Hacker News

Top stories

Live mirror
30 storiesupdated just nowView source snapshot
  1. Training a 4B model to produce 81% faster query plans than Postgres(rohanbansal.com ↗)
    68comments
  2. Nvidia announces native GPU programming in Rust(nvidia.com ↗)
    41comments
  3. Breaking the 1.58-bit Barrier for Ternary LLMs(arxiv.org ↗)
    10comments
  4. Xiaomi Mimo 2.6 live post-training dashboard(xiaomi.com ↗)
    54comments
  5. The engineering behind the US Strategic Petroleum Reserve(johnjwang.com ↗)
    11comments
  6. Backups Aren't Simple(filipovski.net ↗)
    15comments
  7. Small programming tricks(will-keleher.com ↗)
    177comments
  8. OpenSpec – A lightweight and configurable AI spec framework(openspec.dev ↗)
    6comments
  9. Reversing Factorio's RNG(gegell.github.io ↗)
    12comments
  10. Performance Improvements in .NET 11(devblogs.microsoft.com/dotnet ↗)
    25comments
  11. Australia says it could follow Canada in forging deeper ties with EU(independent.co.uk ↗)
    11comments
  12. AWS says it can't restore some data from mideast facilities struck by Iran(wsj.com ↗)
    158comments
  13. Japan's book scene is moving from bookstores to libraries(untranslatedjp.substack.com ↗)
    28comments
  14. How good are frontier models at physics?(arxiv.org ↗)
    28comments
  15. Reverse-engineered Jev-like model(github.com/vinnylarouge ↗)
    8comments
  16. Accurate Models of AMD Matrix Cores(arxiv.org ↗)
    6comments
  17. Show HN: An e-ink frame that hears birds and draws them as 1800s illustrations(github.com/arnegiacomo ↗)
    236comments
  18. Destroy After Reading: photocopiers,cheap paper and DIY gave metal it's look(truegrittexturesupply.com ↗)
    2comments
  19. Mistral X Mozilla: Private, Multilingual AI Browsing(mistral.ai ↗)
    184comments
  20. Why Does the Universe Expand?(cosmicave.org ↗)
    1comments
  21. Anecdotally, programmers dislike "reduce"(evanhahn.com ↗)
    133comments
  22. Dream-RSI: Recursive Self-Improvement through Evolving Worlds(arxiv.org ↗)
    49comments
  23. Anatomy of a Texture(agentlien.github.io ↗)
    12comments
  24. Hackers Got Inside a Flock Camera(wired.com ↗)
    208comments
  25. WalShadow: Sub-second Postgres replication to ClickHouse from physical WAL(clickhouse.com ↗)
    5comments
  26. I replaced my brown-noise browser tab with a menu bar app(oldmanrahul.com ↗)
    5comments
  27. Training Text-to-Image Models 3.6× Faster(linum.ai ↗)
    3comments
  28. The DeepMind Institute(deepmind.com ↗)
    43comments
  29. Vectorized and performance-portable Quicksort (2022)(googleblog.com ↗)
    25comments
  30. Kyber (YC W23) Is Hiring a Forward Deployed Engineer(ycombinator.com ↗)
    discuss

OpenSpec – A lightweight and configurable AI spec framework

24 pointsby 54m agoopenspec.dev
5 comments
38m agoHN ↗

I've been using this, or more pointedly, I built an agent fleet (bespoke harness) where the planner agent uses OpenSpec to generate the plan. Then turns the tasks into a ticket graph.

It works fairly well, and it is definitely less heavy than SpecKit.

20m agoHN ↗

This looks like exactly what I've been thinking I needed. I've tried Superpowers, GSD and oh-my-claude/openagent and mostly they burn more tokens.

Lately I've been using stock OMP and its close to the right balance but not quite enough of the brainstorming and spec maintenance built in. I've tried to layer some simple stuff on myself but with mixed results.

4m agoHN ↗

I think they might be in the process of re-designing the site and/or moving docs because it all used to work not that long ago, but the site design was completely different last time I checked.

8m agoHN ↗

This is my first time seeing openspec, and it seems to share a similar philosophy to what I've been working on this year.

If you like this / SDD, I'd appreciate your feedback:

https://github.com/spekk-ai/spekk-cli

Similar iterative specs philosophy. Ours is a bit different because we focus on declarative specs and installable agent skills. We chose Go for simplicity and minimal requirements (single binary).