AI Agent Guidelines for CS336 at Stanford
1–10 of 176 posts
Re: AI Agent Guidelines for CS336 at Stanford
#2This is ridiculous. The genie is not going to go back into the bottle. This is the equivalent of "you wouldn't download a car". (Yes, we would.)
The solution is to scale the difficulty of the objective measures. Expect far more from students.
Reorient the university around physical laboratories and timesharing resources no single student could afford. It's already like this in many STEM disciplines.
More internships, more networking, more large projects. Less trivial tests of knowledge and credentialism.
Re: AI Agent Guidelines for CS336 at Stanford
#3I always wonder why there is such course. Using agent ai coding tool is trivial.
Re: AI Agent Guidelines for CS336 at Stanford
#4good intention but useless let's be real
Re: AI Agent Guidelines for CS336 at Stanford
#5This seems somewhat sensible to me - the genie _is_ out of the bottle, and students absolutely will use AI agents to finish assignments without learning a thing, but there is some value to showing how agents can be used as teaching tools and what healthy use _can_ look like
Re: AI Agent Guidelines for CS336 at Stanford
#6[dead]
Re: AI Agent Guidelines for CS336 at Stanford
#7This would be an interesting approach if the course supplied a custom Harness (perhaps in place of a textbook) and this was part of the instruction set inside of it. As a standalone thing you ask students to import into their agent, seems unlikely to work.
Re: AI Agent Guidelines for CS336 at Stanford
#8And, yes students are going to follow it....
Re: AI Agent Guidelines for CS336 at Stanford
#9> What AI Agents SHOULD NOT Do
> * Run bash commands
Students who prefer to use zsh keep winning.
Re: AI Agent Guidelines for CS336 at Stanford
#10Hah, I like that these are presented as a CLAUDE.md.
(They have the same content duplicated in an AGENTS.md as well - I really wish Anthropic would hurry up and teach Claude Code to check for that file too.)