szundi

16 years ago it was

Snow Leopard was a nothing release basically - but under the hood a lot got fixed and got better for devs

Trick is to use the newest distro release with previous cycle hardware

Lots of people are working on repetitive simple projects like the Nth website whatever or things like that, boring stuff. This LLM era is already a very big deal for these people.

Personally somehow I am working on stuff that has like 25% not trivial stuff and that is enough to have the same experience as you have.

But also lots of people just don't care about quality and they might be right with their customers/audience. In these cases when someone catches one, an agent is going to iterate on it and make it (seemingly) go away, bandage applied, who cares again. This has a market, I am sure. Lots of programmer folks are just as bad.

I don’t know what people are doing but Minimax produced 16 bugreports which of 15 was false positives (literally a mistake).

In contrast ChatGPT 5.3 and also Opus has a 90% rate at least on this same project. (Embedded)

All other tests were the same. What are you doing with these models?

Seeing the SOTA in FSD techs it is not obvious that Musk made a miscalc so far.

It would have helped if you tell us why you don’t like this approach.

If you go mainstream with your requirements, you don’t step on these though

Those good ones are not even close though - or are they

It is actually quite hard to copywrite if you’re doing a good job.

Also firing people for a minimal bonus is always a lot of people are going to go for

History failed on this one badly

What really matters though is the quality of the human review.

In this case buy the gift card from some shady retailer with a one-time-use virtual card, and give this shady code to your friend. Or buy a physical card from aliexpress, the cheapest one with bad reviews.

Diversion for your whole next week: just generate machine code binary for this

Like it means AI cannot be even worse

If that would be so simple

Exactly, I remember how it was renamed just before "launch" to JavaScript from something else I don't remember

This is not the point though

Hopefully it’s love of cars and your woman.

He or she meant 75% US people. But not everyone. Just the upper ones, who don’t have mortgages but lending the money to people - now on higher rates haha

Yes … while hoping no one ever finds out

I like using emdesh and now i have to stop because this became a meme

How nice when just hung up with a demanding stakeholder who knows you can deliver a lot “instantly” you switch to your phone and your “agents” are just stuck into some weird stuff that they cannot debug.

That must be a nice situ on the beach.

According to your experience with this model, is it just trained for the benchmark or these points are actually representing the performance?

Parent commenter presents perfect arguments to show this opinion or whatever it is is based on questionable grounds

Golden age was a time when basic tinkering could bring you to groundbraking discovery. This is of course over now.

This is what makes Java underrated these years. Some annoying stuff pays off over a decade several times. You can make insane complexity with ease.

Linux detects all your hardware and use drivers accordingly at every boot - some seconds

Funnily if you routinely ask them wether their answer is right, they fix it or tell you they hallucinated

Your experience suggest that monoliths on Postgres might be key to win on the market.