shishirpatil

Joined 4 years ago

Karma

394

Submissions

43

Member since

Oct 5

CS PhD at UC Berkeley. Looking into Systems for ML. https://shishirpatil.github.io/

View on Hacker News

Recent submissions

Specifications: The missing link to make development of LLM an eng discipline arxiv.org

2 shishirpatil 1 year ago 0 comments

LLM Agent Arena from Gorilla X Lmsys Chatbot Arena agent-arena.com

12 shishirpatil 2 years ago 0 comments

Llama 3.2 1B and 3B on-device models twitter.com

6 shishirpatil 2 years ago 0 comments

BFCL V3: LLM Multi-Turn and Multi-Step Function Calling Evaluation gorilla.cs.berkeley.edu

6 shishirpatil 2 years ago 0 comments

Berkeley Function Calling Leaderboard v2 with User Contributed Data gorilla.cs.berkeley.edu

4 shishirpatil 2 years ago 0 comments

Autonomous LLM agents with human-out-of-loop arxiv.org

14 shishirpatil 2 years ago 8 comments

Andrew Ng on LLMs and Tool Use twitter.com

4 shishirpatil 2 years ago 0 comments

New Leader Alert: Anthropic's Claude3 Tops Berkeley Function Calling Leaderboard gorilla.cs.berkeley.edu

15 shishirpatil 2 years ago 1 comments

If you are using LLM RAG – you should be doing RAFT techcommunity.microsoft.com

52 shishirpatil 2 years ago 13 comments

Berkeley LLM Function-Calling Leaderboard and State-of-Art OpenFunctions-v2 gorilla.cs.berkeley.edu

50 shishirpatil 2 years ago 1 comments

Gorilla Openfunctions: Apache 2.0 function calling LLM gorilla.cs.berkeley.edu

6 shishirpatil 3 years ago 2 comments

Comment · 3 years ago

Hey @behnamoh, maybe you are referring to the community post pre-release? It is still very much live here: https://news.ycombinator.com/item?id=37894403! As we released MemGPT this morning (including discord bot, and on Twitter), we took the community feedback to emphasize more on the context length in the title :) Thank you all for the feedback and keep it coming - we are listening!

Comment · 3 years ago

Thanks @wilg and @littlestymaar ! Yeah totally, with the benefit of hindsight, this makes total sense! Hope you find some of our codebase useful to build on top of. We are an Apache 2.0 licensed open source project and welcome contributions :)

Comment · 3 years ago

Yeah! While it’s not known what close-sourced models do, what we think is happening based on some prompt attacks, is that they also use recursive summarization (in addition to what others have mentioned in this thread).

Comment · 3 years ago

Yeah absolutely! And hopefully with some of the techniques we introduce here, we can think of designing perpetual chat bots!