Feed aggregator
No-backprop SNN scores 98.2% on Split-MNIST task-incremental, age 14
Article URL: https://github.com/theGcmd/SNNcontinual-learning
Comments URL: https://news.ycombinator.com/item?id=47251047
Points: 1
# Comments: 0
Major data leak forum dismantled in international cybercrime operation
Show HN: Scout-and-Wave – Parallel agent coordination via prompts
I built a coordination protocol that lets multiple Claude Code agents work on the same codebase in parallel without merge conflicts. The protocol is encoded entirely in markdown prompts, no binary or framework.
The core idea: prevent conflicts at planning time through two invariants: 1. Disjoint file ownership: no two agents in the same wave touch the same file 2. Frozen interface contracts: agents code against exact type signatures defined upfront
How it works:
- Scout agent analyzes the codebase, runs a suitability gate (5 questions), produces a coordination artifact (IMPL doc) with file ownership table and interface contracts - Human reviews and approves - Scaffold agent creates shared type files from approved contracts, compiles them - Wave agents implement in parallel, each in its own git worktree - Orchestrator merges sequentially, conflict-free by construction
The interesting part: the entire protocol lives in natural language. Invariants are embedded verbatim in the prompts at their enforcement points. A capable LLM follows them consistently. This proves you can encode coordination protocols in prompts and get structural safety guarantees, which has implications beyond parallel coding.
Repo: https://github.com/blackwell-systems/scout-and-wave Formal spec with invariants I1-I6: https://github.com/blackwell-systems/scout-and-wave/blob/mai...
I built this because I kept spawning multiple Claude Code sessions in separate terminals and having them conflict. Worktrees isolated execution but didn't prevent the conflicts. Realized the missing piece was coordination before execution, not better infrastructure.
Tradeoffs: rigidity (if an interface is wrong mid-wave, you restart), LLM drift risk (prompts can be reasoned around, unlike code enforcement), and currently Claude Code specific (though the protocol is portable).
Dogfooded on 50+ features across multiple projects. Failure rate: suitability gate rejects ~20-30% of requests (correct rejections), ~85-90% of suitable decompositions complete on first try.
Comments URL: https://news.ycombinator.com/item?id=47251030
Points: 2
# Comments: 0
New RAGLight feature: deploy a RAG pipeline as a REST API with one command
Article URL: https://github.com/Bessouat40/RAGLight
Comments URL: https://news.ycombinator.com/item?id=47251027
Points: 2
# Comments: 1
Monday CEO "If you think about any company, 90% of the context isn't documented"
Full quote from the 20VC podcast: "If you think about any company, even Monday itself, 90% of the context is not documented anywhere. Nobody knows it. It's something that kind of floats in the air. What's the idea? What's the strategy? Who's doing what? What's next month? What's next year? How are we going to do it? Why are we doing what we're doing? What's the thought process behind it?"
This is exactly the problem I set out to solve with my app Bother. Let me know what you think, you can try it without an account: https://bother.now
Comments URL: https://news.ycombinator.com/item?id=47251022
Points: 1
# Comments: 0
The Best AI Tools That Respect Your Privacy
Article URL: https://decrypt.co/359454/best-ai-tools-respect-privacy
Comments URL: https://news.ycombinator.com/item?id=47251016
Points: 4
# Comments: 1
Agent frameworks are solving the wrong problem
Article URL: https://github.com/MrPrinceRawat/kanly
Comments URL: https://news.ycombinator.com/item?id=47251011
Points: 2
# Comments: 1
A taxonomy of text output (from tools that want to be too clever)
Article URL: https://utcc.utoronto.ca/~cks/space/blog/sysadmin/ProgramTextOutputTaxonomy
Comments URL: https://news.ycombinator.com/item?id=47250990
Points: 2
# Comments: 0
The FCC Just Made It Harder to Get Low-Income Internet. Why Critics Are Calling It a 'War on the Poor'
Google's Gemini AI Drove Man Into Deadly Delusion, Family Claims in Lawsuit
Premier League Soccer 2026: Stream Newcastle vs. Man United Live
Intel's Make-Or-Break 18A Process Node Debuts For Data Center With 288-Core Xeon 6+ CPU
Google and Qualcomm have tag-teamed a serious vulnerability in the chipsets used in Android mobile devices, which has been exploited in the wild as a zero-day
My Pixel 10A Review: An Entry Point to Android for iPhone Owners
NotebookLM's Video Overviews Just Got Better Thanks to a Trifecta of Google's AI Models
Aside From Classes, This Is the Fastest Way to Learn How to Cook
Sleep Soundly Tonight by Taking These 7 Natural Vitamins and Supplements
CNET Survey Finds US Adults Want Phones With Better Battery Life, but Can They Afford to Upgrade?
New York could prohibit chatbot medical, legal, engineering advice
Article URL: https://folding-sky.com/blog/ny-senate-bill-s7263-chatbot-liability
Comments URL: https://news.ycombinator.com/item?id=47250286
Points: 1
# Comments: 0
