HN Explorer

skp1995

↗ HN profile [ 75.5 ms ] full profile
Karma
0
Created
()
Submissions
59
  1. Early Access Grok Build CLI (x.ai)
    33 points 1
  2. SOTA on swebench-verified: (re)learning the bitter lesson (aide.dev)
    1 points 0
  3. Mold: A Modern Linker (github.com)
    2 points 0
  4. Show HN: Aide, an open-source AI native IDE (aide.dev)

    Hey HN, We are Sandeep and Naresh, the creators of Aide. We are happy to open source and invite the community to try out Aide which is a VSCode fork built with LLMs integrated. To talk through the features, we…

    253 points 173
  5. Time to First Intelligence

    In today's world of LLMs or LRMs we are focussed on the "time to first token" which is how long does it take for the model to generate the first output token. This is super important in many cases: - code auto-complete…

    2 points 2
  6. Finetuning is now 1 second (ai.google.dev)
    2 points 1
  7. CodeStory (YC S23) Is Hiring a Founding Engineer for Building AI-Native IDE (workatastartup.com)
    1 points 0 job
  8. CodeStory (YC S23) is hiring a Founding Engineer for building an AI-native IDE (workatastartup.com)
    1 points 0 job
  9. Ask HN: Have you guys used the newer Claude models in production?

    Hey all! I have been using the Claude Opus and Haiku models since they dropped and its a very different feeling compared to other LLMs. Haiku with the longer context window and inference speed feels amazing to use and…

    1 points 0
  10. Starcoder-2 (huggingface.co)
    3 points 1
  11. Scuba is a wonderful data visualisation tool (research.facebook.com)
    1 points 1
  12. Python has 189X the dataset size compared to Rust (arxiv.org)
    2 points 4
  13. Why the IDE needs to be reimagined (codestory.ai)
    18 points 29
  14. LLMs can now walk the code graph (codestory.ai)
    9 points 0
  15. How to balance latency and performance with LLMs

    Hi all! I have been using various OpenAI and Palm-2 API in our pipeline. The pipeline by itself works and things are okay until there are issues with OpenAI (very frequent BadGateway issues with GPT4 model, or errors on…

    2 points 0
  16. LexGrep Grep through all of Lex Fridman podcasts (share.streamlit.io)
    3 points 3