sync

I have a similar stack (using oRPC instead of tRPC, recommended!) and I'd say React Native, specifically Expo UI: https://docs.expo.dev/versions/latest/sdk/ui/

This will get you the most native feel across all platforms (e.g. Liquid Glass) and keeps you in one language (TypeScript).

No performance issues to note in particular because Expo UI is (basically) native - it just uses SwiftUI and Jetpack Compose under the hood.

nope! they're releasing something called "Claude Code mods", toted as their "upcoming way to customize the Claude Code harness"

https://x.com/trq212/status/2101009392611278961

AGENTS.md implementation is open sourced as well: https://github.com/anthropics/claude-code/tree/main/mods/age...

As an individual that 'dozen people beta test' is required. It's not required if you're a business. Also depends on when your account was created.

https://support.google.com/googleplay/android-developer/answ...

Same, but I clicked it, awaited the update, and I'm on iOS 27 proper now-- so just a visual bug.

I eval'd this pretty heavily with no audio or just noise, as for us hallucinating a response is very bad. It works great in this scenario. There are some bugs, e.g. randomly exactly 20 seconds of silence will lead to a 403, but I'm sure these aspects will be improved over time. I didn't get any hallucinations though.

Are you in Smart or Verbatim mode?

https://ai.google.dev/gemini-api/docs/transcribe#transcripti...

You can create a PostToolUse hook [0] which will automatically chastise Claude to shrink comments to one line. It's not perfect but better than the sea of prose it tends to generate by default. Bonus is that it would apply to your colleagues as well!

[0] https://github.com/chrisvariety/branch-fiction/blob/deb37f2b...

If you have a ACSM (the file type Adobe Digital Editions uses for DRM) I’ve been using https://www.acsm-converter.com to strip the DRM and return a standard epub

If using straight npm (v11.10.0 or higher), you can just add to .npmrc in the project root:

min-release-age=5

I tried it on my codebase. There's a lot of overlap with tools like Oxlint / ESLint, I'm not sure that's too valuable vs. a more focused tool that actually focuses solely on 'slop' signals. These lint rules tend to get very opinionated which is why those tools expose so many configuration options.

One real bug tho:

> [ERROR] Imports "mdast" but it's not declared in package.json

A type-only import like `import type { Blockquote, RootContent } from 'mdast';` is actually acceptable if `"@types/mdast": "^4.0.4"` is included in the package.json.

Nice ideas! I've been using the `?` shortcut in atuin [0] which accomplishes the same sort of thing, but these days also has access to an Agent-like experience which allows me to prompt something like "Conventional Commit message for unstaged changes" and it will call `git diff` (after asking permission, of course) and then generate the commit message.

[0] https://atuin.sh

Neat! FYI when I tried it out, seems like there's a 60s timeout:

[Error] Failed to load resource: the server responded with a status of 504 (Gateway Time-out) (generate, line 0)

My "prompt" was, uh, simple: "Turns out, you don't need water to live."

You can strip the DRM fairly easily these days if you have an ACSM file, I vibecoded this the other day after I couldn’t find any online converter that actually worked: https://www.acsm-converter.com

I'm having a hard time adjusting to the Project Panel on the right (and, at least for me, hidden by default) - seems like they're trying to bury the concept of a 'file'?

It's certainly interesting though, and I'll give it some time - the post says "It feels more natural once you've spent a little time with it"

Which plan are you on? I could see that happening with Pro (which I think defaults to Sonnet?), would be surprised with Max…

at least for why Cloudflare keeps repeating the word… Welcome to Agents Week: https://blog.cloudflare.com/welcome-to-agents-week/

Yeah, the lede is buried a bit, these new rate-cards seem to be aligning towards token-based pricing with the prior rates now labeled 'legacy'

https://help.openai.com/en/articles/20001106-codex-rate-card https://help.openai.com/en/articles/11481834-chatgpt-rate-ca...

Cute! Cactus for me. Nice animations too - looks like there were multiple of us asking Claude to reverse engineer the system. I did a slightly deeper dive here if you're interested, plus you can see all the options available: https://variety.is/posts/claude-code-buddies/

(I didn't think to include a UUID checker though - nice touch)

I've posted here before about Claude Code's easter eggs [1] and they're back with another one this year for April Fools: Tamagotchi-style "buddies" appearing as ASCII art companions, determined by your userId.

Thanks to the Claude Code source code leak I was able to reverse engineer how it all works. Due to their PRNG choice (Mulberry32) it's trivial to crack all 4.29 billion seeds in seconds.

Some findings:

- 1% legendary chance: 42,989,564 seeds out of 2^32 produce legendaries - Stats & shiny appear to be dead code: rolled but never read anywhere. Pure bragging rights? - Commons can't have hats, only uncommon+ rolls from the hat table - "God" rolls exist: legendary + shiny + a maxed stat at 100.

[1] https://news.ycombinator.com/item?id=44376970

Hmm, the Mac app downloaded gemma-3-4b-it-Q4_K_M.gguf for me (on an Apple M4) - maybe the desktop apps download different models?

Though, I don't see any references to Gemma at all in the open source code...

As of the time of writing, nothing on the status page either :( https://www.githubstatus.com

Unfortunate, significant price increase for a 'lite' model: $0.25 IN / $1.50 OUT vs. Gemini 2.5 Flash-Lite $0.10 IN / $0.40 OUT.

Did gemini-2.5-flash-image get an upgrade as well? I just got the following, which is fascinating, and not something I've seen before:

> I'm sorry, but I cannot fulfill your request as it contains conflicting instructions. You asked me to include the self-carved markings on the character's right wrist and to show him clutching his electromancy focus, but you also explicitly stated, "Do NOT include any props, weapons, or objects in the character's hands - hands should be empty." This contradiction prevents me from generating the image as requested.

My prompts are automated (e.g. I'm not writing them) and definitely have contained conflicting instructions in the past.

A quick google search on that error doesn't reveal anything either

This is essentially a (vibe-coded?) wrapper around PaddleOCR: https://github.com/PaddlePaddle/PaddleOCR

The "guts" are here: https://github.com/majcheradam/ocrbase/blob/7706ef79493c47e8...

That’s weird, pnpm no longer automatically runs lifecycle scripts like preinstall [1], so unless they were running a very old version of pnpm, shouldn’t they have been protected from Shai-Hulud?

1: https://github.com/pnpm/pnpm/pull/8897

Does anyone here understand "interleaved scratchpads" mentioned at the very bottom of the footnotes:

> All evals were run with a 64K thinking budget, interleaved scratchpads, 200K context window, default effort (high), and default sampling settings (temperature, top_p).

I understand scratchpads (e.g. [0] Show Your Work: Scratchpads for Intermediate Computation with Language Models) but not sure about the "interleaved" part, a quick Kagi search did not lead to anything relevant other than Claude itself :)

[0] https://arxiv.org/abs/2112.00114