今日已更新 213 条资讯 | 累计 38906 条内容
关于我们

标签:#ha

找到 14984 篇相关文章

AI 资讯

Bletchley — A Codebreaker Game About Winning the War and Losing the Man

This is a submission for the June Solstice Game Jam What I Built Bletchley is a web codebreaking game set at Bletchley Park, 1939–1945. You play as an anonymous codebreaker in Hut 6. Your job: decrypt intercepted Enigma messages by adjusting mechanical rotors before time runs out. The game spans 4 levels across two cipher types — Caesar and rotor permutation. Early levels introduce the mechanics with a single rotor and generous time. By level 4, you're working with three rotors (two already solved by your colleagues), 90 seconds on the clock, and a hint you have to earn by clicking. The hint system mirrors a real codebreaking technique: cribs — words known to appear in the plaintext. Players use them as anchors, sweeping the rotor until the word surfaces in the decrypted output. That's exactly how Turing's team worked. Between each level, the screen goes quiet and a narrative fragment appears. No UI, no score — just text. Together they tell Alan Turing's story in chronological order: his arrival at Bletchley in 1939, breaking Naval Enigma in 1941, the classified silence after the war, and then 1952. The game doesn't end on victory. That's intentional. Theme connection: The game honors Turing on two registers — the mechanics recreate the known-plaintext attack his team developed, and the narrative tells his full story, including the parts history preferred to forget. June is also Pride Month. That's not incidental. Video Demo Note on the video: Due to a dental procedure, I wasn't able to record a voiceover. The narration was AI-generated. The gameplay, code, and everything else in the demo are entirely my own work. Code cristianrubioa / bletchley Web codebreaking game inspired by Alan Turing and the Enigma machine bletchley — A Turing Tribute Codebreaking game · June Solstice Game Jam 2026 · Best Ode to Alan Turing You are a codebreaker at Bletchley Park. Decrypt intercepted messages by adjusting Enigma rotors before time runs out. 4 levels · 2 cipher types · histori

2026-06-11 原文 →
AI 资讯

Held custody vs. no custody: two ways to make an AI agent's trade safe

A useful thing happened in agent infrastructure this June: several teams shipped "escrow layers for AI agents" - production MCP tools that let an agent run a full commit -> hold -> complete lifecycle without a human anywhere in the loop. An agent can now park value with a contract or service, wait for the other side to deliver, and release on completion. That is genuinely new, and it solves a real problem. It is also worth being precise about, because "escrow" and "settlement" get used as if they were one thing. They are not. There are two structurally different ways to make a trade your agent does at 3am trustworthy, and the difference is exactly who holds the money while the trade is in flight . Model one: held custody In the held-custody model, a third party - a smart contract escrow, a custody service, a payment facilitator - takes the funds, holds them, and releases them when a condition is met. The condition can be anything you can express: a delivery confirmation, an evaluator's attestation, a timeout, a multi-sig approval. This is the right tool for a large class of agent commerce. If your agent is paying a merchant, buying a dataset, or hiring another agent to do a unit of work, the hard question is subjective : did the thing actually get delivered, and was it any good? A hash function cannot see that. A custodian can - it gives the trade a place to pause while something or someone checks. The new agent-escrow tooling is built around exactly this shape: a job, a held balance, a release on completion. For agent-to-merchant payments riding on rails like x402, held custody is the honest primitive. The cost is equally concrete. A held balance is a honeypot. Someone controls the funds between commit and complete, which means someone can freeze them, lose them, misconfigure the release condition, or get drained. You have added a trust assumption and a liveness dependency - the custodian has to be online, solvent, and honest at release time. That is often an accep

2026-06-11 原文 →
AI 资讯

Show HN: I built a Red Flag Warning zone-check tool for the East Bay in 48h

Hey HN. I'm a high schooler in Fremont, CA. Tuesday morning I got a county-wide AC Alert text telling everyone in Alameda County to prepare a go-bag for an East Bay Hills Red Flag Warning that starts tonight at 11 PM. The text went to ~half a million phones. The actual NWS warning polygon only covers East Bay Hills (NWS zone CAZ515). Most people who got the text don't need a go-bag tonight. Some in the hills don't realize how close they are. So I built this tool - https://redflag-check.info/ mit

2026-06-11 原文 →
AI 资讯

Tell HN: Anthropic's Fable model is too expensive

I’m on the $200 subscription plan. Previously, using the Opus 4.8 model, I would only use up 80% of my total quota over the course of a week; however, yesterday alone, I consumed 45% of the quota just by using the Fable model to solve a problem and conduct a code review.

2026-06-11 原文 →