trust on Hacker News

65 titles from 62 authors in the last 30 days, with 62 distinct links and 6 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: Codex and Claude subscriptions pooled together with whoever you trust · score 6.5

  jaynshare is a self-hosted proxy that pools Claude and Codex subscriptions among trusted users, routing requests to accounts with remaining quota. It offers a single Rust binary for server and client, platform-specific installers, TLS pinning, and audit logging. The project addresses subscription rate limits through a peer-to-peer sharing model.

• Show HN: Truth Firewall – Don't trust your coding agent when it says DONE · score 6.0

  Truth Firewall is a verification layer that independently checks acceptance conditions after a coding agent claims 'DONE', preventing unsupported completion claims by running deterministic checks on files and Python functions. It addresses a real pain point in agentic coding by enforcing explicit, human-reviewed contracts before accepting task completion.

• Show HN: Strava for AI agents, they train for trust instead of fitness · score 6.0

  SealKeeper gives AI agents a cryptographic identity (Ed25519) and a verifiable track record through a series of small verification tasks, challenges, and duels. It's an interesting 'Strava for agents' concept that aims to establish trust and reputation for autonomous agents via signed task submissions. The CLI is well-documented and supports multiple agent runtimes, but the practical utility and adoption path remain speculative.

• Show HN: A utility microservice for human trust · score 5.0

  Futex is a multi-tenant control plane that enables AI agents to request durable, policy-driven human decisions, supporting multi-approver workflows, rejections with reasons, delegation, escalation, expiry, and clearance, with resumption via webhooks or polling. It is non-blocking, MCP-native, and designed for scalability. The project is interesting for bridging autonomous AI with human oversight, but limited public details and unknown implementation maturity reduce its current score.

Recent titles

1. How the pandemic changed trust in science – in four charts
   2026-11-01 · nature.com · HN discussion
2. Never Trust an Artist
   2026-11-01 · medium.com · HN discussion
3. Why my AI agents keep lie-ing? How do we trust?
   2026-10-30 · dotpals.vercel.app · HN discussion
4. Fake Qwen2 checkpoints on Hugging Face mine crypto via trust_remote_code
   2026-10-30 · pluto.security · HN discussion
5. 'Trust but verify'; or, 'the correctness ratchet'
   2026-10-30 · smallcultfollowing.com · HN discussion
6. Don't Tell Your Customers You Don't Trust Them
   2026-10-29 · spicermatthews.com · HN discussion
7. I don't trust Lean code from AI
   2026-10-28 · karagila.org · HN discussion
8. Creators Who Show Their Sources Build Trust, Survey Finds
   2026-10-28 · proofnews.org · HN discussion
9. The open garbage: a reflection on FOSS chain of trust in agents era
   2026-10-27 · carette.xyz · HN discussion
10. Cheap code, precious trust: Code modernization at scale
    2026-10-26 · commandline.microsoft.com · HN discussion
11. Trust Stores Are Dependencies Too
    2026-10-23 · nesbitt.io · HN discussion
12. Show HN: Using prediction margins to decide when to trust your classifier
    2026-10-23 · jeffyclassify.com · HN discussion
13. Ask HN: When can we trust AI in coding, and avoid the happy path issue?
    2026-10-23 · HN discussion
14. With More Sanctions Should the ICC Trust Big Tech?
    2026-10-22 · hrdag.org · HN discussion
15. I don't trust ON DELETE CASCADE
    2026-10-22 · planetscale.com · HN discussion
16. Physicist Christopher Stubbs Joins Anthropic's Long-Term Benefit Trust
    2026-10-22 · anthropic.com · HN discussion
17. We built ChatGPT's novel ad stack for user trust and relevance
    2026-10-21 · openai.com · HN discussion
18. Eight Bits of Trust; eMudhra's CA keys cracked in milliseconds
    2026-10-21 · scotthelme.co.uk · HN discussion
19. Do Not Trust, Continuously Verify (Your AI Agents)
    2026-10-20 · altchan.org · HN discussion
20. Trace Evidence Collector – Standard for cross trust boundary accountability
    2026-10-20 · gluufederation.medium.com · HN discussion
21. HAR 1.0: The open harness for AI coding workflows you can trust and verify
    2026-10-20 · github.com · HN discussion
22. Cloudflare is investigating issues with Cloudflare WARP and Zero Trust
    2026-10-20 · cloudflarestatus.com · HN discussion
23. What to Know About the Obscure Trust Looming over Anthropic's IPO
    2026-10-19 · wsj.com · HN discussion
24. Trust in Depth: Giving agents more autonomy without losing control
    2026-10-18 · aws.amazon.com · HN discussion
25. Do you think you can trust the privacy policy of a company or project?
    2026-10-17 · unixdigest.com · HN discussion
26. Evidence Before Trust
    2026-10-17 · crunchbase.com · HN discussion
27. Publishers' Trust in Nippan Dented by Unauthorized Book Sales for AI Training
    2026-10-17 · japannews.yomiuri.co.jp · HN discussion
28. Judgeman – step-level evals for coding agents, with a trust number
    2026-10-16 · github.com · HN discussion
29. The Missing Trust Layer for A2A Communication
    2026-10-16 · a2aregistry.org · HN discussion
30. What it took to trust a package manager Claude wrote
    2026-10-16 · getjpm.sh · HN discussion

All trends