nomadygnt

He didn't make the opposite claim. You are the one that made the claim, meaning you have the burden of supporting it. If there are no studies then no credible claim can reasonably made.

I'm not sure about "forbidden" per se but they definitely make accommodations for various things, e.g. riding as passengers in cars for long trips.

I agree to a point. But it should be regulated as what it is, which is gambling. Prediction markets doing everything in their power to avoid regulation is just scummy.

I agree with you. It is definitely what the PhD student signed up for. But like I said in a sibling reply I think if we are worried about having fewer grad students (not saying that we should be), then we may need to change the incentive structure surrounding the PhD programs to make it more worthwhile for people to invest the time and energy. Because how it is currently going it seems to me like fewer and fewer people are going to consider it worth the investment just for the credential alone.

Yes, but I think as time goes on, fewer and fewer people are going to consider those letters next to their name worth it for the years that they need to invest. So, I am just saying that if MIT or whoever else is worried about having fewer grad students (not saying that they/we should be), then maybe it's time to change how it works.

Taking a longer time to graduate to become the “world expert” in their field is fine if grad students weren’t paid next to nothing for the 60+ hours a week that they are expected to work. As it is now it’s better to finish as quickly as possible so they can have a real life.

This is true, but who do you think knows better what to ask, or has better taste with regards to the open source project? The maintainer? Or the guy shooting a drive by LLM PR? I agree though that it still takes time and effort to make good code contributions with LLMs, but probably less time for the maintainer to do it than for a maintainer to review lots of bad LLM PRs to get the good ones.

I think it is more referring to the quality of craftsmanship of the violin compared to other violins. You can’t make a whole orchestra of Stradivarius violins and their equivalents for other instruments (though what the Stradivarius equivalent is for timpani I couldn’t tell you :)

If an OpenAI model helped someone create a cancer cure I guarantee that they would try to profit as much as possible from that fact. They have even talked in the past about having partial ownership over discoveries made with AI be part of the license. They would be all over that.

I agree with that last part but the people watching the athlete are definitely the customer. The athlete gets paid because people watch them on tv (and in person). If no one watched them on tv, then they quite literally would not get paid. Their employer is selling their talent and abilities (the product) to the watchers (the customers). The watchers are literally paying the athlete and the athletes employer, if not through subscriptions or tickets, then just by watching the ads on tv.

I see what you mean, but the problem is that the LLM provider is trying to provide all the value from the book to the user without the user needing to look at the book at all. I agree if the LLM fails to do so then there is a market for the book. But the LLM provider is trying to minimize that as much as possible. And if the LLM succeeds at providing all the value of the book to the user, without providing any value to the book creator, then in the future there is no incentive to create the book at all, at which point the LLM has no value to provide, etc etc etc.

Maybe I am wrong about this but I think a lot of recent research has shown that trial and error is a great way to learn almost everything. Even just making an educated guess, even if it is completely wrong, before learning something makes it much more likely that you remember and understand the thing that you learn. It’s a painful and time-consuming way to learn. But very effective.

Maybe Linux commands is a little different but I kinda doubt it. Errors and feedback are the way to learn, as long as you can endure the pain of getting to the correct result.

Honestly with how good OpenCode is, this really just makes GitHub copilot the best subscription for the average user. It’s the cheapest. It’s free for students. You get access to all of OpenAI models AND Anthropic models AND Gemini models and you still have a pretty dang good CLI/TUI (OC, not Copilot CLI). And the limits are pretty reasonable. I’ve never hit the limits in a month though admittedly I am not a “five agents at once” kind of vibe coder.

This is fun! I thought I did pretty good with 123.

I found a path from Books to Rainbow with 123 generated topics! Books → Johannes Gutenberg (people) Johannes Gutenberg → Printing press (broader) Printing press → Sedition (evil) Sedition → Peaceful protest (good) Peaceful protest → Social movement (similar) Social movement → Black Lives Matter (places) Black Lives Matter → Alicia Garza (people) Alicia Garza → Reproductive rights (similar) Reproductive rights → Feminism (broader) Feminism → Women's studies (similar) Women's studies → Gender studies (similar) Gender studies → Queer Studies (deeper) Queer Studies → LGBTQIA Studies (similar) LGBTQIA Studies → LGBTQIA History (good) LGBTQIA History → LGBTQ movements (broader) LGBTQ movements → Galden LGBTQ Center (places) Galden LGBTQ Center → LGBTQ community organizations (similar) LGBTQ community organizations → LGBTQ advocacy groups (similar) LGBTQ advocacy groups → GLAAD (places) GLAAD → Gay rights movement (broader) Gay rights movement → LGBTQ rights movement (deeper) LGBTQ rights movement → Pride flag (deeper) Pride flag → Rainbow flag (similar).

Try it yourself at www.llmgame.ai

Another cool tool that’s being developed for rust is verus. It’s not the same as Kani and is more of a fork of the rust compiler but it lets you do some cool verification proofs combined with the z3 SMT solver. It’s really a cool system for verified programs.

Where do you work that you get to write Lean? That sounds awesome!

This seems really interesting to me as I don’t often work in domains that require me to know a lot of facts, but I still feel like SRS could be useful. I just don’t quite know how to use it. Could you give me an example of what you mean here? What kind of decisions do you find meaningful to periodically reflect on?

This is cool! I love this kind of simulation GPU programming stuff. Reminds me of this awesome talk from Peter Whidden: https://youtu.be/Hju0H3NHxVI?si=V_UZugPSL9a8eHEM

Not as technicial but similarly cool.

Which really makes you wonder how well the system is really working. Of course I don’t know this but I feel like if you asked everyone, the majority of people would say that 95, or 90, or 85 is too old to be in congress. But somehow they keep getting reelected…

In my mind reading is more similar to thinking than watching. I have no basis for this but it just feels more mentally active. Of course it could just be my biases but I feel it is much easier to passively watch or listen to something rather than to read. But also I would say from my own experience writing and speaking promote “neurological health” even more so maybe the method of consumption is not as important as long as there is sufficient synthesis and thought on the other end.

Monopolies are anti-competitive. Without competition there is no incentive for innovation, lowering prices, not price-gouging etc. Is a 10x better product really 10x better if it is also 10x more expensive and there is no alternative?

Yes! Whenever people say that we should have one timezone I always bring this up. Either you have to look up what time it is in another country or you have to look up what time of day it is. Either way you still have to look it up.

This was a great interview. I’m a big fan of Neal and Neal.fun

In elixir -> phoenix, python -> django, php -> laravel.

Any other ones are gonna be a little niche but from what I can tell these four (with rails) have the most large and active communities atm.