Hackernews posts about Claude Sonnet

  1. $500 GPU outperforms Claude Sonnet on coding benchmarks (github.com)
    489 points by yogthos 13 days ago | 284 comments
  2. We ran 21 MCP database tasks on Claude Sonnet 4.6 (insforge.dev)
    2 points by Arindam1729 30 days ago | discuss
  3. Show HN: I solved Claude Code's context drift with persistent Markdown files
    4 points by Tanishq0333 23 days ago | 3 comments
  4. Tell HN: Pangram is easily-defeatable with Claude
    3 points by nunez 12 days ago | 4 comments
  5. Show HN: FC-Eval – CLI to Benchmark Local or Cloud LLMs on Function Calling (github.com)
    3 points by gauravvij137 22 days ago | discuss
  6. How long till every major provider sets their RSI loops in motion?
    3 points by foxindustrial 27 days ago | discuss
  7. Show HN: I added barcode scanning to my AI pricing app – 92% cheaper per scan (underpricedai.com)
    2 points by fkratzer 25 days ago | 1 comments
  8. Show HN: Lumen – vision-first browser agent (state of the art, open source) (github.com)
    2 points by fearlessboi 28 days ago | 1 comments
  9. Show HN: ClawAid – AI doctor that fixes OpenClaw in one command (github.com)
    2 points by jjj5666 30 days ago | 1 comments
  10. Show HN: OpenClaw Arena – Benchmark models on real tasks, rank by perf and cost (app.uniclaw.ai)
    2 points by skysniper 8 days ago | discuss
  11. More tokens, less cost: why optimizing for token count is wrong
    1 points by nicola_alessi 29 days ago | 9 comments
  12. Show HN: OpenClaw plugin – hard budget limits for agent tool calls (github.com)
    1 points by amavashev 24 days ago | 1 comments
  13. Show HN: I built an AI-powered technical interview prep tool (crackr.dev)
    1 points by wa5ina 29 days ago | 1 comments
  14. Show HN: Team agents that manage your CMS from Slack, WhatsApp, and Telegram (www.cosmicjs.com)
    1 points by tonyspiro 8 days ago | discuss
  15. Intercom's model beats GPT 5.4 and Sonnet 4.6 at customer support resolutions (venturebeat.com)
    3 points by bscanlan 13 days ago | discuss
  16. 1M context window now generally available for Claude Opus and Sonnet 4.6 (twitter.com)
    6 points by tosh 26 days ago | discuss
  17. Show HN: Altimate Code – Open-Source Agentic Data Engineering Harness (github.com)
    20 points by aaur0 20 days ago | 2 comments
  18. Ask HN: Leaving Notion, Codebase as a Wiki?
    3 points by kthaker1224 12 days ago | 3 comments
  19. Show HN: jj-benchmark – Evaluating AI agents on Jujutsu version control (tabbyml.github.io)
    5 points by wsxiaoys 27 days ago | 2 comments
  20. Launch HN: Canary (YC W26) – AI QA that understands your code
    58 points by Visweshyc 20 days ago | 26 comments
  21. Elevated errors on Claude Opus 4.6 and Sonnet 4.6 (status.claude.com)
    3 points by zurfer 22 days ago | 1 comments
  22. 1M context is now generally available for Opus 4.6 and Sonnet 4.6 (claude.com)
    1220 points by meetpateltech 26 days ago | 520 comments
  23. Ask HN: Alternatives to Claude (Code)?
    10 points by vixalien 1 day ago | 6 comments
  24. Sonnet 4.6 Elevated Rate of Errors (status.claude.com)
    9 points by kylestanfield 23 minutes ago | 4 comments
  25. Ask HN: Are you more quickly hitting Claude Code limits the past 48-96 hours?
    6 points by throwaway6977 13 days ago | 3 comments
  26. Agents are not thinking: a behavioral study of pwning sonnet (technoyoda.github.io)
    3 points by sci-genie 22 days ago | discuss
  27. Ask HN: Optimizing Claude Code Workflow: Subscription or API Billing?
    3 points by robeym 29 days ago | discuss
  28. Ask HN: What's the latest concensus on OpenAI vs. Anthropic $20/month tier?
    13 points by whatarethembits 10 days ago | 15 comments
  29. Show HN: We scored 50k PRs with AI – what we learned about code complexity (gitvelocity.dev)
    11 points by chuboy 9 days ago | discuss
  30. Show HN: Hopsule – Persistent Memory Layer for AI Engineering (hopsule.com)
    5 points by firatcan 20 days ago | 1 comments
More