lad

Yeah, when the same API endpoint sometimes return a string for an error, sometimes an object, and sometimes an array, JSON doesn’t help much in parsing the mess

Yeah, I’d say Russia is pretty chaotic at being evil

$40 is now too much for an old but working laptop? That’s crazy

Good point, I wonder if elasticity of demand will be affected by the AI bubble bursting (I expect there will be a recession and demand will get less elastic, bit I’m no economist)

Wrong country

So, ceo has 20× the average in their company, wow

You got the point, but non-profit that doesn’t usually exist on the brink of collapse or stops existing entirely

JS just implicitly does what

…it wants, also sometimes it’s far from what you want or even could expect

That’s clear, this is just a weird image

Also, I believe they don’t really need to have complete control for that, too

“Iranian Patriots, KEEP PROTESTING - TAKE OVER YOUR INSTITUTIONS!!!.. HELP IS ON ITS WAY,” Trump said in a post on Truth Social, without saying what that help might be

Why do I feel like this is bullshit

Censoring parts of gameplay as you play would be very impressive, btw. Not in a good way, but impressive, like when I first found out about ISP replacing/adding ads on http pages

I have A1 and A2 level in a couple of non-first languages, technically I can speak those, realistically I don’t and will not be able to communicate something more complex than ‘here, take a look’

So I don’t agree with your absolutistic stance

Yeah, I understand that this case doesn’t require a QA, but in the wild companies seem to increasingly think that developers are necessary (yet), but QA are surely not

It’s not even bad engineers, it’s just squeezing of productivity as dry as possible, as I see it

Yeah, if only QA vere not the first ‘replaced’ by AI 😠

I have a feeling that their test case is also a bit flawed. Trying to get index_value instead of index value is something I can imagine happening, and asking an LLM to ‘fix this but give no explanation’ is asking for a bad solution.

I think they are still correct in the assumption that output becomes worse, though

Reminds me a bit of how a prince inherited Spain from Franco. The prince in question dismantled the system and they created a democratic monarchy.

He also turned out to be corrupt and shitty, but at least he was not a ruler of the country, so I guess we can expect something good to happen, after all

You can transpile from C to Malbolge and then run it (this will probably take forever for most of C programs). I thought it can be used for obfuscation, and sure enough Wiki already states that:

Hisashi Iizawa et al. also proposed a guide for programming in Malbolge for the purpose of obfuscation for software protection

No thinking is not the same as no actions, we had bots in games for decades and that bots look like they act reasonably but there never was any thinking.

I feel like ‘a lot of agency’ is wrong as there is no agency, but it doesn’t mean that an LLM in a looped setup can’t arrive to these actions and perform them. It doesn’t require neither agency, nor thinking

It’s kinda good but also reads a bit like

sorry we got caught we never intended to

Yeah, didn’t think about that :( but I imagine the descriptions are still going to be fun, like ‘things don’t behave when I stop looking at them’