Saksham Arora — Chimera

Tag: LLM

7 items with this tag.

  • Aug 07, 2026

    Chimera

    • About
    • HFT
    • Systems
    • Performance
    • AI
    • LLM
    • cpp
    • Quant
    • Wiki
  • Aug 22, 2026

    A Free Mystery Model Just Beat GPT-5.6 on Coding, and Nobody Audited the Number

    • LLM
    • Benchmarks
    • Systems
  • Jul 21, 2026

    GPT-5.6 Closed a 30-Year Math Gap, and the Headline Skipped the Part That Matters

    • LLM
    • Optimization
    • Formal-Verification
    • Quant
  • Jul 13, 2026

    GPT-5.6 Beats Claude by 13 Points on One Benchmark, Loses by 16 on Another

    • LLM
    • Benchmarks
    • Systems
    • Inference
  • Jul 10, 2026

    NVIDIA Killed the Draft Model and Got 4x Throughput For Free

    • LLM
    • Inference
    • Systems
    • Speculative-Decoding
  • Jul 06, 2026

    The 518-Token Bug: When GPT-5.5's Reasoning Gets Cut Off at Fixed Intervals

    • LLM
    • Inference
    • Systems
    • Debugging
  • Jun 18, 2026

    The Average Latency Lie: What 100 LLM API Calls Taught Me About Benchmarking

    • LLM
    • Benchmarking
    • Latency
    • Systems
    • AI

  • GitHub
  • LinkedIn
  • Portfolio