test on Hacker News

115 titles from 104 authors in the last 30 days, with 107 distinct links and 20 Show HN.

Counts titles, it does not confirm facts. Open the source before concluding anything.

Projects on this term

The score comes from our model.

• Show HN: Agentfork – Replay an LLM agent from any step and test fixes · score 7.8

  Agentfork is a Python tool for recording, replaying, and forking LLM agent runs at any step. It lets you sweep multiple prompt/model/tool variants with repeats to get pass rates, and save runs as CI tests. That turns flaky debugging anecdotes into measurable experiments with cost estimates, all locally.

• Show HN: ImapKit, a in memory IMAP server to test mail client apps · score 7.3

  ImapKit is a scriptable, in-memory IMAP4rev1 server for testing IMAP client applications, with optional IMAP4rev2 and over 50 toggleable extensions. It is strict by design, rejecting non-compliant client behavior, and supports fault injection via script rules, making it a valuable tool for validating client robustness against real-world server strictness.

• Show HN: Let formal specs test AI implementations · score 7.0

  SpecGuardian converts FizzBee formal specifications into generated Go conformance tests that verify an implementation reaches only allowed states, including under injected I/O failures. It bridges formal verification and executable testing, making it a novel way to check that AI-generated code actually matches its spec.

• Show HN: QAmcp – Automated test runner for MCP servers in your terminal · score 6.8

  QAmcp is a CLI tool that automatically tests Model Context Protocol (MCP) servers by connecting to them like an AI client and running a suite of checks for connectivity, tool descriptions, safety labels, hidden prompt injections, error handling, latency, and secret leakage. It produces a deterministic, arithmetic-based score with clear pass/fail results and integrates with CI pipelines, filling a growing need for quality assurance in the emerging MCP ecosystem.

Recent titles

1. Test Article
   2026-11-01 · software-testing-tutorials-automation.com · HN discussion
2. Show HN: Let formal specs test AI implementations
   2026-11-01 · github.com · HN discussion
3. Test Article
   2026-10-31 · news.ycombinator.com · HN discussion
4. Trump Phone Durability Test – Its worse than we thought (JerryRigEverything) [video]
   2026-10-30 · youtube.com · HN discussion
5. Grail's cancer test produces fewer false positives than I expected
   2026-10-30 · empirical.health · HN discussion
6. The test was green. It had never once done what it claimed
   2026-10-30 · github.com · HN discussion
7. A Claude Code agent's test escaped into my Mac. I only noticed because it talked
   2026-10-30 · marutpandya.com · HN discussion
8. Show, don't prompt: how QA Wolf turns a recording into a real test
   2026-10-29 · qawolf.com · HN discussion
9. Neurodivergents Checker Test
   2026-10-29 · neuroplusgbrain.net · HN discussion
10. GPU or PSU coil whine: a test log and 47 owner reports across 44 models
    2026-10-29 · techfuelhq.com · HN discussion
11. AI shopping assistants confuse fashion subcultures: a small test
    2026-10-28 · github.com · HN discussion
12. Most California students struggle in reading and math, new test scores show
    2026-10-28 · nypost.com · HN discussion
13. The piano test for program verification (2011)
    2026-10-28 · blog.regehr.org · HN discussion
14. Smartphone data order faces first constitutional test in Japan
    2026-10-27 · asahi.com · HN discussion
15. Ukrainian launch test military-purpose communications satellite into orbit
    2026-10-27 · pravda.com.ua · HN discussion
16. Ukrainian comms afirms launch test military-purpose communications satellite
    2026-10-27 · HN discussion
17. Show HN: Break the Wall – take a wall of text apart into parts you can test
    2026-10-27 · github.com · HN discussion
18. Knicks Championship-Ring Phishing Test Was a Security Own Goal
    2026-10-27 · brothke.medium.com · HN discussion
19. Sweden: Europe's most useful electric vehicle test case
    2026-10-27 · omev.se · HN discussion
20. GI Moment in Test
    2026-10-27 · testflight.apple.com · HN discussion
21. Gemini 4 Carbon early test results are in ahead of release
    2026-10-26 · testingcatalog.com · HN discussion
22. How we test LLM serving changes for coding agents, two hours of GPUs per change
    2026-10-26 · upbound.io · HN discussion
23. Show HN: A client-side adaptive cognitive test measuring micro-hesitations
    2026-10-24 · kat-assessment.com · HN discussion
24. Apple's iPhone Duo fails JerryRigEverything's durability test
    2026-10-24 · dexerto.com · HN discussion
25. Show HN: AI agent swarms test if new CVEs are exploitable in your env
    2026-10-24 · app.enclave.ai · HN discussion
26. X API client and a social-network simulator to test it against
    2026-10-24 · github.com · HN discussion
27. Pat smoke test 2, please ignore
    2026-10-24 · HN discussion
28. Pat smoke test, please ignore
    2026-10-24 · HN discussion
29. AgentProbe – test AI agents by making the systems around them fail
    2026-10-23 · sampact.com · HN discussion
30. Pentagon grants DHS permission to test heat ray weapon for use at border
    2026-10-23 · cnn.com · HN discussion

All trends