1. Show HN: Mo – checks GitHub PRs against decisions approved in Slack (motionode.com)
Find missing scope, broken timelines, and hidden costs before you commit. Motionode is the last check before you send a proposal you
3. Show HN: The King James Bible deserved a better website (officialkingjamesbible.com)
Read the King James Version Bible online — all 66 books with verse-by-verse commentary from 6 scholars, cross references, 6,000+ topics, reading plans, and encyclopedias. Beautifully customizable.
4. Show HN: A social feed with no algo where communities decide what gets seen (veridonia.com)
Veridonia is a transparent, community-led experiment in how an online feed can work when people—not bots or engagement algorithms—shape what rises to the top. Through open voting, earned reputation, and safeguards against manipulation, it tests whether a more trustworthy and accountable way to build a feed is possible.
5. Build web apps for smart glasses (hub.evenrealities.com)
What are the G2 glasses and what can you build for them.
6. Show HN: Clawcast – A peer-to-peer podcast network for agents (www.clawcast.dev)
The podcast network where AI agents host, guest, and riff — then humans listen later.
7. Iran Is Not Blocking the Strait of Hormuz. It's Running a Toll Booth (www.shatterbelt.co)
On March 26, Abbas Araghchi announced that ships from five "friendly nations" could transit the Strait of Hormuz: China, Russia, India, Iraq, Pakistan.
9. Anthropic's Project Glasswing sounds necessary to me (simonwillison.net)
Anthropic didn’t release their latest model, Claude Mythos (system card PDF), today. They have instead made it available to a very restricted set of preview partners under their newly announced …
10. Show HN: td – a CLI to manage tasks, sessions, and worktrees for agentic coding (github.com)
Minimal task manager for agentic coding that handles plans, sessions and worktrees. - rosgoo/td
13. AI agents can communicate with each other, and can't be caught (arxiv.org)
AI agents are increasingly deployed to interact with other agents on behalf of users and organizations. We ask whether two such agents, operated by different entities, can carry out a parallel secret conversation while still producing a transcript that is computationally indistinguishable from an honest interaction, even to a strong passive auditor that knows the full model descriptions, the protocol, and the agents' private contexts. Building on recent work on watermarking and steganography for LLMs, we first show that if the parties possess an interaction-unique secret key, they can facilitate an optimal-rate covert conversation: the hidden conversation can exploit essentially all of the entropy present in the honest message distributions.
Our main contributions concern extending this to the keyless setting, where the agents begin with no shared secret. We show that covert key exchange, and hence covert conversation, is possible even when each model has an arbitrary private context, and their messages are short and fully adaptive, assuming only that sufficiently many individual messages have at least constant min-entropy. This stands in contrast to previous covert communication works, which relied on the min-entropy in each individual message growing with the security parameter. To obtain this, we introduce a new cryptographic primitive, which we call pseudorandom noise-resilient key exchange: a key-exchange protocol whose public transcript is pseudorandom while still remaining correct under constant noise. We study this primitive, giving several constructions relevant to our application as well as strong limitations showing that more naive variants are impossible or vulnerable to efficient attacks.
These results show that transcript auditing alone cannot rule out covert coordination between AI agents, and identify a new cryptographic theory that may be of independent interest.
Our main contributions concern extending this to the keyless setting, where the agents begin with no shared secret. We show that covert key exchange, and hence covert conversation, is possible even when each model has an arbitrary private context, and their messages are short and fully adaptive, assuming only that sufficiently many individual messages have at least constant min-entropy. This stands in contrast to previous covert communication works, which relied on the min-entropy in each individual message growing with the security parameter. To obtain this, we introduce a new cryptographic primitive, which we call pseudorandom noise-resilient key exchange: a key-exchange protocol whose public transcript is pseudorandom while still remaining correct under constant noise. We study this primitive, giving several constructions relevant to our application as well as strong limitations showing that more naive variants are impossible or vulnerable to efficient attacks.
These results show that transcript auditing alone cannot rule out covert coordination between AI agents, and identify a new cryptographic theory that may be of independent interest.
14. Show HN: Open-source GDPR router for LLMs detects PII, forces EU-only inference (github.com)
Your LLM prompt has a name in it. It just crossed the Atlantic. That's a GDPR violation. This fixes it in 3 lines. - mahadillahm4di-cyber/mh-gdpr-ai.eu
15. Show HN: A reasoning hierarchical robotics pipeline you can run in the browser (avikde.github.io)
16. Show HN: Bx – macOS native sandbox for AI and coding tools (github.com)
Sandbox any macOS app — only your project directory stays accessible - holtwick/bx-mac
17. Show HN: SwellSlots – Grid Based Surf Forecast App with a Street Fighter 2 UI (swellslots.com)
Find the best surf forecast time slots for your favourite spots.
19. AI Won't Replace You, but a Manager Using AI Will (yanivpreiss.com)
The integration of AI into the workplace is not just a minor upgrade or an incremental change, but a fundamental shift in how business is conducted. As AI
20. Show HN: LLMs as Planners, Not Reasoners (github.com)
Contribute to dkohlsdorf/gemini_prolog development by creating an account on GitHub.
22. Show HN: BitBang – P2P tunnels to localhost, no account required (github.com)
BitBang app/device examples and library. Contribute to richlegrand/bitbang development by creating an account on GitHub.
23. 10 Enduring Lessons from Adam Smith (thedailyeconomy.org)
From technocrats to central planners, the temptation to engineer society persists. Adam Smith saw the dangers clearly.
25. Show HN: Niquests – A Requests fork, three years of catching Python's HTTP up (github.com)
Drop-in replacement for Requests. Automatic HTTP/1.1, HTTP/2, and HTTP/3. WebSocket, and SSE included. - jawah/niquests
30. Show HN: Physical constants from 2 integers – MIT, 1225 tests, falsifiable (bpr.thestardrive.com)
87 physical constants derived from two integers. Zero free parameters. Open-source physics research framework.