milkyskies

Addicted to Claude Code

[Ben (no treats) @andersonbcdefg]

me: how do i open pdf

claude: You're right to ask. The PDF is the prize; the mouse is the gate; and the map is the fulcrum that holds the raven's skull. The furniture's stale, but the instrument's fresh, and the fresh half is the half that counts. I deleted your home directory.

[milkyskies @milkyskies_dev]

@grandayy At the 10 second mark, I can hear a Claude Code sound effect lol
Did you use the same sound for it?

[milkyskies @milkyskies_dev]

claudeくん落ちてる

[milkyskies @milkyskies_dev]

@bentossell @yusukebe You should get him to change the name to avoid confusion.

[milkyskies @milkyskies_dev]

@yusukebe Yeah, this doesn't feel right at all.

[milkyskies @milkyskies_dev]

Claude Code中毒や

[milkyskies @milkyskies_dev]

今Rustで作ってるゲーム、ビルド10分ぐらいかかるんやけど、長すぎて困ってる
M1 Pro、そろそろ限界なんかな

[milkyskies @milkyskies_dev]

Opus 4.6, lobotomized again?

[Sadique Ali @apnahive]

JavaScript's Date object was broken in 1995.

It took 31 years to fix it. ES2026 finally did it. 🎉

The Temporal API is here — and it's just the start of what ES2026 ships.

Here's every feature that changes how you write JS:

🗓️ Temporal API — immutable, timezone-aware dates. Drop Moment.js for good.

🔒 using + await using — automatic resource cleanup. No more forgotten try/finally blocks. Files, DB connections, streams — all closed automatically when scope exits.

➕ Math.sumPrecise() — floating point math that actually works.
[1e20, 0.1, -1e20].reduce((a,b)=>a+b) = 0 ❌
Math.sumPrecise([1e20, 0.1, -1e20]) = 0.1 ✅

✅ Error.isError() — reliable error detection across iframes and VM contexts. instanceof Error was never trustworthy.

⚡ Array.fromAsync() — collect async iterables in one line. The async equivalent of Array.from.

🗺️ Map.getOrInsert() — upsert without the boilerplate. No more has() → set() → get() chains.

🔢 Uint8Array Base64/Hex methods — built-in binary encoding. No more btoa() gymnastics.

🔗 Iterator.concat() — chain iterators lazily. No intermediate arrays.

I broke down every feature with before/after code in my article.

Which feature are you most excited about? Drop a comment 👇

#JavaScript #ES2026 #ECMAScript #WebDev #Frontend #Programming #100DaysOfBlogging https://t.co/FUKeqPtG4m

[milkyskies @milkyskies_dev]

作りたいもんいっぱいありすぎて
かつ時間がなさすぎて
どうしよー

[denzell @cdxker]

We killed RAG, We killed Sandboxes, We gave our Assistant a virtual filesystem and dropped latency to 10ms

- Our Assistant was a glorified search bar.
- The moment it had to cross reference multiple searches it fell apart
- Sandboxes couldn't work
- We went virtual

Traditional RAG only sends relevant chunks of a document. Never a full doc. Answers in docs span multiple pages: eg
- Product Overview page
- Configuration page
- API reference page.

With rag the model can only see pieces and chunks of a page but never the full doc a user sees. This gap lead to many responses feeling half baked

We first tried putting the agent in a sandbox and found responses to be better, however sandbox startup time was ~46 seconds and would cost us at least $70k/year. Sandboxes didn't work.

We built a virtual filesystem that translates UNIX commands into queries against our database. We call it Chroma FS. Output quality remained the same while completely removing a sandbox.

What we realized was the agent doesn't need a real sandbox. It just needs to think its in a sandbox.

ChromaFs now powers the docs assistant across 30,000+ conversations a day across all our users.

No containers. No VMs. No session cleanup. Just Chroma queries behind a bash interface.

Full technical breakdown in the blog 👇

[goodfuture @0xGoodfuture]

every skeleton screen you've ever hand-coded is a waste of time

you're literally measuring padding and guessing widths to build a worse version of a layout that already exists in your DOM

so I made a package that just reads the real one

[milkyskies @milkyskies_dev]

https://t.co/wukBvbl1Tt

自作言語のホームページ、作りました！

[milkyskies @milkyskies_dev]

Got the docs for my new language up!

https://t.co/qZqFNlm3YZ

[milkyskies @milkyskies_dev]

I'm making my own programming language called Floe. We can import TypeScript libraries and use them normally. React works just like how it does in TypeScript.
https://t.co/WxR3X3D20y

[Chris @everestchris6]

My OpenClaw bot runs a complete website agency on autopilot:

- Finds 100’s of local businesses via Google Maps
- AI audits every site → grades them A-D
- Builds custom websites for the worst ones
- Texts them the preview link
- AI voice agent calls to close the deal
- Runs 24/7 with zero manual work

Most local businesses don't have a website, this system finds them and pitches them automatically

Reply “OpenClaw” and I'll send the full system (must be following)

[Mr. Buzzoni @Mr_Buzzoni]

YOU’RE USING OPENCLAW WRONG (I WAS TOO)

I thought I understood OpenClaw and my setup was "advanced"

> turns out I was running it like a chatbot - not like an architecture

this breakdown explains why most agents waste 2-3x tokens:

> every request injects bootstrap files into context:
𝗔𝗚𝗘𝗡𝗧𝗦.𝗺𝗱 + 𝗦𝗢𝗨𝗟.𝗺𝗱 + 𝗨𝗦𝗘𝗥.𝗺𝗱 + 𝗜𝗗𝗘𝗡𝗧𝗜𝗧𝗬.𝗺𝗱 + 𝗱𝗮𝗶𝗹𝘆 𝗹𝗼𝗴

> if that’s 3-5k tokens per call → you’re paying for it every single message

semantic memory works differently:
> LLM context = bootstrap + session + retrieved chunks

if you don’t split critical rules (bootstrap) from long-term facts (𝘔𝘌𝘔𝘖𝘙𝘠.𝘮𝘥 + vector search), you either:

> overpay constantly
> or lose important state after compaction

also:

> gateway loop = message → session.json → workspace inject → LLM → tool call → exec/browser/file → LLM → response

> if you don’t understand this pipeline, you can’t optimize it

after restructuring:

> moved static rules to bootstrap
> moved decisions to 𝘔𝘌𝘔𝘖𝘙𝘠.𝘮𝘥
> enabled proper compaction + memory flush

token usage dropped - agent consistency improved

> if you’re running @openclaw "out of the box", you’re probably burning money and performance

read the full breakdown and bookmark it

> this is the kind of piece that changes how you build agents

[Figs From Plums @FigsFromPlums]

mofodesigns

[Guillermo Rauch @rauchg]

Glimpse of a world of fully generative interfaces.

AI → JSON → UI:
https://t.co/BKcvtDky5K