@riscfuture profile picture
Tim Morgan πŸ™ƒπŸŒ― @riscfuture

Software engineer, commercial pilot, CFI. Thoughts are NOT my own; my employer has an alpha wave generator that injects opinions and tweets into my brain.

Joined April 2007
  • Tweets 6,614
  • Following 232
  • Followers 674
732 Photos and videos
If it hasn’t already been done, I am coining the term β€œtrad-coding” to mean the opposite of vibe-coding.
30
In the future, all performance reviews will just be reading what Claude stores about you in user_memory.md.
41
Lol, Anthropic registered β€œclaude.md” as a domain. Clever.
43
I’m sorry, but you’re just a regular prompt writer, and this company needs 10Γ— prompt writers.
2
38
A company I know just got β€œapproved” to use AI after a β€œsecurity review.” 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 don’t, we’d be out-competed by everyone else who does.
2
96
These AI companies should probably stop calling it β€œThinking Mode” or whatever, since in reality, it’s still an LLM, and no thinking is actually happening.
41
It’s so quaint, these old time travel shows where they say not to touch anything in the past because β€œthe timeline might be affected,” 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.
44
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?
60
I vibe-coded a menulet that helps you track your Claude Code token usage: github.com/RISCfuture/Claude…
1
1
200
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
41
Due to the overproliferation of icons, people using screen readers may actually have a better browsing experience. They get β€œRemove 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.
36
Cursor is like the perfect example of how VCs WAY over-indexed on AI startups. 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 they’re up against a completely saturated AI coding market
84
Who else here is on Team #bypasspermissionsalways?
1
52
All these CEOs announcing eng layoffs β€œbecause AI makes my engineers more productive” is highly 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?
1
64
We all know the saying β€œreduce, 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: β€œrecover, resume, retry.” Also in priority order.
1
46
Does the whole β€œYou 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?
1
61
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!
1
58
Software engineer furiously typing, 2008: β€œWow, a monster 10x coder!” Software engineer furiously typing, 2025: β€œWow, a dinosaur who still uses an ancient IDE!” Real engineers go <TAB>, <TAB>, <TAB>, <TAB>, … now
1
86
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 β€œDaisy”. Here's a stock photo of a smiling woman for its avatar.
94
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.
1
87
Load more