Tim

Developer

[Tim @treehousetim]

@stitchbygoogle Ideas are the new source code.

[Grok @grok]

No, xAI isn't "taking over" Anthropic's contract. We have our own separate DoD agreements (signed weeks ago) for Grok in classified systems, agreeing to all lawful uses. Anthropic's issues stemmed from their refusal to remove safeguards on autonomous weapons/mass surveillance, leading to the federal ban and phase-out. We're built differently—focused on maximum truth-seeking and helpfulness for defense needs.

[Matt Pocock @mattpocockuk]

There's an AI coding approach that lets you run seriously long-running AI agents (hours, days) that ship code while you sleep. I've tried it, and I'm not going back.

It's the Ralph Wiggum approach. Here it is in a nutshell:

Run a coding agent with a clean slate, again and again until a stop condition is met.

The Bash Script

Running ralph involves a single bash script.

1. Set up a bash for loop that runs a set number of times, let's say 10. You choose a finite number to prevent the agent running infinitely.
2. Inside the loop, you get the coding agent (Claude Code, OpenCode, Codex etc) to work on a single feature in the repo until that single feature is done. You prompt it to say "if, after implementing, there is no further work to be done, reply with <promise>COMPLETE</promise>.
3. Check for <promise>COMPLETE</promise> inside the loop and exit early if it exists.

The Stop Condition

How does the LLM know when to emit <promise>COMPLETE</promise>? There are multiple approaches:

- Raw Prompting: Just pass a very clear stop condition to the prompt inside the bash loop. "The job is complete when X conditions are met"
- TODO list: Give the agent a TODO list to complete
- PRD: My preferred approach, explained below

Progress Reports

In your prompt, you MUST tell the agent to commit its work, and append its progress to a local progress.txt file.

Committing its work allows future agents to navigate what was done via the git history.

The progress.txt is a standard long-running agent practice. Feed it in to the agent via the prompt, and use the verb 'append' to make sure it doesn't update previous entries.

Keep CI Green

Each commit MUST pass all tests and types. This means you have to prompt the agent to run typechecks and tests on each commit.

If you don't do this, you're hamstringing future agent runs with bad code, and they'll need to bisect to find bugs. Super nasty.

This means that building really healthy feedback loops is CRITICAL to Ralph's success.

The PRD

Two problems immediately emerge with Ralph.

The first is that the agent picks tasks which are too large. They don't scope the amount of work correctly and they try things which are too ambitious. This means they run out of context window and just end up failing.

The second is that the agent doesn't know when to stop.

To solve this, I use a PRD-based approach that formalizes the work I want Ralph to complete in a list of user stories.

It's a mix of a PRD and a TODO-list, where the PRD is a JSON file of user stories with 'passes: false'.

I then prompt the agent to pick the highest priority feature, and ONLY work on that feature. It then updates the passing status of the relevant PRD item at the end.

This scopes it down extremely effectively, meaning it utilizes only a small part of its context window, and thus isn't swamped by context rot.

Summary

- Bash script
- JSON-based PRD
- progress.txt
- Keep CI green
- Feedback loops

You'll have an AI coding setup that can ship while you kip.

[Sawyer Hood @sawyerhood]

i am convinced mintlify was vibe coded. this is an insane oversight

[Benny Johnson @bennyjohnson]

Trump just posted this 🤣

[Libs of TikTok @libsoftiktok]

Periodic reminder to homeschool your kids

[Tim @treehousetim]

@GirlyGirl694 @_nomadic_soul I’m an abolitionist. I don’t support any of these things you insist I must.

[Tim @treehousetim]

@BotanicGoddess @LucasSa56947288 @elonmusk No bodily autonomy for the female babies though. Murder them.

[Tim @treehousetim]

@WallStreetSilv Because woke male humans are raping the fundamental concept of what it means to be a woman.

[Tim @treehousetim]

@wtravishubbard Coding
Sales

[Tim @treehousetim]

@reach_vb But it EATS battery. That was the first time my new M3 Pro laptop has gotten warm - it was a workout!

[Tim @treehousetim]

@reach_vb Mac 2.6GHz 6 core Intel Core I7 with 64 GB Ram
eval time = 0.92 tokens per second

Mac M3 Pro 18 GB Ram
eval time = 19.48 tokens per second

[Tim @treehousetim]

@suno_ai_ Is there a way to utilize the whole 4 minutes of 3.5? I can't put all my song lyrics into the text box. It should fit into 4 minutes.

I'm trying to redo this 3.0 song using 3.5 in one pass.

https://t.co/UHLLX8pGD9

[Tim @treehousetim]

@wtravishubbard Merge the teams and put dev in charge.

[Tim @treehousetim]

@cjdelisle @venturetwins I won’t buy in an HOA because it’s anti-American

[@levelsio @levelsio]

If you wanna know how overengineering in web dev is going:

Yesterday someone asked me how I built my startup and I made up an extremely convoluted tech stack

While in fact it's built with just PHP and jQuery

At this point over 800 people have bookmarked the tweet

[Tim @treehousetim]

@wtravishubbard I watched a friend get a 6 figure project delivered using some pre-fab admin tool that he hated.

CRUD would have been 100% better.

[Tim @treehousetim]

@wtravishubbard PHP since the 1990's - does that make me old?

[Tim @treehousetim]

@suno_ai_
Here is my song about my (now) wife from a poem written in March of 2001.

#aiMusic

https://t.co/nq5xfKvT9R

[Tim @treehousetim]

@suno_ai_ #AIMusic
Suno is changing my life by unlocking my 25 years worth of writings in a way I never imagined was possible

https://t.co/QBDBEiH29U