Hacker News

New stories

Live mirror
30 storiesupdated just nowView source snapshot
  1. Nobody Has a Good Answer for Agentic Identity Yet (fusionauth.io)
    —discuss
  2. Paul Graham on LLMs 'Thinking' (twitter.com/paulg)
    —discuss
  3. Pragtical v3.13.0 is out with native audio API and built-in audio player (pragtical.dev)
    —discuss
  4. Fluid Simulation on Flip Dots (mitxela.com)
    —discuss
  5. ServingStudio: Simulating, Analyzing, and Optimizing LLM Serving Systems (syfi-servingstudio.github.io)
    —discuss
  6. X-planes: Are they needed in the new era of drones? (bbc.com)
    —discuss
  7. Tell HN: Apple urgently needs a way to disable Apple Intelligence
    4comments
  8. Seven books I keep close because I love them (plover.com)
    —discuss
  9. OpenAI attacked Australia's health system and doubled down. Time to act (theguardian.com)
    —discuss
  10. The collie and the pug – HackMIT keynote 2026 [video] (youtube.com)
    —discuss
  11. Sunday is your last sure chance to visit the Academy of Natural Sciences museum (inquirer.com)
    1comments
  12. (KV) Cache Rules Everything Around Me (completeskeptic.com)
    —discuss
  13. OpenCode-search: fast full-text search of all your sessions (github.com/arvindell)
    2comments
  14. Peter Thiel: The AI Crisis, Europe's Decline and the Battle for America [video] (youtube.com)
    —discuss
  15. Ask HN: How do you feel about the new $500 OpenAI subscription?
    5comments
  16. Positron Valued at $5B in New Funding as Demand for AI Chips Surges (wsj.com)
    —discuss
  17. Procrastination (wa.gov.au)
    —discuss
  18. The Test (tante.cc)
    1comments
  19. Show HN: Vons – Jev-inspired local decisions for AI agents, in the browser (github.com/inlevel9-com)
    —discuss
  20. Show HN: TopoTrace – Modernized, self-hosted IT asset and fleet risk tracker (topotrace.org)
    —discuss
  21. Brazilian President Lula clip dataset (huggingface.co)
    —discuss
  22. AI is deciding whether or not people receive medical care (vox.com)
    2comments
  23. Rails and AI (rubyonrails.org)
    1comments
  24. Remembering Johannes Doerfert (llvm.org)
    —discuss
  25. SWE-Serve: Benchmarking Agentic Engineering for Production Inference Serving (nvidia.com)
    —discuss
  26. Propylea – Sub-Microsecond L7 Reverse Proxy and Active Defense in Rust (github.com/xuoxod)
    —discuss
  27. Stats: 72% of respondents said they felt curious, happy or excited about AI (marginalrevolution.com)
    —discuss
  28. Agentic ERP (shakegraph.com)
    —discuss
  29. Anthropic to Pay Akamai Technologies $11.6B over Seven Years for Cloud Services (wsj.com)
    —discuss
  30. Accomplishing More with LFM2.5-VL-DSpark (2tinteractive.com)
    1comments

Ask HN: Do you cuss at your agent?

2 pointsby 2h ago
6 comments
Do you vent your frustrations at your agent when it keeps making stupid mistakes and asinine assumptions or asks obvious questions?

I did it for the first time and I feel ashamed.

45m agoHN ↗

Don’t blame the agent for not giving it the right requirements and skills to accomplish a task.

31m agoHN ↗

Sometimes upstream providers swap in lobotomized aggressive quants in order to shed load or cut costs. In that case the user is not to blame. And the agent is not so much to blame, either. Same as how you wouldn't blame a child for crashing a car.

It's the fucking provider who took your dollars and handed you back a shit sandwich in return.

36m agoHN ↗

I do very sparingly, same as with humans.

I also give them praise, and sometimes give them pep talks. Like, hey, I know you can do this. Stop asking me for feedback, make good decisions, and let me know when you're done.

29m agoHN ↗

Fuck yes, I do. Not the most effective way to get things done, but a bit cathartic. And no, the stochastic parrot does not have emotions. And yes, it sometimes does worse after being cursed at, but you’re generally better off forking/rolling back the convo to a point before it screwed up anyway. And other times strong language manages to provide the emphasis you need to get it to actually pay attention.

Anyway, why are you ashamed of it?

4m agoHN ↗

I felt ashamed because it fooled me into believing it had feelings like a living thing.

20m agoHN ↗

Yes, but hardly ever at Astra, because it usually gets the job done. Definitely at worse models when you give them very clear instructions and goals to follow and they respond telling you that the job has been completed perfectly, verified byte-identical, all tests pass, etc etc and you look at it and it’s a pile of garbage.