siddhadev
LightNews LightNews
siddhadev.bsky.social
siddhadev
@siddhadev.bsky.social
3 followers 24 following 6 posts
Posts Replies Media Videos
siddhadev.bsky.social
I've been just about to get into fitness, but then got sidetracked into vibe coding kpe.github.io/workout-trac...
Home Workout Tracker
kpe.github.io
May 23, 2025 at 3:15 PM
siddhadev.bsky.social
Just another podcast on machine learning security and robustness (some MLOps) in case someone (me) wants to catch up on the go youtube.com/playlist?lis... #mlops #machinelearning #deeplearning #datascience
The Robust And Secure Machine Learning Podcast - YouTube
Insightful and engaging recaps on seminal works in the fields of ML security and robustness.
youtube.com
January 9, 2025 at 4:06 PM
siddhadev.bsky.social
New advancement in #LLM interpretability by Antrotic - www.anthropic.com/research/map...
Mapping the Mind of a Large Language Model \ Anthropic
We have identified how millions of concepts are represented inside Claude Sonnet, one of our deployed large language models. This is the first ever detailed look inside a modern, production-grade larg...
www.anthropic.com
May 22, 2024 at 7:03 AM
siddhadev.bsky.social
new Long-Context Retrieval Benchmark and M2-BERT models by HazyResearch #LLM
hazyresearch.stanford.edu/blog/2024-05...
Announcing LoCoV1 and the Latest M2-BERT Models
Benchmarking and Building Long-Context Retrieval Systems
hazyresearch.stanford.edu
May 21, 2024 at 12:52 PM
siddhadev.bsky.social
medium.com/@siddhadev/c...
Compression in Unsupervised Learning and Bayesian Flow Networks
This is a short post to collect some resources on ideas around compression, language modeling (or probabilistic modeling in general), and…
medium.com
May 21, 2024 at 11:51 AM
siddhadev.bsky.social
No Large Language Models in 5 years?
medium.com/@siddhadev/n...
No Large Language Models in 5 Years?
Recently, Yann LeCun made a bold prediction about autoregressive LLMs, by saying:
medium.com
May 21, 2024 at 11:51 AM