Hacker News
Project Nomad – Knowledge That Never Goes Offline
More common mistakes to avoid when creating system architecture diagrams
Project Nomad – Knowledge That Never Goes Offline
More common mistakes to avoid when creating system architecture diagrams
More common mistakes to avoid when creating system architecture diagrams
Be intentional about how AI changes your codebase
Be intentional about how AI changes your codebase
A sufficiently detailed spec is code
Be intentional about how AI changes your codebase
A sufficiently detailed spec is code
A sufficiently detailed spec is code
Show HN: Tmux-IDE, OSS agent-first terminal IDE
Show HN: Tmux-IDE, OSS agent-first terminal IDE
Get Shit Done: A meta-prompting, context engineering and spec-driven dev system
Get Shit Done: A meta-prompting, context engineering and spec-driven dev system
Learnings from training a font recognition model from scratch
Learnings from training a font recognition model from scratch
Learnings from training a font recognition model from scratch
X / Twitter
a brainstorming canvas that changes the linear process of concepting into a fun exploratory manuscript with bridges of reasoning between nodes ...
any topic, one single canvas, infinite exploration to dive into rabbit holes. that was the idea behind gridscape. https://t.co/PqjlhoTIQ2
I've been building a Claude Code skill that turns Claude into a color science expert.
113 reference files. 286K words. From Helmholtz (1856) to OKLCH.
Install in one line:
git clone https://t.co/2amC74icMo ~/.claude/skills/color-expert
Still a work in progress, but I've published the first draft of a new chapter on "Using Git with coding agents" https://t.co/uP2DGVcMtQ
pi + ghostty running entirely in a cloudflare workers durable object. sqlite based file system + js code exec + cron support. The best part is it can deploy worker sites using Dynamic Worker Loaders. https://t.co/CflJjXjchP
Anthropic is on a tear https://t.co/uWVR8dd3gT
https://t.co/THBioErFj7
v0.14.4 adds GitHub review submission, pi extension self-hosting wiring, and three community contributions.
- Post reviews (comments, approvals) directly to GitHub from the code review UI . per-file, per-line annotations mapped to PR review comments.
- Pi's extension now has proper env vars to communicate with self-hosted share service.
- Repo name in tab titles
- Parser fix for nested markdown code fences, scrollbar interaction fix, other UI cosmetics
Peep the header in this PR review:
1/ if there's code mode, there's also query mode.
https://t.co/gPolE9eBBQ 💧
npm install -g dripline
introducing dripline, turns any API, CLI, or cloud service into a SQL table. install a plugin, clanker writes a query, get rows back. joins, aggregations, window functions and duckdb handles the rest.
ultra easy to extend, repo includes 13 plugins, 61 tables. github, docker, pi, brew, kubectl, cloudflare, vercel, and more.
obligatory @badlogicgames pi-dripline-context extension that injects all available tables into your agent's context so it knows what it can query:
pi install npm:dripline
thanks to @DanielGri 's last update to Glimpse, pi-diff-review now works on macos, linux, and windows!
https://t.co/8EF1s3waFw https://t.co/JdM6iM3qGZ
We just released Stash — fast local-first folder sync across your devices & agents. It's backed by GitHub, with more storage providers coming.
We've been using this @telepathinc to keep notes, docs, and skills in sync across computers, team members, and remote agents. Now available on npm.
Wasn't joking about this one btw
You can reverse-engineer pretty much any part of Apple platform internals in seconds using Claude or Codex with Hopper MCP https://t.co/lBxuJ3ElCH https://t.co/iiNLH0lqA7
https://t.co/z7p1rL84KV
Hands-on sound: IRCAM's ASAP apps are now free on iPad:
https://t.co/6byOO5H9ft
@Ircam @ircamforum https://t.co/ZFSPPxhwGl
Design.md isn't your design system.
With design systems in Magic Patterns, AI uses your:
- Components (syncs to codebase via MCP)
- Typography (can use custom fonts)
- Color tokens (import from Figma / tokens.json)
- Icons (any library)
- Spacing tokens
- Rules https://t.co/3kJsIJNmQ2
I have been working on Obsidian Reader for a over a year. I didn't want to share it until I felt it was good enough. It's finally there.
Consistent formatting for any article. Outline, syntax highlighting, nice footnotes, adjustable typography.
Runs locally. Just rules, no AI. https://t.co/Nf2mO0FpjW
https://t.co/D9wdpMh7TR
Introducing the Readwise CLI.
Anything you've saved in Readwise (highlights, articles, PDFs, books, youtube, newsletters) is now instantly accessible from the terminal.
