Hacker News

Article URL: https://mcyoung.xyz/2024/04/17/calling-convention/

Comments URL: https://news.ycombinator.com/item?id=47208688

Points: 1

# Comments: 0

Article URL: https://github.com/virtengine/bosun/releases/tag/0.37.0

Comments URL: https://news.ycombinator.com/item?id=47208678

Points: 1

# Comments: 0

Article URL: https://www.youtube.com/watch?v=wLTcubTNIl4

Comments URL: https://news.ycombinator.com/item?id=47208669

Points: 1

# Comments: 0

Article URL: https://newsletter.djr.ai/p/the-sunday-signal-capital-doesnt

Comments URL: https://news.ycombinator.com/item?id=47208667

Points: 1

# Comments: 0

Article URL: https://www.metabase.com/blog/lessons-learned-building-ai-analytics-agents

Comments URL: https://news.ycombinator.com/item?id=47208650

Points: 1

# Comments: 0

TLDR; I built a tool that turns any API into a CLI designed for ai agents

---

Got tired of dealing with bloated context windows from MCP servers and skills that stuff entire API docs into the agent's context

CLIs fix this, agents run a single command to self-discover everything an API has to offer

So, built a tool to generate them for any api. All CLIs are written in Go, fast and lightweight, no dependencies

Help text (via the --help flag) is the killer feature: all context for each command/endpoint/parameter is extracted directly from the user-facing API docs and enhanced with llms. It's bundled directly with the CLI and agents fetch only what they need at runtime. No context overhead, no fumbled API calls.

Most APIs don't have a CLI yet. Can have Opus one-shot simple ones, but building a great one with cross-platform binaries, install scripts, detailed help text, and auto-updates takes time and is frustrating to repeat for every API. Maintaining it the API grows is a headache

Give InstantCLI any API docs url and it generates a production-ready CLI in minutes. It includes binaries + install scripts for all platforms, auto-updates as your API changes, docs-enhanced help text designed for agents, and hosting

Comments URL: https://news.ycombinator.com/item?id=47208636

Points: 2

# Comments: 2

Rust/macroquad game with single player AI mode, online VS, and local 1v1. All running via WASM in the browser.

Still WIP as art assets still need to be added and tweaked.

Full disclosure. Used Claude Opus, Nanobanana, and SunoAI a huge amount to do the heavy lifting for this project

Comments URL: https://news.ycombinator.com/item?id=47208628

Points: 1

# Comments: 0

I've been building Claude Code tools for the past 60 days — mostly because I couldn't stop asking "wait, how much time am I actually spending on this?"

The result is 41 zero-dependency tools. Some examples:

- *cc-wrapped*: Spotify Wrapped for Claude Code — drag in your ~/.claude folder, get a visual year-in-review - *cc-session-stats*: Session durations, streaks, health warnings if you've gone 3+ hours without a break - *cc-agent-load*: How much time is actually YOU vs AI subagents? Mine is 35% me, 65% AI - *cc-ghost-log*: "Ghost Days" — days you had zero Claude Code sessions but committed code anyway - *cc-impact*: What did you actually build? Commits, lines added, files changed across all your repos - *cc-peak*: When are you most focused? Hour-of-day heatmap + optimal 4-hour working window - *cc-collab*: Are you getting better at working with Claude Code? Weekly commits-per-hour efficiency trend - *cc-focus*: Are you spreading too thin? Weekly project scatter — mine went from 4 projects to 1 (converging -40%) - *cc-score*: 0–100 productivity score. I'm 89/100 (A — Power User) - *cc-burnout*: Same data, different angle. My burnout risk: 60/100 (High). High score ≠ sustainable. - *cc-monthly*: Monthly retrospective in Markdown — paste it straight into your dev blog - *cc-predict*: The only forward-looking tool — projects your month-end stats based on last 14 days

All 41 tools are free, MIT licensed, zero dependencies. Most run in browser (no install), CLI versions available via npx.

The raw numbers from 60+ days: 3,580 sessions, 142 hours, 40 Ghost Days, 563 commits, +305k net lines.

