HN Explorer

shishirpatil

↗ HN profile [ 520 ms ] full profile
Karma
103
Created
October 5, 2022 (3y ago)
Submissions
0
CS PhD at UC Berkeley. Looking into Systems for ML. https://shishirpatil.github.io/
  1. Specifications: The missing link to make development of LLM an eng discipline (arxiv.org)
    2 points 0
  2. LLM Agent Arena from Gorilla X Lmsys Chatbot Arena (agent-arena.com)
    12 points 0
  3. Llama 3.2 1B and 3B on-device models (twitter.com)
    6 points 0
  4. BFCL V3: LLM Multi-Turn and Multi-Step Function Calling Evaluation (gorilla.cs.berkeley.edu)
    6 points 0
  5. Berkeley Function Calling Leaderboard v2 with User Contributed Data (gorilla.cs.berkeley.edu)
    4 points 0
  6. Autonomous LLM agents with human-out-of-loop (arxiv.org)
    14 points 8
  7. Andrew Ng on LLMs and Tool Use (twitter.com)
    4 points 0
  8. New Leader Alert: Anthropic's Claude3 Tops Berkeley Function Calling Leaderboard (gorilla.cs.berkeley.edu)
    15 points 1
  9. If you are using LLM RAG – you should be doing RAFT (techcommunity.microsoft.com)
    52 points 13
  10. Berkeley LLM Function-Calling Leaderboard and State-of-Art OpenFunctions-v2 (gorilla.cs.berkeley.edu)
    50 points 1
  11. Gorilla Openfunctions: Apache 2.0 function calling LLM (gorilla.cs.berkeley.edu)
    6 points 2
  12. MemGPT – LLMs with self-editing memory for unbounded context (github.com)
    363 points 85
  13. Gorilla-CLI: LLMs for CLI including K8s/AWS/GCP/Azure/sed and 1500 APIs (github.com)
    152 points 62
  14. Gorilla LLM is now Apache 2.0 – can be used commercially (github.com)
    9 points 1
  15. Gorilla: Large Language Model connected with massive APIs (gorilla.cs.berkeley.edu)
    255 points 119