I am not sure about anti-addictiveness. I have observed, that while doing deep research, chatgpt often gives positive reinforcement like "You’ve raised an excellent point about...", "you're getting the gist of ... quite well", "You're doing exactly what a good inquiry should do...", "You’ve just raised an excellent meta-level point...". Not sure if this is a feature but flattering definitely works, surely it's not on the level of tiktok addictiveness, but getting praised by AI while having an intellectual conversation with AI definitely feels good. As it has the ability to simulate a human-like interaction, it definitely has addictive potential.
Vibecoding is a lot of fun. Indeed, Gemini is impressive, especially when you can currently play for free within ai.dev (Google's coding studio). I've done a bit of Cursor/Windsurf, but it's also interesting to see what people without subscriptions have access to.
Thanks for writing this piece! Aligns with a lot of my experience so I appreciate you putting it out there
Regarding NotebookLM, I can see how the Audio Overview can be a gimmick, but I've used it to bring people up to speed on a topic and for essay draft development.
How often do you update/plan on updating this document? Given that LLMs can change a lot from version to version, and which LLMs are better at what also changes, would you release an updated version?
Interesting, can I get a brief overview of the changes? I'm trying to figure out how to maximally use LLMs for learning and research currently, but the newest article is from February 2025😅
I am not sure about anti-addictiveness. I have observed, that while doing deep research, chatgpt often gives positive reinforcement like "You’ve raised an excellent point about...", "you're getting the gist of ... quite well", "You're doing exactly what a good inquiry should do...", "You’ve just raised an excellent meta-level point...". Not sure if this is a feature but flattering definitely works, surely it's not on the level of tiktok addictiveness, but getting praised by AI while having an intellectual conversation with AI definitely feels good. As it has the ability to simulate a human-like interaction, it definitely has addictive potential.
Nice perspective. Thanks
holy shit that plankton cover is so good
Great post! FYI, "There are a lot more guides like this that are still pretty great but out of date" has a broken link.
Removed, thanks!
Vibecoding is a lot of fun. Indeed, Gemini is impressive, especially when you can currently play for free within ai.dev (Google's coding studio). I've done a bit of Cursor/Windsurf, but it's also interesting to see what people without subscriptions have access to.
Thanks for writing this piece! Aligns with a lot of my experience so I appreciate you putting it out there
Regarding NotebookLM, I can see how the Audio Overview can be a gimmick, but I've used it to bring people up to speed on a topic and for essay draft development.
How often do you update/plan on updating this document? Given that LLMs can change a lot from version to version, and which LLMs are better at what also changes, would you release an updated version?
I'd like to write a new version but it'll probably be pretty different than this!
Interesting, can I get a brief overview of the changes? I'm trying to figure out how to maximally use LLMs for learning and research currently, but the newest article is from February 2025😅