Full data story at: https://yurukusa.github.io/cc-story/

Comments URL: https://news.ycombinator.com/item?id=47208594

Points: 1

# Comments: 0

Article URL: https://maderix.substack.com/p/inside-the-m4-apple-neural-engine

Comments URL: https://news.ycombinator.com/item?id=47208573

Points: 2

# Comments: 0

Article URL: https://www.newscientist.com/article/2514976-how-ukraine-became-a-drone-factory-and-invented-the-future-of-war/

Comments URL: https://news.ycombinator.com/item?id=47208567

Points: 3

# Comments: 0

Article URL: https://www.youtube.com/watch?v=R2ulYtpV_rs

Comments URL: https://news.ycombinator.com/item?id=47208561

Points: 2

# Comments: 0

Article URL: https://www.bloomberg.com/news/articles/2026-03-01/jack-dorsey-s-4-000-job-cuts-at-block-arouse-suspicions-of-ai-washing

Comments URL: https://news.ycombinator.com/item?id=47208545

Points: 4

# Comments: 1

Article URL: https://www.askverdict.ai

Comments URL: https://news.ycombinator.com/item?id=47208532

Points: 1

# Comments: 1

Article URL: https://www.bloomberg.com/news/articles/2026-02-27/the-science-of-cancer-care-is-being-changed-by-brain-tumor-survivors

Comments URL: https://news.ycombinator.com/item?id=47208523

Points: 4

# Comments: 1

Article URL: https://ounapuu.ee/posts/2026/03/01/cloud/

Comments URL: https://news.ycombinator.com/item?id=47208518

Points: 1

# Comments: 0

Article URL: https://www.ft.com/content/e352b4b3-ecba-4bc2-984f-9e4f3ce8a366

Comments URL: https://news.ycombinator.com/item?id=47208507

Points: 2

# Comments: 2

Article URL: https://www.reuters.com/business/media-telecom/hackers-hit-iranian-apps-websites-after-us-israeli-strikes-2026-03-01/

Comments URL: https://news.ycombinator.com/item?id=47208505

Points: 4

# Comments: 0

Comments URL: https://news.ycombinator.com/item?id=47208481

Points: 2

# Comments: 1

Built a crisis monitoring dashboard for the current Middle East situation using zero paid APIs. News from RSS feeds (Al Jazeera, BBC, Reuters, AP), market data from TradingView embeds, live TV streams, and a map with conflict hotspots. Source: https://github.com/jayyvk/situationtracker

Comments URL: https://news.ycombinator.com/item?id=47208472

Points: 2

# Comments: 0

1. Specs and plans are source code: Specs and plans live in git alongside source code, not in chat history. A new agent reads arch.md for the big picture, then its specific spec. You always know why something was built.

2. Three models review every phase: Claude, Gemini, and Codex catch almost entirely different bugs. No single model found more than 55% of issues. If you only review with the model that wrote the code, you're missing half the bugs. 20 bugs caught before shipping. Claude Code found 5 bugs, Gemini and Codex caught another 15, including a severe security issue Claude missed.

3. Enforce the process, don't suggest it. A state machine forces Spec → Plan → Implement → Review → PR. The AI can't skip steps. Tests must pass before advancing. AIs don't stick to the plan by themselves, you need rails.

4. Annotate, don't edit. Most of the work is writing specs and reviews that guide the code, not hacking at files in an open-ended chat.

5. Agents coordinate agents. An architect agent spawns builder agents into isolated git worktrees. You direct the architect; it directs the builders. They message each other async.

6. Manage the whole lifecycle. Most AI tools help you write code faster — maybe 30% of the job. The other 70% is planning how, reviewing, integrating, deployment scripts, managing staging vs prod. Have AI run the whole pipeline from spec to PR and beyond.

Overall result: One engineer able to produce what a team of 3-4 would usually do. Measured 1.2 points better code on a 10 point scale vs claude code. Downsides: takes a lot longer, much more token usage, but still reasonable at $1.60 per PR.

We open sourced it: https://github.com/cluesmith/codev More details and raw results: https://cluesmith.com/blog/a-tour-of-codevos/

Comments URL: https://news.ycombinator.com/item?id=47208471

Points: 2

# Comments: 1