HN Explorer

broyojo

↗ HN profile [ 18.9 ms ] full profile
Karma
0
Created
()
Submissions
0
  1. 1 points 0
  2. Show HN: Running an LLM Inside Scratch (github.com)

    This runs the smallest llama2.c checkpoint (stories260K) inside Scratch/TurboWarp by compiling C inference code into Scratch blocks using llvm2scratch. The model is quantized to Q8_0 and packed into Scratch lists. If…

    1 points 0
  3. SWE-Agent: Agent-Computer Interfaces Enable Automated Software Engineering (arxiv.org)
    1 points 0