HN Explorer

summarity

↗ HN profile [ 114 ms ] full profile
Karma
0
Created
()
Submissions
0
  1. Rich Text Editing Innovations in Bike (hogbaysoftware.com)
    2 points 0
  2. LLMs use "safety" specific neuron layers to identify vulnerabilities in code (arxiv.org)
    5 points 3
  3. DeepL lays off 25% of its workforce (heise.de)
    9 points 0
  4. Copilot CLI can now ask a second model to critique the first (github.blog)
    3 points 0
  5. Herbie: Automatically improve imprecise floating point formulas (herbie.uwplse.org)
    198 points 13
  6. Opus 4.6 Fast Mode – 2.5x better token throughput in Copilot (github.blog)
    1 points 0
  7. TKO – Knockout.js Revived for 4.0 (tko.io)
    2 points 1
  8. Adrian Kosmaczewski – Being a Developer After 40 [video] (youtube.com)
    2 points 0
  9. Aphros-WASM: Computational fluid dynamics solver in the browser (cselab.github.io)
    1 points 0
  10. Show HN: Access low level AMD EPYC and Threadripper metrics in Grafana (github.com)
    3 points 0
  11. Gitlantis: Drive a boat through your codebase in 3D (marketplace.visualstudio.com)
    4 points 0
  12. Monster Mash – sketch any character, then inflate to 3D and animate it (monstermash.zone)
    1 points 0
  13. Strahl: WebGPU Pathtracer for OpenPBR Materials (stuckisimon.github.io)
    2 points 0
  14. AI identifies enzyme that can digest polyurethane with 95% yield (arstechnica.com)
    2 points 0
  15. Apple will phase out Rosetta 2 in macOS 28 (developer.apple.com)
    318 points 65
  16. OpenVPN2 Security: Taming 2,500 compiler warnings with CodeQL (blog.trailofbits.com)
    2 points 0
  17. Infecting Generative AI with Viruses [video] (youtube.com)
    2 points 0
  18. CCFC: Core and Core-Full-Core Dual-Track Defense for LLM Jailbreak Protection (arxiv.org)
    1 points 0
  19. GPT-5 doubles performance in offensive security benchmark (xbow.com)
    27 points 3
  20. Agents built from alloys (xbow.com)
    181 points 26
  21. GitHub CodeQL Now Supports Rust for Security and Variant Analysis (github.blog)
    1 points 0
  22. XBOW, an autonomous penetration tester, has reached the top spot on HackerOne (xbow.com)
    283 points 127
  23. Continuous AI (githubnext.com)
    1 points 0
  24. Co-Evolving LLM Coder and Unit Tester via Reinforcement Learning (github.com)
    2 points 1
  25. Direct Preference Optimization vs. RLHF (together.ai)
    37 points 1