matter

Researcher with public evidence across AI research, Models & releases, Safety & security.

AI signals
1
past 30d
Sources
1
distinct domains
Discussions
0
past 30d
Latest signal
3d ago
View every signal from Roma Patel →
research scientist @deepmind. language & multi-agent rl & interpretability. phd @BrownUniversity '22 under ellie pavlick (she/her) https://roma-patel.github.io

Articles & links

we believe this is the start of a great interdisciplinary mission for nlp researchers to ensure that the language models built align with the long-term well-being of human users. read out paper for more thoughts on this topic arxiv.org/pdf/2608.02491

arxiv.org
View on Bluesky · ♥ 0 ↻ 0 ↩ 0 · 3d ago

Recent commentary

🚨 new position from my students and collaborators! ever since the release of chatgpt in 2022 (wow, 4 years ago!) chatbots are increasingly integrated into people's lives. we call for a shift towards "longitudinal measurements and mitigations in alignment frameworks 🧵

View on Bluesky · ♥ 3 ↻ 0 ↩ 1 · 3d ago

In Roma Patel's orbit

Center = Roma Patel. Left = members they follow (green edges). Right = members who follow them (blue edges). Top = mutual follows (orange edges, slightly larger). Drag any node to reposition; click to open that profile.