Hackernews posts about Quesma

  1. Claude Code pricing: same tokens, same model, up to 40x the price (quesma.com)
    31 points by jakozaur 10 days ago | 10 comments
  2. AI Tokenomics: What AI tokens cost and where they're wasted (github.com)
    13 points by bkotrys 26 days ago | discuss
  3. Do Qwen 3.6 27B quantizations break the pelican? (quesma.com)
    9 points by stared 25 days ago | discuss
  4. I wired 4 models together in Claude Code. It backfired 4 ways on Terminal-Bench (quesma.com)
    7 points by bkotrys 11 days ago | 1 comments
  5. Tokenflation: When "Hi" triggers 33 tool calls (quesma.com)
    6 points by jakozaur 26 days ago | 1 comments
  6. Gemini 3.7 Flash, Grok 4.6, GLM-5.3 and DeepSeek V4 Pro joined the frontier (quesma.com)
    4 points by stared about 15 hours ago | discuss
  7. Tokenflation: When "Hi" triggers 33 tool calls (quesma.com)
    4 points by Bluestein 10 days ago | discuss
  8. Benchmarking Kimi K3, Opus 5, Grok 4.5, and Gemini 3.6 Flash on Baba Is You (quesma.com)
    4 points by stared 23 days ago | discuss
  9. Agentic coding costs in a nutshell: patterns, monitoring, metrics, optimization (github.com)
    3 points by bkotrys 24 days ago | discuss
  10. Baba Is Solved by Fable 5 and GPT-5.6 Sol, but at what cost? (quesma.com)
    2 points by stared 21 days ago | 1 comments
  11. Quantization hurts knowledge nonlinearly – Qwen3.6 27B case study (quesma.com)
    2 points by stared 18 days ago | discuss
  12. Kimi K3 Is Open, Opus 5 Is Good, DeepSeek V4 Flash Is Cheap: LLMs on Baba Is You (quesma.com)
    1 points by stared 19 days ago | 1 comments
  13. Alibaba, Datadog, and Quesma Join Forces on Go Compile-Time Instrumentation (opentelemetry.io)
    37 points by darccio over 1 year ago | 4 comments
  14. Show HN: Ggplot2 chart playground – in the browser with WebAssembly (github.com)
    4 points by stared 11 months ago | discuss
  15. Qwen 3.6 27B is the sweet spot for local development (quesma.com)
    1192 points by stared about 2 months ago | 759 comments
  16. We hid backdoors in ~40MB binaries and asked AI + Ghidra to find them (quesma.com)
    245 points by jakozaur 6 months ago | 98 comments
  17. Tau² benchmark: How a prompt rewrite boosted GPT-5-mini by 22% (quesma.com)
    197 points by blndrt 11 months ago | 65 comments
  18. I burned all my tokens researching how to save tokens (quesma.com)
    181 points by bkotrys about 1 month ago | 213 comments
  19. The security paradox of local LLMs (quesma.com)
    160 points by jakozaur 10 months ago | 87 comments
  20. CompileBench: Can AI Compile 22-year-old Code? (quesma.com)
    148 points by jakozaur 11 months ago | 65 comments
  21. Benchmarking OpenTelemetry: Can AI trace your failed login? (quesma.com)
    144 points by stared 7 months ago | 79 comments
  22. Show HN: Reviving a 20-year-old puzzle game Chromatron with Ghidra and AI (quesma.com)
    28 points by stared 6 months ago | 9 comments
  23. Tau² Benchmark in Action: Early Results and Key Takeaways (quesma.com)
    16 points by luciesim 12 months ago | discuss
  24. The true cost of saying "Hi" to an AI agent (quesma.com)
    9 points by stared about 1 month ago | 4 comments
  25. Baba Is Solved by Fable 5 and GPT-5.6 Sol, but at what cost? (quesma.com)
    7 points by stared about 1 month ago | 3 comments
  26. Outside of the bubble, AI is Black Mirror (quesma.com)
    7 points by stared 9 months ago | discuss
  27. We hid backdoors in binaries – Opus 4.6 found 49% of them (quesma.com)
    6 points by stared 6 months ago | 2 comments
  28. Prompts are (not) the new source code (quesma.com)
    6 points by stared 7 months ago | 1 comments
  29. Migrating CompileBench to Harbor: standardizing AI agent evals (quesma.com)
    6 points by stared 8 months ago | discuss
  30. A postmortem on our $2.5M database gateway: lessons from pilot purgatory (quesma.com)
    6 points by jakozaur 10 months ago | discuss
  31. Don't Let Apache Iceberg Sink Your Analytics: Practical Limitations in 2025 (quesma.com)
    6 points by jakozaur about 1 year ago | discuss
  32. ClickHouse Cloud Pricing Change in January 2025: A Price Hike with Many Tweaks (quesma.com)
    6 points by jakozaur over 1 year ago | discuss
  33. We hid backdoors in binaries – Opus 4.6 found 49% of them (quesma.com)
    5 points by stared 6 months ago | 2 comments
  34. Nano Banana Pro: raw intelligence with tool use (quesma.com)
    5 points by stared 9 months ago | 2 comments
  35. AI for coding is still playing Go, not StarCraft (quesma.com)
    5 points by stared 10 months ago | 2 comments
  36. OTelBench: Can AI instrument OpenTelemetry? (quesma.com)
    5 points by jakozaur 7 months ago | 1 comments
  37. Building Grafana dashboards with AI, CLI and a bit of pragmatism (quesma.com)
    5 points by stared about 1 year ago | 1 comments
  38. Show HN: 60-Second Linux Analysis, Supercharged with Nix and LLMs (quesma.com)
    4 points by piotrgrabowski 12 months ago | 1 comments
  39. Baba Is Solved by Fable 5 and GPT-5.6 Sol, but at what cost? (quesma.com)
    4 points by agluszak about 1 month ago | discuss
  40. Benchmarking OpenTelemetry: Can AI trace your failed login? (quesma.com)
    4 points by stared 7 months ago | discuss
  41. Nano Banana Pro: raw intelligence with tool use (quesma.com)
    4 points by jakozaur 9 months ago | discuss
  42. Sandboxing AI-Generated Code: Why We Moved from WebR to AWS Lambda (quesma.com)
    4 points by stared about 1 year ago | discuss