Hackernews posts about DEC

1. 271
   

   newI built non-autoregressive decision models with RL a year agolaya.convaiinnovations.com

   ▲ 1363nandakishor_ml13d💬 318savesaved
2. 272
   

   newLibreOffice breaks download records after declaring it has no AI featuresmanualdousuario.net

   ▲ 722rpgbr24d💬 237savesaved
3. 273
   

   newOllaya – Ollama for open-source, Jev-style decision modelsollaya.dev

   ▲ 617Ardakilic7d💬 145savesaved
4. 274
   

   newClef: Open-weight decision models, and new RL fine-tuning platformblog.cloudflare.com

   ▲ 610jasondavies27h💬 214savesaved
5. 275
   

   newJeff – Jev-compatible 0.8B decision models, trained at home, ~30 msgithub.com

   ▲ 574firelex3d💬 225savesaved
6. 276
   

   newKev: Tiny Jev-like family of decision models built on top of Qwen3.5github.com

   ▲ 462tosh11d💬 211savesaved
7. 277
   

   newFable 5 – Median thinking declined in Augusttwitter.com

   ▲ 427espeed11d💬 293savesaved
8. 278
   

   newJury finds Facebook liable for deceiving users in Cambridge Analytica casewww.cbsnews.com

   ▲ 423pseudolus6d💬 107savesaved
9. 279
   

   newShow HN: Reladraw – A diagram language where you decide where to place thingsgithub.com

   ▲ 411jpwalsh2346d💬 119savesaved
10. 280
    

    newParley: Federated, decentralised chat that speaks plain IRCgit.mills.io

    ▲ 327davidcollantes4d💬 190savesaved
11. 281
    

    newJeeves. Reasoning improves Jev-like decision modelsgithub.com

    ▲ 242nicowaltz3d💬 95savesaved
12. 282
    

    new120 days until Google restricts side-loading, declaring war on Android freedomtuta.com

    ▲ 183krunck29d💬 74savesaved
13. 283
    

    newUsing LLMs to trace alchemical knowledge and decode 17th century lettersresobscura.substack.com

    ▲ 174benbreen8d💬 44savesaved
14. 284
    

    newThe most important product decision is what you don't buildliamnugent.me

    ▲ 161ChrisArchitect14d💬 54savesaved
15. 285
    

    newShow HN: JevBench, a reproducible benchmark for typed decision modelsbenchmarkheaven.com

    ▲ 153florianstandhar10d💬 39savesaved
16. 286
    

    newDecoding the NEC V20 Microcodemartypc.blogspot.com

    ▲ 150mariuz28d💬 10savesaved
17. 287
    

    newSpeculative Decoding in vLLM on AMD GPUsvllm.ai

    ▲ 145ankitg1225d💬 53savesaved
18. 288
    

    newResident Evil 4 (GameCube) – complete byte-identical decompilation to C/C++github.com

    ▲ 140metrofun12d💬 99savesaved
19. 289
    

    newTurning GLM-5.3-Flash into a Jev-like decision modelwww.privatemode.ai

    ▲ 138flxflx6d💬 59savesaved
20. 290
    

    newWe've followed their lives for six decades; now the stars of 7 Up are bowing outwww.bbc.co.uk

    ▲ 132mellosouls20d💬 37savesaved
21. 291
    

    newPISA 2025 Students' reading and mathematics performance declined across the OECDwww.oecd.org

    ▲ 131mazokum24d💬 169savesaved
22. 292
    

    newTelstra outage: The night a network decided the year was 2006www.netnod.se

    ▲ 93TMWNN14d💬 34savesaved
23. 293
    

    newShow HN: Air-gapped file encryption as self-decrypting HTML pagecms-sfx-demo.apeleg.com

    ▲ 90emurlin8d💬 32savesaved
24. 294
    

    newDecapitating a MacBook (2025)mm-dev.rocks

    ▲ 67luu26d💬 48savesaved
25. 295
    

    newPeople that worked on the same idea for decadesnityasnotes.com

    ▲ 63sebg29d💬 32savesaved
26. 296
    

    newAdding Floating-Point Decimals for Fun and Profitblog.vero.site

    ▲ 60ibobev3d💬 35savesaved
27. 297
    

    newDeCloudflare0xacab.org

    ▲ 52DeepLogin20d💬 55savesaved
28. 298
    

    newShow HN: jevals – replacing LLM judges with typed Jev decisionsgithub.com

    ▲ 47gbayomi11d💬 6savesaved
29. 299
    

    newShow HN: AI·rete·RAG – a Rete rule engine decides, RAG explains whyai-rete-rag.com

    ▲ 46ZaharaHussain10d💬 11savesaved
30. 300
    

    newWhen anyone can build software, who decides what not to build?architectureintel.com

    ▲ 44younss19d💬 35savesaved

· edit