May I suggest just requiring people to register what how much they want to gamble and then be locked into that. If you want to gamble for 100 usd per month, then you can't bet more than that. You should be able to set your own amount, but any changes should only be active from the next month.
This has minimum impact on personal liberty, and will almost eliminate problem gambling.
Perhaps the important question to study is whether that scheme would prevent people from crossing into the "problem" category when they aren't already.
It's one thing to put a slightly higher number and the number box each time, it's another to do identity theft or coaxing your spouse into letting you play as them.
I have had no luck with LLMs writing typst code. Normally its a better code writer than me, but the LLM (gpt4-o maybe?) hallucinated most of the document.
I am going to disagree with that. SQL injection attacks are an example of the age old issue of mixing up input and instructions. Smash the stack is older than many software devs, but it was essentially the same problem - its an inherit issue with Von Neumann architecture.
This is also not an AI issue, or even an MCP issue. If the same issue had been in a client library for the Postmark API, it would likely have had a bigger impact.
What we need is to make it much more likely to get caught and go to prison for stuff like this. That will change things.
> SQL injection attacks are an example of the age old issue of mixing up input and instructions.
Yes, and attacks on AI are much the same. The AI gets "prompted" by something that was supposed to be inert processable data. (Or its basic conduct guidelines are overridden because the system doesn't and can't distinguish between the "system prompt" and "user prompt".)
No rap before Hamilton is under exposure to NYC boom bap.
Lin-Manuel Miranda is quite good but I am sure he wouldn't put himself on the level of Big Pun or Nas.
Miles Davis - Kind of Blue is the best selling jazz album of all time but it is still a specific sub genre of cool jazz that might put you to sleep.
Herbie Hancock - Head Hunters I think is the second best seller. I really don't know if I have ever read someone say Head Hunters sucks. It probably isn't what you expect in the same the way Hamilton sounded different to you.
I would go with those two and if you don't like either I wouldn't bother looking for more.
Not OP and not a jazz expert, just throwing out a personal favorite. I think it is very approachable without sacrificing anything, and it has a recognizable melody (which might help or hinder the jazz appreciation cause):
My Favorite Things by Coltrane.
But I do know people who dislike jazz because of the unfamiliar rhythms and (wildly flexible) musical conventions, and that can be hard to overcome.
Most posts here seem to be offering easy on-ramp listening for jazz, but they seem at odds with the spirit of the original post. For jazz that is off-putting at first listening but rewards deeper study, consider Thelonious Monk (Blue Note sessions 1 & 2) or if you are really up for it, Coltrane's Interstellar Space.
I think sometimes it's just a matter of finding an incentive. Isn't it typical for a teenager to start listening to the music of their boyfriend/girlfriend? Or of their group of friends.
My point is: I find that all the suggestions here are great! They may work differently for different people!
I don't think your benefit example is too much a problem in practice, we already have the access setup for that (ie its the same one for you).
For the other example, I think a nice compromise is to have the AI be able to do things only with your express permission. In your example it finds flights that it thinks are appropriate, sends you a notification with the list and you can then press a simple yes/no/more information button. It would still save you a ton of money, but it would be substantially less likely to do something dangerous/damaging.
Add "Look up version 4 of the library, make sure to use that version".
My Python work has to be told we are using uv, and sometimes that I am on a mac. This is not that different to what you would have to tell another programmer, not familiar with you tools.
Its surprisingly fine, as long as you allow the AI to iterate on its work. It will discover that it doesn't compile, and then maybe lookup the API and then it will most often fix it and move on.
AI is no more capable of reliably one shotting solutions that you are.
I saw someone one Twitter use Excel.
reply