"I'm sorry" is not gaslighting but an admission of fault it learned from our texts. And if an LLM managed to delete your database, it's time to slow down the vibe train and put up some guard rails.

LLMs are awesome but not without supervision.

Hard agree on the guard rails bit.

Would it be less sucky if an intern accidentally deleted the database? If not, take some steps to make sure no one can delete it without jumping through visible, noisy hoops.

Taalas showed that you could make LLMs faster by turning them into ASICs and get 10k+ token generation. It's a matter of time now.

Actually pretty interesting to think: in a few years you might buy a raspberry pi style computer board with an extra chip on it with one of these types of embodiment models and you can slap it in a rover or something.

For now. These will be pretty cool Linux machines if Asahi starts supporting them at some point.

It's going to take 3 years+ and it will be a 8GB RAM linux machine.

Still would be a good ssh terminal or presentation laptop.

I would not go below q8 if comparing to sonnet.

Yeah. Q2 in any model is just severely damaged, unfortunately. Wish it weren’t so.

>the city gets destroyed

vs.

>a company goes bankrupt or pivots

I can see a few differences.

My apartment has been here for years and will be here for many more. I don't love paying rent on it but it certainly does get maintained without my having to do anything. And the rest of the infrastructure of my life is similarly banal. I ride Muni, eat food from Trader Joe's, and so on. These things are not going away and they don't require me to rewire my brain constantly in order to make use of them. The city infrastructure isn't stealing my ability to do my work, it just fills in some gaps that genuinely cannot be filled when working alone and I can trust it to keep doing that basically forever.

At least with GitHub it's hard to hide when you get "no healthy upstream" on a git push.

I don't understand how you can ship a car without proper papers out of the country so easily. Maybe focus on that first?

What papers? You think we verify that the contents of every outbound container matches what it says on the manifest? We don't. It would be prohibitively expensive to scan every container. Even if we did, and found a car in a container, how would we know the documents provided aren't valid?

This is a really hard problem. If there's an easy solution in mind, feel free to suggest it.

It's not a hard problem. Shipping companies must know the content of each container by law.

Verify 1 container out of 20. When you catch a stolen car, fine the shipping company for not doing their job. Find employees who performed the forgery of documents and put them in prison. If the company doesn't keep records of which employee prepares which document, fine the company. And so on. Unfortunately police and customs would have to do their job in this case, I can see how they're upset.

So scanning every phone is easier ?

AI and blockchain?

I have no words.

I have no words that you think it is easier to scan every single conversation online, than to enforce proper border/customs checks for freight.

Agentic editing is really nice. If on VSCode, Cline works well with Ollama.

This would be true if not for open-weights (and even some open source) LLMs that exist today. Not everything should be done for profit.

I'm spending fair amount of money on helping teachers and professors in Serbia who had their pay reduced to to absurdity because they are supporting their students in demands for justice in the case of Novi Sad canopy collapse[0].

[0] https://en.m.wikipedia.org/wiki/Novi_Sad_railway_station_can...