tomjen3

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.

That, and the ability to push an update without human interaction.

I would have said no on Rap before Hamilton. I would like to know your goto for Jazz.

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.

Even Azures native queue systems can guarantee that, because it gets hard to scale. You can only have one processor for any given queue, because otherwise one might take so long to process a message that others have finished processing others in the meantime.

But given OPs need for at-most-once, this doesn't really seem to matter in the first place.

Makes sense. I have seen far too many coworkers dismiss AI completely without trying it for their job.

At this point, you need to learn what AI can and cannot do, for the same reason you need to keep up with new versions of whatever framework you use. Since AI develops so fast (e.g many image use cases that AI would be terrible at 4 months ago, they now do perfectly), you need to repeat that exercise frequently.

There are 4 problems with adoptions as I see them:

1) Hype. Some people overhype what AI can do, which causes people to dismiss them when they don't immediately work;

2) Plenty of people don't like to change what they do/feel threatened by change. Doubly so when that change is perceived (real or not) to impact their job.

3) AI is weird and so it sometimes fails spectacularly at simple things, while it works very well at more complex things;

4) People use ChatGPTs free model or other AIs that are free. These are older/less powerful models, which means people end up with wrong expectations of what they can and cannot do.

5) Who likes to be told what to do? Especially by a clueless boss.

Where I running a company, I would ensure that my employees had access to a top of the line model and cursor/windsurf. I would monitor usage and have a talk with those whose usage was drastically lower than their peers.

However it would be a talk only - with the aim of figuring out why AI did not work for that employee, and what we could do to fix it.

I have a deep hatred of Go for all the things it doesn't have, including a usable type system (if I cannot write SomeClass<T where T extends HorsePlay> or similiar, the type system is not usable for me).

For NodeJS development, you would typically write it in Typescript - which has a very good type system.

Personally I have also written serverside C# code, which is a very nice experience these days. C# is a big language these days though.

Why do you believe that there is such a thing as objective morality?

Good. Plastics are one of those technologies that have been maligned incorrectly and now we cannot be reasonable about it.

We are not even looking at e.g removing plastics from the ocean, because that would force us to come to terms with the inconvinient truth that most of the plastic is from a few rivers in poor areas (basically it is been used as a self emptying trash system) and used up fishing nets.

There are solutions for these problems, but the ones like banning plastic straws simply do not address this problem.

The industrial revolution took something like 98% of jobs and farms and just disappeared them.

Could you a priori in 1800 have predicted the existence of graphics artists? Street sweepers? People who drive school buses? The whole infrastructure around trains? Sewage maintainers? Librarians? Movie stuntmen? Sound Engineers? Truck drivers?

The problem is that it leaves nothing for those who cannot afford to pay for the full cost of therapy.

Local Library?

That is probably still good advice for most companies. Joe's roof fixing business may be the best roof fixing business in 3 states, but would you want them to run their own server for their website, email, and booking?

Anyone who is on this forum is capable of building their own stuff, and running their own server, but that is not most people.

If HN had been around in 1997, would you have considered it odd if 13 out of 30 submissions were about the internet?

AI, even if hated here, is the newest tech and the fastest growing one. It would be extremely weird if it didn't show up massively on a tech forum.

If anything, this community is sleeping on Genie 3.

That is an extreme claim, what is your source for this?

iPhones comes to mind - except for a small group, most people no longer care. They used to stand in lines for the midnight release.

But the granddaddy for your question would be the Polio vax.

Thats not at all what he said.

All countries pay for their militaries. Russia invaded Ukraine and is actively comitting genocide.

There is a difference.

My credit card company will reject the transfer, and the company won't create the stickers in the first place.

I am not sure I see most of this as a problem. For an agent you would want to write some longer instructions than just "book me an aniversery dinner with my wife".

You would want to write a couple paragraphs outlining what you were hoping to get (maybe the waterfront view was the important thing? Maybe the specific place?)

As for booking a babysitter - if you don't already have a specific person in mind (I don't have kids), then that is likely a separate search. If you do, then their availability is a limiting factor, in just the same way your calendar was and no one, not you, not an agent, not a secretary, can confirm the restaurant unless/until you hear back from them.

As an inspiration for the query, here is one I used with Chat GPT earlier:

>I live in <redacted>. I need a place to get a good quality haircut close to where I live. Its important that the place has opening hours outside my 8:00 to 16:00 mon-fri job and good reviews. > >I am not sensitive to the price. Go online and find places near my home. Find recent reviews and list the places, their names, a summary of the reviews and their opening hours. > >Thank you

Based on the live stream, so does OpenAI.

But of course humans makes a multitude of mistakes too.

There are strangers I would like to talk to. It is just that most strangers are not someone I would like to talk to - if I wanted to talk to somebody I could just remove my airpods.

This isn't part of the social conditioning, it is because most people are not very interesting.

The part about the airpods is something that is going to change very soon: now that they are officially approved as hearing aids, asking someone to remove them, or even creating the expectation that one does will get you into Ada territory.

>One day, he proposed proving a special, much simpler case of the conjecture as a homework assignment. As an optional part, he included the original conjecture

There is a lesson there: always give people an opportunity to excel, if you can.

Most of them were so shit in the first place. Click bait and listicle upon listicle.

You are just not listening to the right places.

fly.pieter.com made a fortune while he live vide coded it on Twitter. One made making a modern multiplayer game.

Or Michael Luo, who got a legal notice after making a much cheaper app that did the same as docusign https://analyticsindiamag.com/ai-news-updates/vibe-coder-get...

There are others, but if you have found a gold mine, why would you inform the world?

You can get any old thinkpad, remove the WiFi module and then you have the full choice of any writing app you want to use.

Thats exactly why I think it is such a good idea.

Tv tropes seems an undervalued platform for "finding media that engages with a specific idea", however the downside is that once it starts to get used for that purpose, someone will learn how to use it to push their content and then it will be worthless.

For curation to work, you have to trust the currator.