That's exactly what happens. The algo does not judge how hurtful a rabbithole may be - it optimizes for engagement with some moderation sprinkled on top. I've tried to make my facebook feed palatable for a couple months and eventually passed up on trying. I'd rather IM my family about cat photos than engage with their fringe political views. Same goes for colleagues on LinkedIn.
Is this true? I'm getting a feeling that most of this is adding external stucture when coding agents already provide a framework for it.
I've had moderate success in throwing a braindump at the llm, asking it to do a .md with a plan and then going with the implementation for it. Specialized thinking prompts seem like overkill (or dumbo-level coding skills are enough for me).
Failed to load module script: Expected a JavaScript module script but the server responded with a MIME type of "text/html". Strict MIME type checking is enforced for module scripts per HTML spec.
Ad infinitum for a list of a couple .js files with repeating names.
Guess we'll have to come back in a day or two to experience it in it's full glory :).
Hey, thanks for reporting - this is fixed now. I messed up the static build and some browsers freaked out. By law of showing things publicly, I of course only tested in a browser that didn't. Hope you can give it another chance!
Banks like that exist. mBank from Poland does in-app approve/reject - similar to what you get on an Android phone when you try logging in on a new PC.
They also send phishing warnings when they find active campaigns.
That said, plain old social engineering works well on people. Last week one small-scale influencer fell victim to a bank transfer scam. Got phoned by a bank person telling her that her account is targeted by hackers, then a cybersec police head phoned her and asked to transfer her savings to a 'secure account'.
This is an issue with CSV numerical values stored as strings, for numbers it's a bit better. Libraries sometimes allow for a raw import that preserves the internal data type of the format, then you get proper numbers, not adjusted to locale formats.
If you do it for excel it even handles dates pretty well because they're in a numerical format and you can infer that a column is filled with dates because of the range.
The pre-internet conclusion is right. They try to keep backwards compatibility. Also, Excel doesn't handle big data well (1-2M rows) and neither do import libraries (at least in JS land).
There was an AMA with Emad yesterday on discord. He got asked this. The promise is that 1.5 will be released in the following week.
The slowdown has numerous issues. They got legal threats, death threats, and threats from some congresswoman to have them banned by the NSA (1).
Stability.ai workers (except for one) have a clause that they can open-source anything they're working on. They do and supposedly will open-source everything because they want to do a ecosystem, not a cash grab in the model of DALL-E.
Also they don't have one central place for all their projects and will scale from 100 to 250 employees in the following year so things should speed up.
Or so you may think. Working with diffs / merge conflicts already exposes you to internals. Knowing that committing big binary blobs is a bad idea also could be categorized as "knowing internals". Knowing why LF/CRLF leads to conflicts (without setting .gitattributes) also is knowing git internals.
Tentacrul did a good video on it and more across the years https://m.youtube.com/watch?v=MPyJBJTHyO0&pp=ygUWZmFjZWJvb2s...