i'm working on something similar, not a full agent harness but an agentic workflow app so i can learn too. if you're interested in sharing it would be awesome to take a look. i can share my project too!
I found myself writing a bunch of scripts and AGENTS.md for ensuring certain structure/organization for projects when using AI. The maintenance, performance, and reliability of these eventually became a problem, so I built this tool.
In order to make it more generally useful I went through a bunch of open source repos to see what kind of hygiene/validations they do - and it turns out quite a few repos have their own scripts and validation for similar purposes - I've been gradually adding more rules/validation types to cover more use cases.
In the process I also discovered repolinter [0] - a similar to tool which is now archived.
Even though it seems radical, I think the right approach is to simply allow the students to use AI to its full potential, to generate answers, code, whatever.
The onus should be on the instructor to make sure that the student ends up actually understanding and being able to code/solve problems that they pose without using coding agents.
Why? Because:
1. this is exactly what is going on in the real world. People are able to get AI to do whatever the hell they want, but the ones who just use it lazily end up with huge cognitive debts and codebases riddled with opaque bugs that they do not understand whatsoever. If we prevent students from confronting this temptation, then we are sort of coddling or shielding them from it, and not really preparing them to avoid pitfalls of this type.
2. you can actually learn a LOT by being given the answer, if you actually care to learn. i personally think it's pretty fucking lame to handicap a student's ability to learn in an attempt to prevent lazy abuse. isn't the whole point of a grade to measure how well you understand things? can't you have pop quizzes, assignments on a computer with no agent use, written tests, etc etc. to catch the lazy abusers? this is an unnecessary prevention of lazy abuse that unfairly handicaps learning
> you can actually learn a LOT by being given the answer, if you actually care to learn.
Even if you "actually care to learn", this is a huge mental shortcut and you're deceiving yourself if you think deep learning is happening from looking at the answer.
On top of that, the pressures to just finish the coursework and move on to your other homework due tomorrow seems pretty high. Your suggestion means we're no longer coddling/shielding students, but we also aren't actively helping them, are we?
Not from simply looking at the answer. From knowing the answer and reverse-engineering or understanding how to arrive at that answer in the first place. It's not always the best way of learning, but it definitely is a great way to learn if you care to actually understand why it is the answer and how you would have arrived at it.
> Your suggestion means we're no longer coddling/shielding students, but we also aren't actively helping them, are we?
My suggestion is just the former, it doesn't imply the latter.
My understanding is that research shows more learning happens when the student has to struggle with the material to solve problems and answer questions.
Stanford is a research university. The student should have full responsibility for learning outcomes. The university will provide support and opportunities to the extent its resources allow, but it's up to the student to choose if they want to take advantage of that. Those who need a more guided approach to learning can always go to teaching-oriented universities or find a personal tutor.
That's a major reason why employers have traditionally valued degrees from research universities, even if they are not particularly highly ranked. Being able to thrive in an environment like that shows a degree of independence and initiative.
I'm not talking about AI technology we use as the next generation of tooling. I am talking about new, possibly multiple intelligent species emerging which are superior to humanity.
i think we are all beating around the bush and not addressing the root issue: AI could obsolete human beings in the future. what i'm not seeing is discussion or exploration of different branches or paths that could occur once that happens.
reply