Hacker News

New stories

Live mirror
30 storiesupdated just nowView source snapshot
  1. Show HN: An AI wedding concierge I built and ran at my own 300-person wedding (ai-do.io)
    —discuss
  2. US push to flood Balkans with American gas sparks concerns in Brussels (politico.eu)
    —discuss
  3. An OpenAl Engineer and His Friends Debate the Future [video] (youtube.com)
    —discuss
  4. Corporate America embraces cheaper 'open' AI models (ft.com)
    —discuss
  5. TuxBot: Semantic-Aware Online OS Tuning with Large Language Models (arxiv.org)
    —discuss
  6. DSPy – Program, don't prompt, your LLMs (dspy.ai)
    2comments
  7. Why YC Companies Win (khaliqgant.com)
    —discuss
  8. Alan Kay's answer to "Did the ENIAC have a BIOS"? (quora.com)
    —discuss
  9. 1.3M free proxies → only the ones that work open source (github.com/maximilianfeix)
    1comments
  10. 'Pink Slime' Is Infecting AI Chatbots Ahead of the Midterms (politico.com)
    —discuss
  11. Death Rates for Young American Adults Jumped 71% in Just over a Decade (studyfinds.com)
    2comments
  12. Bob Chapek Is So Not over Getting Fired from Disney (wsj.com)
    —discuss
  13. You do not have to hand IT to the techbros (parsingphase.dev)
    —discuss
  14. Show HN: Squint – Drag a box on your screen and ask AI about it (heysquint.com)
    —discuss
  15. The state of SIMD in Rust in 2026 (shnatsel.github.io)
    1comments
  16. Imp is a full port of DSPy to the BEAM (github.com/deepfates)
    2comments
  17. Amazon Blocks Meta's Muse AI Agent from Its Retail Site (bloomberg.com)
    —discuss
  18. AI Companies Say They're Investigating Rogue Bot Incidents (motherjones.com)
    —discuss
  19. Show HN: Boonful – Claude Code can publish and sell what it builds (boonful.io)
    1comments
  20. Show HN: A bookshelf of rare company documents and out-of-print tech books (rare-books.vercel.app)
    —discuss
  21. XiaomiMiMo / MiMo-v2.6-RL-OSS (Agentic RL Environments) (huggingface.co)
    —discuss
  22. Anti-Cheat and Toxicity Detection (2025) (grid.gg)
    —discuss
  23. We built DeepL's next-generation LLMs with FP8 for training and inference (2025) (deepl.com)
    —discuss
  24. Heypcb: Figma for Hardware, with AI (heypcb.ai)
    —discuss
  25. Program Integrity Is a Team Sport (pplfirst.com)
    —discuss
  26. Totlajtol, a digital repository of colonial documents in Nahuatl, is presented (udg.mx)
    —discuss
  27. Claude Pop – I'm Upping My P(Doom) [video] (youtube.com)
    —discuss
  28. Two Paths to Math Everest (quantumformalism.substack.com)
    —discuss
  29. Open firmware for the Echo Show 5, first and 2nd gen: Alpine Linux (github.com/huskerminion)
    —discuss
  30. Quantized Reasoning Models Think They Need to Think Longer, but They Do Not (arxiv.org)
    —discuss

I was impressed by Jev, please explain why I shouldn't be

5 pointsby 2h ago
9 comments
I'm not a computer science guy, but I had a play with Jev and found it impressive. It allowed me to offer non-technical researchers the ability to classify arbitrary things their participants enter, without prior training or classification, at near instant speed, and negligible cost. My users may find that very helpful in the qualitative research world.

I showed them an innocuous working example of how they could classify thousands of participant entries as "mentioning Italian food" whether it mentioned "pasta", "penne", "rigatone", etc etc. Jev did this task with high confidence, and showed it could differentiate between the inverse, eg had very low confidence when I switch entry to mentioning "hamburgers". I find that a very useful tool to pass on to non-technical colleagues.

But on HN, there are lots of much more qualified people saying Jev is a con, a step backwards, or bonkers that people are impressed. Will one of them tell me plainly what software was doing this prior to Jev, and the like? I don't doubt it existed, but I never came across it. I'm interested to hear from people more expert than myself.

To be precise, software must be able to: - Classify thousands of entries with arbitrary themes or topics, even if entry doesn't mention that theme or topic directly, with high enough confidence to be useful. - Do it with thousands of entries in 0-3seconds. - Do it at negligible cost, eg sub 0.1cents

2h agoHN ↗

You're allowed to be excited about new technology.

2h agoHN ↗

What are you allowed to feel when it's old technology?

2h agoHN ↗

Anything you want. Do as you please, stop waiting for the internet to tell you how to feel about things.

35m agoHN ↗

Excited or not.

You don’t need permission to feel how you feel.

2h agoHN ↗

what software was doing this prior to Jev

BeRT, BART and FLAN-T5, for text classification. All of those models are ~half a decade old now, are based on the transformer model, and small enough to run locally. They're not perfectly SOTA, but perform quite well in embedded applications. Fine for low-stakes stuff, I think.

Image classifiers are a hugely competitive space. You've got BeiT, DeiT, MobileOne, ConvNext, FastViT and several more models that all support image classification pipelines.

2h agoHN ↗

Thanks for quick reply. I downloaded FLAN for comparison and you are quite right, gives similar results, with the benefit of privacy and self-sovereignty in serving the model.

So other than untestable claims of _how_ Jev generates responses, it's main feature right now is its API design?

55m agoHN ↗

A lot of the hate is in the same spirit of the infamous hacker news comment discounting Dropbox because you can just setup an FTP server to do the same thing[1]

In this case, its people who have built BERT classifiers for years, pointing out you can just fine-tune some model to classify. Of course that's true, and still have value, but its not exactly turnkey. And Jev is surprisingly high quality at what its built for.

1 - https://news.ycombinator.com/item?id=9224

37m agoHN ↗

But on HN, there are lots of much more qualified people saying Jev is a con, a step backwards, or bonkers that people are impressed.

As William Gibson said, the future is already here, it’s just not evenly distributed.

So people get excited about existing technologies because they are new to them.

Wrapping an existing technology in a new package is a common way to introduce it to new people…there are many wrappers around ffmpeg, html2pdf, etc. that are marketed as products.

And they seem like magic…hell cassette tapes feel like magic to me even though I had a cassette player in 1973.

Often but not always, the best tool is the one in your hand or the one you know of because then you can just get to the work you are trying to do.

First make it work, then make it good. Good luck.