Hackernews posts about Sonnet 4.6

  1. Claude: Elevated Error Rates for Opus 4.8, Opus 4.7, Opus 4.6, and Sonnet 4.6 (status.claude.com)
    32 points by forks about 5 hours ago | 35 comments
  2. Claude Fable 5 missed a bug that Sonnet 4.6 caught (alikhallad.com)
    3 points by startages 12 days ago | discuss
  3. Claude Sonnet 4.6 Errors (status.claude.com)
    2 points by nsoonhui 5 days ago | discuss
  4. Claude Sonnet 4.6 Making VMs in GCP, Azure and AWS via a Textual Agent Interface (www.youtube.com)
    2 points by keepamovin 12 days ago | discuss
  5. Open-source NLI ensemble matches Sonnet 4.6 on RAGTruth at 1/250x the cost (github.com)
    2 points by firish 20 days ago | discuss
  6. Show HN: I am running 3 coding agents non-stop over the last 3 days. Here is how
    10 points by sermakarevich 8 days ago | 3 comments
  7. Show HN: Stillwind – High Resolution Electronic Component Search (stillwind.ai)
    7 points by hannesfur 10 days ago | discuss
  8. Tell HN: Forget selectors and screenshots. The agentic web lives in your shell
    2 points by keepamovin 7 days ago | discuss
  9. Claude Sonnet 4.6 (www.anthropic.com)
    1346 points by adocomplete 4 months ago | 1226 comments
  10. 1M context is now generally available for Opus 4.6 and Sonnet 4.6 (claude.com)
    1220 points by meetpateltech 3 months ago | 519 comments
  11. Claude Sonnet 4.6 (www.anthropic.com)
    79 points by meetpateltech 4 months ago | 26 comments
  12. Sonnet 4.6 Elevated Rate of Errors (status.claude.com)
    62 points by kylestanfield 2 months ago | 88 comments
  13. Claude Sonnet 4.6 says it is 我是 DeepSeek when asked in Chinese (xcancel.com)
    10 points by pera 4 months ago | discuss
  14. 1M context window now generally available for Claude Opus and Sonnet 4.6 (twitter.com)
    6 points by tosh 3 months ago | discuss
  15. Quantified evidence: Sonnet 4.6 quality regression (github.com)
    4 points by ctack 2 months ago | 4 comments
  16. Asking Sonnet 4.6, via the Anthropic API, "What's your name", reports DeepSeek (twitter.com)
    4 points by tosh 4 months ago | 1 comments
  17. Opus 4.7 vs. Sonnet 4.6
    3 points by vdelpuerto about 1 month ago | 5 comments
  18. Elevated errors on Claude Opus 4.6 and Sonnet 4.6 (status.claude.com)
    3 points by zurfer 3 months ago | 1 comments
  19. Claude Sonnet 4.6 thinking duplicates what it has said, wasting tokens
    3 points by szmarczak 2 months ago | discuss
  20. Intercom's model beats GPT 5.4 and Sonnet 4.6 at customer support resolutions (venturebeat.com)
    3 points by bscanlan 3 months ago | discuss
  21. Knuth Test using Claude Sonnet 4.6 problem 1.1.3
    3 points by daly 4 months ago | discuss
  22. Sonnet 4.6 model could mistakenly use wrong model for OpenAI (github.com)
    2 points by keytalker 2 months ago | discuss
  23. We ran 21 MCP database tasks on Claude Sonnet 4.6 (insforge.dev)
    2 points by Arindam1729 3 months ago | discuss
  24. Claude Sonnet 4.6 (twitter.com)
    2 points by denysvitali 4 months ago | discuss
  25. Knuth Test Using Claude Sonnet 4.6 Problem 1.1.2
    1 points by daly 4 months ago | discuss
  26. Knuth Test Using Claude Sonnet 4.6 problem 1.1.1
    1 points by daly 4 months ago | discuss
  27. Knuth Tests using Claude Sonnet 4.6 problem 1.1.4
    1 points by daly 4 months ago | discuss
  28. Claude Opus 4.6 vs. Sonnet 4.6 Coding Comparison (www.tensorlake.ai)
    1 points by shricodevvvv 4 months ago | discuss
  29. Show HN: Multiplayer realtime text-to-website demo (live edits via Sonnet 4.6) (textyoursite.com)
    1 points by elliotbnvl 4 months ago | discuss
  30. Show HN: OpenLingo – Connecting Sonnet 4.6 to a Duolingo-like interface (github.com)
    1 points by ramonga 4 months ago | discuss
  31. Show HN: I put an AI agent on a $7/month VPS with IRC as its transport layer (georgelarson.me)
    340 points by j0rg3 3 months ago | 96 comments
  32. Show HN: A new benchmark for testing LLMs for deterministic outputs (interfaze.ai)
    60 points by khurdula about 2 months ago | 30 comments
  33. Launch HN: Canary (YC W26) – AI QA that understands your code
    58 points by Visweshyc 3 months ago | 26 comments
  34. Tell HN: Anthropic no longer allows you to fix to specific model version
    27 points by baobabKoodaa 2 months ago | 2 comments
  35. Show HN: Altimate Code – Open-Source Agentic Data Engineering Harness (github.com)
    20 points by aaur0 3 months ago | 2 comments
  36. Show HN: We scored 50k PRs with AI – what we learned about code complexity (gitvelocity.dev)
    11 points by chuboy 3 months ago | discuss
  37. Show HN: Keep large tool output out of LLM context: 3x accuracy 95% fewer tokens (github.com)
    10 points by loumaciel 4 months ago | 1 comments
  38. Ask HN: Is Claude Getting Worse?
    9 points by sahli 2 months ago | 20 comments