Hacker News

Top stories

Live mirror
30 storiesupdated just nowView source snapshot
  1. There's no point at which turning your brain off will work(danluu.com ↗)
    21comments
  2. Cloudflare Quick Tunnels(cloudflare.com ↗)
    117comments
  3. Photon-Emission-Guided Laser Fault Injection Enables RP2350 Secure Debug(ledger.com ↗)
    2comments
  4. An Empirical Study of Harness Design for Coding Agents(arxiv.org ↗)
    37comments
  5. North Korean nuclear test sets off years of earthquakes(science.org ↗)
    70comments
  6. Show HN: Cactus Needle 3: 8-29MB automation models can match DeepSeek V4 Flash(cactuscompute.com ↗)
    16comments
  7. C++26: Trivial infinite loops are no longer undefined behaviour(sandordargo.com ↗)
    97comments
  8. OpenJev(openjev.com ↗)
    203comments
  9. Mathematicians Build Long-Awaited Graph Sandwich(quantamagazine.org ↗)
    5comments
  10. I vibed a proof of Conway's conjecture(overreacted.io ↗)
    103comments
  11. A heap overflow and SSO misconfiguration to compromise OpenAI internal repos(hacktron.ai ↗)
    179comments
  12. GrassLobster: AI Agentic Generation of Parametric Geometry Workflows(miro.vision ↗)
    3comments
  13. I don't like passkeys(hawksley.dev ↗)
    525comments
  14. Jemalloc 5.4.0(github.com/jemalloc ↗)
    75comments
  15. NATS publishes preliminary report on technical incident of 8 September(nats.aero ↗)
    23comments
  16. The Shadows Lurking in the Equations – Underwater Islands(gods.art ↗)
    9comments
  17. Cekura (YC F24) Is Hiring(ycombinator.com ↗)
    discuss
  18. BeanShell3 in Development(beanshell.github.io ↗)
    11comments
  19. The scourge of x86 emulation(fex-emu.com ↗)
    67comments
  20. Bonsai 2 27B: Near-Lossless Compression in a 9x Smaller Footprint(prismml.com ↗)
    176comments
  21. Warren Buffett Steps Down as Berkshire Chairman, Names Son to Replace Him(nytimes.com ↗)
    152comments
  22. Build Faster Feedback Loops Using Qualitative User Research(nseldeib.com ↗)
    1comments
  23. US Treasuries Have Become Unappetizing for Foreign Central Banks and Governments(wolfstreet.com ↗)
    48comments
  24. Show HN: Scry, programmable internet search w/ congestion pricing(scry.io ↗)
    2comments
  25. Qwen 3.8 Omni Flash(qwen.ai ↗)
    117comments
  26. Show HN: Microsoft Office running with Wine on Linux with no virtualization(github.com/tombert ↗)
    50comments
  27. Second Circuit Allows Government to Search Electronic Devices at the Border(knightcolumbia.org ↗)
    37comments
  28. How to Write with an LLM(sockpuppet.org ↗)
    193comments
  29. Pre-Greek: The lost language hidden within Ancient Greek(linguisticdiscovery.com ↗)
    61comments
  30. Microsoft exec called AI scraping 'the largest theft of labor in human history'(techcrunch.com ↗)
    632comments

Open-sourced jev architecture last year with model,paper and dataset

42 pointsby 1d ago
10 comments
Everyone now talks about the architecture that's not auto regressive and does lightning fast probability prediction with a json schema. I worked on this literally one year back in March 2025, published an arxiv paper, pushed the model to huggingface along with the pypi package and training dataset. And then one year later, a frontier lab came, proposing the same idea like literal breakthrough without technical papers, open weights and no open dataset. For anyones information the main guiding model is RL not embedding model or LLM

Paper: https://arxiv.org/abs/2503.23303

Model: https://huggingface.co/DeepMostInnovations/sales-conversion-model-reinf-learning

Dataset: https://huggingface.co/datasets/DeepMostInnovations/saas-sales-conversations

Also the second work published in September 2025 was exactly the same one jev proposed now

Paper: https://arxiv.org/abs/2510.01237

My model uses PPO over sequence embeddings to output turn-by-turn conversion trajectories (probabilities from 0.0 to 1.0).

Jev uses parallel sampling (trained via RLCD) to output confidence distributions and schema choices.

It's incredibly frustrating that the thing that you made with months of hard work, sweat and sleepless night is architecturally similar with the vertical use case and don't get the support you deserve because frontier lab build something horizontal. The open-source story in general

1d agoHN ↗

Feeling that open-source community do not get the recognition they deserve

1d agoHN ↗

The world's heavily about marketing, resources, connections, and signaling, unfortunately. You probably needed to market it in a bigger forum with shinier claims to attract attention (I don't think a paper on Arxiv is enough).

1d agoHN ↗

Put it on your CV

"I can come up with revolutionary ideas one year earlier than entire billion dollar organizations"

"I inventet Jev a year earlier"

1d agoHN ↗

Pity because without the frustration it would’ve been a good post. Catch is you’ve got intuition, but looking around instead of forward. Do it again, open-source it, either you’d quietly bring down few companies, or, when you’re close, you’d get offers from them. The who’s done what is a dying paradigm.

1d agoHN ↗

We are human , frustration is something we feel when same kinda architecture is closed sourced and we celebrate it

17h agoHN ↗

We are human , frustration is something we feel

Absolutely. Besides, when we see injustice we shouldn't be silent about it because that would encourage more of it.

when same kinda architecture is closed sourced and we celebrate it

I saw the post about Jev and the lack of basic information felt wrong and bizarre, I now see the most likely reason for it.

The best thing to do now, is to develop your open source project further and beat the Jev-ers, that story is very motivational and I'm interested.

1d agoHN ↗

Can you (or someone) provide some context for this post? What's Jev? What's the innovation here that was duplicated by the frontier lab?

48m agoHN ↗

From what I can tell these are classifiers trained for a single task. What excites people about Jev is that it can do zero-shot structured responses for arbitrary prompts. Now, this isn't new either; models like GLiNER have been around for a while. But Jev appears significantly more flexible and polished while still being cheap and fast.