FistfulOfHaws
Re:AI Agent Guidelines for CS336 at Stanford
on Monday June 01, 2026 @07:26PM (#48363917)
Learning mode has been a huge help for me, it quickly became my favorite way to learn. I ended up created a “Coaching Mode” output style that took some of the learning concepts like stubbing todos for the users and added other intructions that better fit how I learn
Re:AI Agent Guidelines for CS336 at Stanford
on Monday June 01, 2026 @07:19PM (#48363859)
I’ve done something similar for myself to learn Django. Claude Code has a built in Learning Mode, I extended that with a Coaching Mode. Where it is instructed on how to coach me, how to help stub out features, how to give feedback in code review, etc. With the main instruction being never to write code for me when in that mode. It can write basic logic examples/pseudo code and discuss different approaches to the problem. I have found it to be really effective, it is my go to for learning new things. I’m using it now to learn Elixir.
Re:LinkedIn Prevents You from Deplatforming
on Sunday January 04, 2026 @05:43PM (#46493150)
Similar thing happened to me. Randomly one of my LinkedIn posts got a ton of likes, so I figured I would look through the list of people who liked and try to figure out where they were coming from/if they would be interesting to reach out to.
After viewing a 100 or so profiles, I was logged out of LinkedIn and when I tried to log back in my account was suspended. I was in LinkedIn jail for like a week, and when I was finally able to login again I got the automatic tool warning and had to agree that I wouldn’t use one again (even though I never had used one).
Re:Show HN: Gemini Pro 3 hallucinates the HN front page 10 years from now
on Tuesday December 09, 2025 @05:48PM (#46211806)
This is super fun! I tried something similar a few months ago using: https://websim.com/
Had it do HN main feed, HN jobs and Product Hunt. It didn’t follow consistent styling but did generate articles and comments for each post. Some screenshots are in this post: https://world.hey.com/haws/the-ai-time-machine-7833669d
Re:Andrej Karpathy on X: NotebookLM is quite powerful and worth playin...
on Sunday September 29, 2024 @08:42PM (#41692266)
Nat Friedman estimated that if we stopped developing new models today, we’d have 5-10 years worth of innovation to tap into before we’d need more models.