If you work at OpenAI, leave now while you can.

Yes, it is different.

An AI actions and reasons through probabilistic methods - creating a lot more risk than a human with memory, emotions, and rationale thinking.

We can’t trust AI to do any sensitive work because they consistently f up. With & without malicious intent, whether it’s a fault of their attention mechanisms, reward hacking, instrumental convergence, etc all very different than what causes most human f ups.

I think a key ingredient here is accountabilty and liability.

If there's a mistake, you can't blame the computer. Who is the human accountable at the end of it all? If there's liability, who pays for it?

That's where defining clear boundaries helps you design for your risk profile.

Can you sue an ai agent?

It’s totally different. People have to obey laws and contracts because there are consequences if they don’t, there are fines, arbitrage, courts.

What happens if AI agent you run causes a lot of damage? The best you can do is to turn it off

Exactly, and I would never turn over my email or computer over to a contractor or anyone really. They get their own environment, email etc. Their actions stay as their actions.

My point is: Trust the work of AI just like the work of a contracter: Check and verify, but dont micromanage.

As others have said: accountability

I hardly use Google anymore. I almost always use Claude. It can do the "higher level task" I often want to accomplish when I go to google.

Claude checks multiples websites, reads them all, and answers my question.

This is quite a bad idea. You need to control the size and quality of your context by giving it one file that is optimized.

You don’t want to be burning tokens and large files will give diminishing returns as is mentioned in the Claude Code blog.

It is not an "idea" but something I've been doing for months and it works very well. YMMV. Yes, you should avoid large files and control the size and quality of your context.

Indeed seems like Vercel completely missed the point about agents.

In Claude Code you can invoke an agent when you want as a developer and it copies the file content as context in the prompt.

The BMW neue klasse is far superior to the latest Teslas.

Both in software hardware and handing.

https://youtu.be/P-H-GJaGiUg?si=eq8YWy8gyJ5YS99X

I think it even surpasses Chinese brands.

i think they look absolutely horrible both inside and out. but, of course, beauty is in the eye of the beholder.

They're indeed fuglier than fugly. I've had many BMWs but that BMX iX3 looks really bad. Don't know what they were smoking.

Wife's daily driver is a 4-series "Gran Coupé" (weird term to say it's got 4-doors and not two like the "coupé" but... "Gran" is not a french word: the french word would be "grand" so I think they somehow fucked up [1]) with the B48 ICE engine. Sweet car and really good looking.

But yeah: to each his own bad taste.

[1] not as bad as Audi and its "e-tron" where "etron", literally, means "turd" in french.

I think the (negative) point is the cost of ownership. European cars are very cool, if you can afford to keep them running

This is amazingly cool

Is open router used a lot? I just use claude code, so this is a misrepresentation of what is actually the most popular model right?

I dont like the "impure" label. But the guts of it is right. Most software solves a business problem. Even the "pure" ones could choose to deliver value sooner with tech debt.

Maybe "practical" engineering is a better label?

You could go for "pragmatic" but then it's taking sides :-) If instead of "pure" you use "purist" you completed the loop!

The main thing that lacks in go is auto OpenAOI generation from a golang func. You at least need reflection. It can be done. But not as easy as in python