Partiful has a paid subscription model now? Donβt they know their product is just an AI prompt??
178
Announcing aviation-mcp.org β add deep knowledge of airports, NOTAMs, weather, navaids, airspace, procedures, terrain, and more to your AI bot.
2
3
232
Oh goodie, Slack has a menu bar icon now. As a reminder, here is a short questionnaire you can use to determine if your startup is important enough to deserve a menu bar icon:
1. No
1
85
At work weβve been having problems with people merging vibe-coded PRs without reviewing them. So we had Claude add a pre-merge quiz. You have to answer five questions about your PR correctly before it will let you merge.
3
2
100
Yo, people who develop for the Apple App Store! I have written a library and tool called XCUIPromoKit that helps your agents design and produce promo assets for your app store listing (search photos, header photos, and promo videos).
github.com/RISCfuture/XCUIPrβ¦
76
If youβre lamenting the eventual death of Maestral, the macOS Dropbox client, Iβve got a replacement for you: zephyrmac.app
Zephyr is a Mac-assed Dropbox client with Finder integration and a slew of Mac-specific features. Available for download and on the App Store.
96
The future of software is hyper-personal. Whoever happens to pay for dinner, everyone will just use their individual vibe-coded Splitwise knockoff.
1
171
All of my iOS/macOS apps now have slick Claude-designed marketing sites:
riscfuture.github.io/FART/
hsk-hanzi.github.io/iOS/
cta-helper.github.io/iOS/
riscfuture.github.io/SubTracβ¦
sf50-told.github.io/iOS/
riscfuture.github.io/IP-Inboβ¦
1
181
If it hasnβt already been done, I am coining the term βtrad-codingβ to mean the opposite of vibe-coding.
41
In the future, all performance reviews will just be reading what Claude stores about you in user_memory.md.
50
Iβm sorry, but youβre just a regular prompt writer, and this company needs 10Γ prompt writers.
2
40
A company I know just got βapprovedβ to use AI after a βsecurity review.β Which is ridiculous β no security team would ever approve the use of AI. AI is a security nightmare. The only reason we all use it is because if we donβt, weβd be out-competed by everyone else who does.
2
97
These AI companies should probably stop calling it βThinking Modeβ or whatever, since in reality, itβs still an LLM, and no thinking is actually happening.
42
Itβs so quaint, these old time travel shows where they say not to touch anything in the past because βthe timeline might be affected,β like our current timeline is so precious. If I ever end up in the past, I am shooting every dinosaur and stomping on every rodent I can find.
45
How is it that the ENTIRE Claude Code system prompt fits into just 9.4k tokens, but your typical SaaS MCP (Sentry, GitHub, etc.) somehow uses 30k tokens??
Is it that Anthropic's engineers are just that good, or do MCP engineers not prioritize efficient prompt engineering?
61
I vibe-coded a menulet that helps you track your Claude Code token usage: github.com/RISCfuture/Claudeβ¦
Man, there is no better feeling than preflighting the plane for a sunset joyride, while your inbox fills up with emails of GitHub CI failures because Claude is rage-committing trying to fix your broken pipeline. That used to be me, my AI friend. That used to be me.
1
42





