amitav1

I prefer OpenClaw because it's more persistent. I know, I know, theoretically you could do the same thing with Claude Code and markdown files (which, to be fair, is pretty much how OpenClaw works), I guess it's mostly the telegram interface I like. Most of the time I don't have my laptop with me, and ssh using Termux, and opening a remote claude code is a much greater hassle than sending a telegram message, and with telegram (or whatsapp or discord or whatever) you get the benefit of being able to send voice messages, which I find very useful. In what way is Clawdbot "insane"? Obviously if you give it write access to your email and twitter and whatnot, that's not great, but for me I really just give it access to that probably wouldn't ruin my life / career if they got out (e.g. my class notes and Anki decks).

I don't see why not, but I also have no experience in that sort of stuff, so take my endorsement with a grain of salt

By schedule my tasks throughout the day, I mean that it will figure out when I should do each thing, not that it does all of the things for me.

Personally, I use it to manage all of the stuff I don't want to. I give it my course content and it makes flashcards for me to review. I give it my tasks and it schedules them throughout the day. All of the menial stuff that is necessary but not productive. It also has a much better memory than I do on account of it's constant access to a filesystem and grep. It's like my personal assistant and tutor and guidance counsellor and sysadmin, all in one. I do think that a) you need to stick with it for a few days and b) use a good model. When I first started using it, it was just a worse version of ChatGPT, but after bringing in all of my data from ChatGPT it's a lot easier for it to search for stuff when it's confused. Now it can also do stuff like manage nginx or my sync serviceand whatnot, ~autonomously. Originally I was using locally running qwen models, but they were so timid as to be useless. Right now I'm using Kimi 2.5 as my model.

Because LLCs aren't people

Am I missing something? LaTeX is associated with slop now?

How would this work for independent researchers?

(no snark)

I can't think of anybody apart from Osama bin Laden who wouldn't want to play Candy Crush. \s

I guess the way one would verify that this is more general trend in academia would be to run this on accepted papers to a non-AI conference?

It was slow to load for me but loaded eventually.

I'm doing some research, and this is something I'm unsure of. I see that "suppressing null results" is a bad thing, and I sort of agree, but for me personally, a lot of the null results are just the result of my own incompetence and don't contain any novel insights.

I mean, to steelman their point, there's a lot more misinformation than information on Google. I still personally think that it's a worthwhile trade though

I believe so