Profile avatar
sraval.bsky.social
Physics, Visualization and AI PhD @ Harvard | Embedding visualization and LLM interpretability | Love pretty visuals, math, physics and pets | Currently into manifolds Wanna meet and chat? Book a meeting here: https://zcal.co/shivam-raval
41 posts 684 followers 1,238 following
Prolific Poster
comment in response to post
Here are the slides from the presentation: docs.google.com/presentation... Feedback, comments or suggestions are most welcome 😄
comment in response to post
Update: The event is free now, thanks to generous funding from Northeastern University!
comment in response to post
1) In the narrow area of prompt generation techniques LLMs can generate ideas rated as more novel and exciting. They are sometimes less feasible. Out of 4000 ideas generated, only 200 were potentially unique. arxiv.org/abs/2409.04109
comment in response to post
To wrap your head around agents and think through the ethics, our Society and Ethics team put together a great resource - 👏 @mmitchell.bsky.social @sashamtl.bsky.social @evijit.io @giadapistilli.com huggingface.co/blog/ethics-...
comment in response to post
Yes, me too! Currently trying to get myself to update my website
comment in response to post
Can’t dm you, but I have someone to nominate!
comment in response to post
The closest this DataMapPlot allows is to be able to search over metadata, including keywords: datamapplot.readthedocs.io/en/latest/in... I am currently working on adding semantic search functionality to the library!
comment in response to post
Please add me in!