Tim Morgan
banner
riscfuture.bsky.social
Tim Morgan
@riscfuture.bsky.social
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 20k-30k tokens?? Is it that Anthropic's engineers are that good, or do MCP engineers not understand/prioritize the importance of efficient prompt engineering?
December 8, 2025 at 9:12 PM
I vibe-coded a menulet that helps you track your Claude Code token usage: github.com/RISCfuture/C...
December 4, 2025 at 6:10 PM
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.
November 24, 2025 at 1:06 AM
This describes 100% of my personal projects. It’s the reason I haven’t turned any of them into a huge success.
November 17, 2025 at 2:19 AM
Due to the overproliferation of icons, people using screen readers may actually have a better browsing experience. They get “Remove attachments over 20MB” while we have to stare at an icon of a paperclip with an inset bomb and anvil, trying to figure out what that means.
October 31, 2025 at 5:01 PM
Cursor is the perfect example of how VCs WAY over-indexed on AI startups. When it first started, it seemed like a slam-dunk unicorn, raising almost $1B on $10B … but now that the industry has matured, it’s obvious that there's no moat and Cursor is up against a completely saturated AI coding market.
October 7, 2025 at 7:09 PM
Who else here is on Team #bypasspermissionsalways?
September 9, 2025 at 8:30 PM
All these CEOs announcing eng layoffs “because AI makes my engineers more productive” is
sus. If your engineers are more productive now, why are you doing the same with less? Why aren’t you being more ambitious and doing more?
September 3, 2025 at 6:28 AM
We all know the saying “reduce, reuse recycle”. It’s three ways to avoid generating extra waste, in priority order. I’ve invented a similar saying for writing fault-tolerant systems: “recover, resume, retry.” Also in priority order.
August 26, 2025 at 8:26 PM
Does the whole “You are a helpful assistant who…” prompt preamble actually make a difference, or is it just cargo-culted industry wide from one engineer who wrote it one time at OpenAI?
July 16, 2025 at 5:36 PM
Huge libraries of 4000+ icons are a Bad Thing in modern UI design, not a good thing. Now websites and apps have little icons next to EVERY. THING. Not everything needs a cute little icon next to it! You don’t have to vomit little icons all over your UI!
June 10, 2025 at 3:45 AM
Typing a really long, perfect prompt into Cursor, going out for coffee, and then coming back to see it just had a follow up question is the equivalent of an EM assigning a bunch of work and then coming back from lunch to find the engineers all just playing ping pong. “We’re blocked on a question!”
May 30, 2025 at 1:47 AM
Software engineer furiously typing, 2008: “Wow, a monster 10x coder!”

Software engineer furiously typing, 2025: “Wow, a dinosaur who still uses an ancient IDE!”

Real engineers go <TAB>, <TAB>, <TAB>, <TAB>, … now
May 24, 2025 at 9:19 PM
Fun game to play at work: Meeting Roulette. At some point in every meeting, one person, chosen at random, has to turn their camera on.
May 19, 2025 at 3:54 PM
Startup idea: LLM chatbot naming as a service. You send us a description of your LLM, and we name it.

Input: Our LLM proactively engages with customers to drive them through our sales funnel

Output: Your LLM is named “Daisy”. Here's a stock photo of a smiling woman you can use for its avatar.
May 7, 2025 at 11:28 PM
Extra-spicy hot take: If you need to disallow your interview candidates from using ChatGPT during the technical interview, you’re probably asking a bad interview question.
April 15, 2025 at 2:49 PM
Thank you, Apple, for making this switch statement so easy and sensical!
April 4, 2025 at 9:49 PM
Unicode in variable names is pretty cool.
February 26, 2025 at 7:37 PM
Ok, we don’t call it “Security” anymore. All those old movies should be updated to have the rich guy yell “Trust & Safety!!” instead.
February 12, 2025 at 5:29 AM
Sigh, there was a time when I was actually good at this stuff…
December 18, 2024 at 10:00 PM