Hacker News

New stories

Live mirror
30 storiesupdated just nowView source snapshot
  1. KDE and AI, and You, and Me(pointieststick.com)
    discuss
  2. Security auditing in the age of (good enough) AI(trailofbits.com)
    discuss
  3. Buzz: Share spare compute and run open models together over P2P networks(iroh.computer)
    discuss
  4. Prepping for an engineering interview? Created this skill you can use(github.com/bravilogy)
    discuss
  5. Scientists Made a Body Transparent. It Changed How We See Obesity(youtube.com)
    discuss
  6. A Strange Four Days(auldkoi.substack.com)
    discuss
  7. How to Build an AI Visibility Tracker from Scratch(crawlspider.com)
    discuss
  8. Uiarc(uiarc.dev)
    discuss
  9. Jev is 13.6x faster, 2.7x cheaper than GPT Luna 6(tessl.io)
    2comments
  10. DoorDash Spent $1.4M Trying to Stop Mamdani from Becoming Mayor. Now We Know Why(theintercept.com)
    discuss
  11. Show HN: Varkos – a local AI pet that can talk, interact, and play small games(varkos.party)
    1comments
  12. Vibecade – A home for vibe-coded games(vibecade.co)
    discuss
  13. UniCoreFW v1.2.0 has been released(github.com/unicorefw-org)
    discuss
  14. Jobs of the Future May Resemble Those from the Past(robertvesco.com)
    1comments
  15. RF applications in particle accelerators (2024) [pdf](cern.ch)
    discuss
  16. Show HN: Upgrade to Neuro+ GBrain(gemini.google.com)
    1comments
  17. Euler's Eyes(valeman.medium.com)
    discuss
  18. Engagement Speak is the hen-house with a growth chart attached(notsocommonthoughts.com)
    1comments
  19. Virus-Like 'Jumping Genes' Became Our Partners in Evolution(quantamagazine.org)
    discuss
  20. Biology Might Not Be Quantum, but Its Math Is Quantumlike(quantamagazine.org)
    discuss
  21. Code Critique: Intent, Drift, and Spotlight for AI-Generated Diffs at Scale(arxiv.org)
    discuss
  22. Owners mourn spoiled food after firmware update bricks Samsung smart fridges(arstechnica.com)
    discuss
  23. Opaquer .NET Obfuscator(opaquer.net)
    discuss
  24. Show HN: AgentRun: DSL to turn agents into Workflows(github.com/parcha-ai)
    discuss
  25. VSArena – The official open browser benchmark for embodied AI(vsarena.vercel.app)
    discuss
  26. Earth's magnetic field alters lifespans of fruit flies in surprising ways(404media.co)
    discuss
  27. Designing a domain-specific research harness(sparsethought.com)
    discuss
  28. "Good" AI(wyounas.com)
    1comments
  29. GoAccess – real-time web log analyzer(github.com/allinurl)
    discuss
  30. Nuvio – Open-Source Alternative to Netflix for Your Own Media Sources(digitalescapetools.com)
    discuss

How we made claude.ai 3x faster in two weeks

53 pointsby 48m agoclaude.dev
18 comments
32m agoHN ↗

This writeup legit coincidentally matches the asking-agents-to-make-code-faster-but-with-constraints-to-stop-agents-from-breaking-things writeup I posted on Monday: https://news.ycombinator.com/item?id=49803085

Front-end UI optimization is slightly trickier than optimizing strict algorithms, but I found that prompts to the agents to build tooling to track visual regressions are more than sufficient. The main issue (at least with GPT models) is that you have to be very explicit about the use of padding/margins/negative space.

That said, for my front end projects from scratch, I'm staying away from front-end JS frameworks and seeing how far and fast I can get with just HTML/CSS/vanilla JS shenanigans now that agents can wield them effectively.

25m agoHN ↗

Opus 5.5. is really something. We use it to make animations and it is amazing.

24m agoHN ↗

This was a fantastic read. Lots of useful info in there for your own projects.

17m agoHN ↗

Great writeup really appreciate the detail on what actually worked vs. what didn't.

16m agoHN ↗

tl;dr if you make absolute dogshit software that takes 4.38 seconds to stabilize its first paint you can make really nice headline claims by "optimizing" it later

9m agoHN ↗

Unironically true, can someone question, what is Claude desktop app doing that needs 500k+ lines of code?

Agents complicate something that should be much smaller and simpler and then agents speed it up adding more complexity. I suppose functionally you may say this is fine but aesthetically it is hideous!

2m agoHN ↗

There is nothing even functionally fine about this. The me who has programmed for a 4mhz computer with 128kb of RAM is crying inside. It's a fucking trivial interface for writing and displaying text and sending HTTP requests. You could have that dispayed ~instantly on an 80s home PC. Now we have home computers that can do somewhere between billions and trillions of instructions per second and yet a task that should take <10ms takes 4500ms. Our industry has become an absolute embarrassment.

2m agoHN ↗

Most line-of-business software has a lot of optimization opportunities. Making software optimized takes up time that can be spent building features. The fact that you can just make things go fast without having to take time away from feature building is actually pretty awesome.

13m agoHN ↗

How about you make Opus 5.5 actually work?

I had it try to prepare a code review for me. Not only did it refuse, it refused to even tell me what the prompt (written by another Claude!) was. Why?

When I had another model read the session (all of the "stupider" models handled it just fine) it explained that it had the word "reasoning" in it

That's the entirety of Anthropic's billions of dollars of research: any prompt with the word "reasoning" is trying to hack Claude to figure out how it reasons!

A model like that should never have gotten out of QA, let alone been released.

12m agoHN ↗

seems a bit weird to complain about the model issues in a post about the harness/sites?

1m agoHN ↗

the skill issue is "having to use a cloud model to do work of any value"

might as well offer your life to a king to work in their fields.

10m agoHN ↗

Let's try this again if you want an instant 10x speed up:

Claude rewrite Claude Code from TypeScript into Rust. Make absolutely no mistakes.

8m agoHN ↗

AI written slop. They need to upgrade to Opus 5.5 or switch to OpenAI for writing.

6m agoHN ↗

Step 1 - make a website that takes 3 seconds to load a blank page.

Step 2 - bring it down to 1 second and pat yourself on the back.

3m agoHN ↗

I used Opus 5.5 today for the first time hoping the writing would be more bearable and it SUCKS.

Why can't they fix that

1m agoHN ↗

Opus 5.5 writing is much more concise than 5.0