Hacker News

New stories

Live mirror
30 storiesupdated just nowView source snapshot
  1. Human TPS: How fast can your fingers generate tokens? (homoagens.github.io)
    —discuss
  2. That First and Last Question (brianschrader.com)
    —discuss
  3. Show HN: Cordum Edge – A local firewall to sandbox AI coding agents (github.com/cordum-io)
    —discuss
  4. Reduced-Round SHA-256 Compression Preimages (github.com/kamb-code)
    —discuss
  5. Ex-ARRR: Sailing the 0-click Seas (ironpeak.be)
    —discuss
  6. Show HN: Low Poly Earth – The whole planet in 3D, built from OpenStreetMap data (lowpolyearth.pages.dev)
    —discuss
  7. Detect when elements overlap with CSS (ishadeed.com)
    —discuss
  8. What I believe about the future of software development (thorstenball.com)
    —discuss
  9. Dual-Syncopation Meet-in-the-Middle Attacks: New Results on SHA-2 and MD5 (iacr.org)
    —discuss
  10. Ask HN: How is code review holding up at your company?
    —discuss
  11. Phyllotaxis: An audio-reactive LED display (jagi.studio)
    —discuss
  12. privacyguides.org (github.com/privacyguides)
    —discuss
  13. The large robotic arm on the International Space Station has stopped working (arstechnica.com)
    —discuss
  14. Opus 5.5 showcasing: Liquid Glass-like elements for the web (tomacco.github.io)
    1comments
  15. Infinitrance [video] (youtube.com)
    —discuss
  16. How to reduce token usage in Claude Code, Codex, and Cursor (avanderlee.com)
    —discuss
  17. Recursive Self-Improvement via On-Policy Distillation for Reasoning (arxiv.org)
    —discuss
  18. The problem is not the AI code, but nobody knows anything anymore (ssp.sh)
    8comments
  19. 13 Months Sober (2025) (bobbytables.io)
    —discuss
  20. Active, in-the-wild exploitation of CVE-2026-88771 with IoCs (twitter.com/lupovisdefence)
    —discuss
  21. Congress is considering giving doctors automatic annual pay raises in Medicare (statnews.com)
    —discuss
  22. Show HN: Assay – a QA CLI that finds bugs with no LLM and no tests written (github.com/awss1i)
    —discuss
  23. Nero (storia-e-libri.fandom.com)
    —discuss
  24. AI-guided optimization for thermostable mRNA vaccines (nature.com)
    —discuss
  25. Should I Stay or Should I Go? (newyorker.com)
    —discuss
  26. Daily Logic Puzzles (logicpuzzles.io)
    1comments
  27. APOD's main NASA site is moving (apod.com)
    1comments
  28. Open-source Python simulation benchmarking rainbow gravity against NGC 3198 (domushorizon.vercel.app)
    —discuss
  29. Mega Bomberman: Special 8 Player Demo (segaretro.org)
    —discuss
  30. FY2025 NASA Planetary Research and Analysis Funding Cut by More Than 50% (planetary-research.org)
    —discuss

Show HN: Telos – build, run, and evolve software from declarative goals

1 pointsby 38m agousetelos.ai
0 comments
Hi HN,

I've been a heavy user of coding agents for over a year now, and while excited by the productivity gains - I've increasingly been frustrated at the process around it.

- Prompts are imperative and ephemeral, and code is increasingly a black-box, so I lose track of intent over long horizons.

- Pull requests, CI/CD, and even GitHub have become process bottlenecks and are increasingly losing meaning in a world of code abundance.

- I'm tired of babysitting coding agents, cleaning up slop, and reviewing AI output!

I've been building Telos to solve some of these problems - it's a new, declarative abstraction layer for building software with AI. We treat the goal specification as the source of truth that AI coding agents continuously reconcile against in a cloud environment.

We've been dogfooding this quietly for a few months, and it's solved many of the problems above for us - we're excited to share this with the world!

Our agent runtime's source is available [0], and instructions to try it out alongside a real-world example are at the end of the linked post.

Cheers

[0] https://github.com/telos-org/telos

A quiet thread, for now.Start the conversation on HN ↗