For you, and your AI agents.
npm install -g @readwise/cli https://t.co/JAJsN3mE60
Introducing the Secure Exec SDK
Secure Node.js execution without a sandbox
⚡ 17.9 ms coldstart, 3.4 MB mem, 56x cheaper
📦 Just a library – supports Node.js, Bun, & browsers
🔐 Powered by the same tech as Cloudflare Workers
$ 𝚗𝚙𝚖 𝚒𝚗𝚜𝚝𝚊𝚕𝚕 𝚜𝚎𝚌𝚞𝚛𝚎-𝚎𝚡𝚎𝚌 https://t.co/tQqCIgVhAV
Introducing TigerFS - a filesystem backed by PostgreSQL, and a filesystem interface to PostgreSQL.
Idea is simple: Agents don't need fancy APIs or SDKs, they love the file system. ls, cat, find, grep. Pipelined UNIX tools. So let’s make files transactional and concurrent by backing them with a real database.
There are two ways to use it:
File-first: Write markdown, organize into directories. Writes are atomic, everything is auto-versioned. Any tool that works with files -- Claude Code, Cursor, grep, emacs -- just works. Multi-agent task coordination is just mv'ing files between todo/doing/done directories.
Data-first: Mount any Postgres database and explore it with Unix tools. For large databases, chain filters into paths that push down to SQL: .by/customer_id/123/.order/created_at/.last/10/.export/json. Bulk import/export, no SQL needed, and ships with Claude Code skills.
Every file is a real PostgreSQL row. Multiple agents and humans read and write concurrently with full ACID guarantees. The filesystem /is/ the API.
Mounts via FUSE on Linux and NFS on macOS, no extra dependencies. Point it at an existing Postgres database, or spin up a free one on Tiger Cloud or Ghost.
I built this mostly for agent workflows, but curious what else people would use it for. It's early but the core is solid. Feedback welcome.
https://t.co/IPhieopOSP
Just launched https://t.co/s21SCq1KVO a free tool to stress-test your logo 🔳 https://t.co/T7pjTKMwYj
https://t.co/vSz7AJyeUy
For the freaks:
Our experimental CLI is open-source and available for you to try.
npm install -g @aredotna/cli
https://t.co/WUYTMc4neX https://t.co/rbj3s5HFWX
We've been building an internal Claude Code plugin system at Intercom with 13 plugins, 100+ skills, and hooks that turn Claude into a full-stack engineering platform. Lots done, more to do. Here's a thread of some highlights.
This is how a code factory should work.
I was waiting at the doc’s office and filed 6 bugs - all from my phone.
1 is already merged, 2nd is merging, 3-6 are getting done in parallel.
Using Symphony + Codex (Elixir, Codex App Server, Linear, GitHub) https://t.co/ZpTEw3GEB8
New blog post: "A sufficiently detailed spec is code"
I wrote this because I was tired of people claiming that the future of agentic coding is thoughtful specification work. As I show in the post, the reality devolves into slop pseudocode
https://t.co/V86V7cjWpS
i can't speak for david. what i see is this:
if you let agents build or extend a codebase with only minor or no supervision, you get unmaintainable garbage, because the agent makes terrible decisions that compound, both big and small.
those decisions make it hard for both you and the agent to keep modifying the code base, until eventually it's unrecoverable.
why does the agent make bad decisions? i can't tell for sure, but my gut tells me that training data can currently not capture the holistic thinking needed to design and evolve complex systems. that's one part of the problem. related to that, and oversimplified: agents output the "mean quality" of the code they saw during training. most of that code is very bad. specifically tests, which humans are terrible at writing at.
another part of the problem is that specification via prompt is not precise enough, so the agent has to fill in the blanks, giving it enough rope to hang itself. the more detailed your spec gets, so the agent gets constrained and less likely to produce crap, the closer you are to handwriting the code yourself, as that's the most detailed version of the spec that can exist. so then you gain nothing. back to prompt spec it is, which means the agent fills in blanks, which means we get suboptimal or truely bad results.
using agents can still be a net productivity boost (see other posts in my thread), but it is not easy to come up with consistent workflows that produce both production quality maintainable code while retaining the speed advantages agents give you.
Today, we’re introducing Cheats.
Prompting has failed us. Most people don’t know what to type.
AI unlocked a ton of skills for experts, but the rest of us kinda need a… cheat.
Sound on! https://t.co/sg8AjxjeI1
pi-mcp-adapter lets you install 100+ MCP servers without any token or resource bloat. Just added MCP UI support with bidirectional messaging and streaming.
pi install npm:pi-mcp-adapter
https://t.co/wvg2Iv4krl https://t.co/wQC9kbkwrg