decision on Hacker News

123 titles from 103 authors in the last 30 days, with 115 distinct links and 38 Show HN.

Counts titles, it does not confirm facts. Open the source before concluding anything.

Projects on this term

The score comes from our model.

• Show HN: Decision Studio – LM Studio for open-source, Jev-style decision models · score 8.3

  Bud Decision Studio is a desktop application for running open-source decision models locally, similar to LM Studio but for Jev-style 'System One' models. It provides a playground, template management, evaluation, history, API server, and on-device training with LoRA, all accessible through a polished GUI and CLI.

• Show HN: Homi, open decision model for audio, near Flash on MMSU and 50x cheaper · score 7.8

  Homi is an open decision model for audio that answers typed questions (yes/no, multiple-choice, scored levels) about audio clips, using a Qwen3-Omni-based architecture with a decision head instead of text generation. It claims strong performance on VocalGrad and MMSU benchmarks at significantly lower cost than Gemini Flash, with a fully reproducible training and evaluation pipeline.

• Show HN: BeelineBench – How well do decision models solve multi-step problems? · score 7.5

  BeelineBench is a benchmark for evaluating how efficiently decision models solve multi-step planning problems by scoring how directly they navigate to a solution. It uses a best-first search harness across seven domains (e.g., sliding puzzles, Blocksworld, Wikipedia navigation) and compares model performance against classic heuristics, random choice, and an oracle. The project is well-documented, configurable, and integrates with custom model APIs, making it a valuable tool for AI planning research.

• Show HN: Plannotator Inbox – Decision Making Surface for Agents · score 7.3

  Plannotator is a local, browser-based review and annotation surface for AI coding agents (Claude Code, Codex, Gemini CLI, OpenCode, and others), letting users mark up plans, specs, diffs, and HTML artifacts and send feedback directly back to the agent. Its Inbox feature decouples agent sessions from human review so agents can keep working while questions and decisions are queued for the user. It fills a real gap in the human-in-the-loop agent workflow by combining annotation, code review, and multi-agent decision queuing in one local tool.

Recent titles

1. Show HN: Devloops – Adversarial agent loops so humans only make the key decision
   2026-11-01 · github.com · HN discussion
2. Show HN: AnchorGit – Hardware-signed Git decision ledger for AI code
   2026-11-01 · anchorgit.com · HN discussion
3. Show HN: Nouli – A multi-turn decision graph harness for System One models
   2026-10-29 · github.com · HN discussion
4. Show HN: Homi, open decision model for audio, near Flash on MMSU and 50x cheaper
   2026-10-28 · github.com · HN discussion
5. Show HN: Better Backlog: Filter GitHub issues with decision models
   2026-10-28 · github.com · HN discussion
6. I turned a looped transformer into a decision model that scores answer options [pdf]
   2026-10-27 · wyat.io · HN discussion
7. Show HN: Qev – quake and local decision models
   2026-10-27 · twitter.com · HN discussion
8. Valen – Open multimodal decision models for text, images and video
   2026-10-27 · valen-team.github.io · HN discussion
9. Enabling new use cases for decision models beyond high-volume cheap decisions
   2026-10-27 · uprightproject.com · HN discussion
10. A technical architecture decision tree for SAP Clean Core and S/4HANA migrations
    2026-10-27 · medium.com · HN discussion
11. Show HN: Arc-decide – an MIT 0.4B decision model for RAG checks that runs on CPU
    2026-10-26 · docs.docsgpt.cloud · HN discussion
12. Sevenbox, find what an AI agent's wrong decision affected
    2026-10-24 · github.com · HN discussion
13. Glyphh Ada: Decision model that learns from your past decisions, no transformer
    2026-10-24 · glyphh.ai · HN discussion
14. Arm comments on jury decision in Qualcomm trial
    2026-10-24 · eetimes.com · HN discussion
15. How to Use Decision Models for Evals
    2026-10-24 · hamel.dev · HN discussion
16. Show HN: Whyline – Git native decision history for coding agents
    2026-10-24 · github.com · HN discussion
17. Decision Making Is the Bottleneck with AI
    2026-10-23 · backnotprop.com · HN discussion
18. Mammoth-1 and Elephant-1: frontier decision models
    2026-10-22 · labs.baseten.co · HN discussion
19. Show HN: Decido – an open decision model that runs CPU-only on a laptop
    2026-10-22 · github.com · HN discussion
20. Jeffan-31B: A Gemma fine-tune ranked #1 on the Jev Decision Index
    2026-10-22 · huggingface.co · HN discussion
21. Mammoth-1 and Elephant-1 decision models by Base Labs
    2026-10-21 · twitter.com · HN discussion
22. Base Labs releases top-ranked decision models mammoth-1 and and elephant-1
    2026-10-21 · baseten.co · HN discussion
23. Starlink access in Ukraine a decision for Musk, not White House, Rubio says
    2026-10-21 · reuters.com · HN discussion
24. Architecture Decision Record: now in many more languages
    2026-10-21 · HN discussion
25. Qev-0.8B · New SOTA tiny local decision model
    2026-10-21 · app.labqoat.com · HN discussion
26. Artificial Analysis Decision Index v1.0
    2026-10-21 · artificialanalysis.ai · HN discussion
27. How to Use Decision Models for Evals
    2026-10-21 · twitter.com · HN discussion
28. Show HN: AHP Matrix, local, open-source Analytic Hierarchy Process decision tool
    2026-10-20 · github.com · HN discussion
29. Decision model as prompt-injection judge: 40 of 40 on 78 texts
    2026-10-20 · loomcycle.dev · HN discussion
30. Show HN: 80s computing era meets small local decision models
    2026-10-20 · github.com · HN discussion

All trends