site banner
PaperclipPerfector  3d ago (text post)   2427 thread views

Small-Scale Question Sunday for July 26, 2026

Do you have a dumb question that you're kind of embarrassed to ask in the main thread? Is there something you're just not sure about?

This is your opportunity to ask questions. No question too simple or too silly.

Culture war topics are accepted, and proposals for a better intro post are appreciated.

1
Top Bottom Old Controversial Comments
Jump in the discussion.

No email address required.

Does anyone have a good resource (or set of resources) for getting started using AI in coding that emphasizes building understanding? I've pretty much eschewed AI to this point, but it seems it's only getting more integrated and capable, so I might as well develop the skill. My experience is mostly in python in a data science context, with a little bit of C and the rare instances of assembly thrown in to run isolated or low-bandwidth sensors with extremely limited onboard compute. I have generally preferred VSCode, so bonus points if the resource integrates it.

I think the best guide for me is going to read something like, "A harness performs functions X, Y, and Z. Let's walk through setting up a basic harness so you can develop intuitions around what it's doing and how you might modify an existing harness to suit your future needs." Conversely, a terrible guide for me might read, "Download (someone else's) harness from (website); it's the best one for coding (no explanation as to why). Point your IDE at it and start typing your prompt (no elaboration on what makes a useful or effective prompt)."

My best understanding (which may be out of date) is that you'd be best served by subscribing to the $100-per-month Claude, opening it up, and asking it pretty much exactly what you just asked us. Any time you get to a step you don't understand how to perform, say, "I don't understand what this means, can you break it down more simply for me?"

In other words, I think the resource you're looking for is Claude. That's it. That's the whole list. Though probably you could do it with ChatGPT, too--I just haven't had much luck getting it to seriously drop both the sycophancy and the verbosity to focus on results. Claude seems better geared toward actual production of results.

I have tried similar things with lesser models, with worse (often, unusable) results. It will be interesting to see whether we are converging toward a single "roughly the best LLM we can create" that will eventually be baked into a chip and put in everyone's devices, and how that might impact the AI market landscape. I have a hard time shelling out even $20 per month for LLMs because I so rarely have any use for them, but in those instances where I have had a use, the most expensive models have been actually useful in ways that no other models seem to be.

What does the $100/month subscription get you that you couldn't get from paying for tokens on openrouter.ai or the like? Just wondering

Openrouter tokens are much more expensive.

For heavy use you might be right. I've never gotten close to spending $100 per month on openrouter though.

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