site banner
ArjinFerman  Tinfoil Gigachad  5mo ago (text post)   562 thread views

Tinker Tuesday for June 24, 2025

This thread is for anyone working on personal projects to share their progress, and hold themselves somewhat accountable to a group of peers.

Post your project, your progress from last week, and what you hope to accomplish this week.

If you want to be pinged with a reminder asking about your project, let me know, and I'll harass you each week until you cancel the service

1
Top Bottom Old Controversial Comments
Jump in the discussion.

No email address required.

Starting a greenfield project to build a stable software environment for ai coding. I can't think freely when operating within legacy codebases. So starting from scratch to build my ideal ai-native scaffolding.

I'm starting with a tool to auto-redact pdfs. Simple, useful, well constrained. Would appreciate suggestions on software paradigms that have worked well for ai development.

Stack:

  • Python FastAPI backend + Streamlit Frontend + Sqlachemy ORM over rel-db
  • uv for packaging + environment
  • firebase for cloud provider + github actions for ci/cd
  • prefect (or something similar) for orchestration
  • Openai codex + github copilot as my LLM coding friends
  • Dockerized deployments

Some ideas:

  • Monolithic codebase to make it easy for agents to operate on it
  • Minimize implicit everything (state, side effects)
  • Maximize explicit everything (types for everything, explicit validators)

I have a basic demo ready. Codex is already raising PRs. The redacted bounding boxes are off. And the LLM redaction logic is wonky. But, so far I am impressed at the LLM's ability to build a greenfield project by itself.

I'm a serviceable software engineer. Cracked engineers of the motte, what are some software systems paradigms that you think I should play with ? I would especially like to know paradigms that make it easier for agents to understand, write & verify auto-generated code.

Haha, yep, tables and rich extraction is pretty bad out of the box.

In this case though, I can confidently say I'm an expert on PDF extraction for llm use.

I can confidently say I'm an expert on PDF extraction for llm use.

ANy tips and tricks you picked up regarding this not available out there on the web? I basically just throw the most powerful vision model at it and YOLO it.

Why not just use one of the many existing commercial solutions? That's what we did last I dealt with OCR'ing PDFs, just used Azure's API and then processed the data. Would be surprised if a raw vision model is cheaper or higher quality.

What is this place?

This website is a place for people who want to move past shady thinking and test their ideas in a court of people who don't all share the same biases. Our goal is to optimize for light, not heat; this is a group effort, and all commentators are asked to do their part.

The weekly Culture War threads host the most controversial topics and are the most visible aspect of The Motte. However, many other topics are appropriate here. We encourage people to post anything related to science, politics, or philosophy; if in doubt, post!

Check out The Vault for an archive of old quality posts. You are encouraged to crosspost these elsewhere.


Why are you called The Motte?

A motte is a stone keep on a raised earthwork common in early medieval fortifications. More pertinently, it's an element in a rhetorical move called a "Motte-and-Bailey", originally identified by philosopher Nicholas Shackel. It describes the tendency in discourse for people to move from a controversial but high value claim to a defensible but less exciting one upon any resistance to the former. He likens this to the medieval fortification, where a desirable land (the bailey) is abandoned when in danger for the more easily defended motte. In Shackel's words, "The Motte represents the defensible but undesired propositions to which one retreats when hard pressed."

On The Motte, always attempt to remain inside your defensible territory, even if you are not being pressed.


New post guidelines

If you're posting something that isn't related to the culture war, we encourage you to post a thread for it. A submission statement is highly appreciated, but isn't necessary for text posts or links to largely-text posts such as blogs or news articles; if we're unsure of the value of your post, we might remove it until you add a submission statement. A submission statement is required for non-text sources (videos, podcasts, images).

Culture war posts go in the culture war thread; all links must either include a submission statement or significant commentary. Bare links without those will be removed.

If in doubt, please post it!


Rules


Recommended Posts And Communities

Recommended Realtime Chats