tomberin

I was impressed with the Demo, ready to pay 10 and no option to sign up with email :(

This isn’t how any of this works. Manifests are built at boarding, visas work at entry. You are inventing problems to take the side of a corporation.

not tabloids, not a hoax, did you go on Twitter during that period? I have him blocked and saw his tweets

We can't comment on why, but there's no rational way to watch his behavior and assume he isn't obsessed with being liked. He constantly tweets about his own tweets performance, makes humiliating appearances on stages, and pretty much terrified that someone might do something 1/100000th as awful to him as he and his family have done to others.

he is isn't a CEO, he is a whining baby

It can't cite articles, if it told you it did and the link was gone that's because it was a hallucination.

There's a huge warning on the first page. This is a weird stance. Don't use it if you're at all concerned.

See the FAQ :)

This is true of any webscraper though, you need to santitize any content you collect from the web. If a person wanted a scraper to get something different from the browser, they could easily use UA sniffing to do so. (I've seen it this done a few times.)

Asking GPT to create JSON and then validating the JSON is one piece of that process, but before someone deserialized that JSON and executed INSERT statements w/ it, they should do whatever they usually would do to sanitize that input.

The author asked me to share this here: https://mastodon.social/@jamesturk/110086087656146029

He's looking for a few case studies to work on pro bono, if you know someone that needs some data that meets certain criteria they should get in touch.

FWIW, That's been my use case, when I saw the author post his initial examples pulling data from Wikipedia pages I dropped my cobbled together scripts and started using the tool via CLI & jq.

TIL, thanks!

No inference is needed. IME it can do a single page in ~10s, $0.01/page. Not practical for most use cases, great for a limited few right now.

These kind of one-shot examples are exactly where this hit for me. I was in the middle of some research when I saw him post this and it completely changed my approach to gathering the ad-hoc data I needed.

:) Agree, but the scraping arms race is way beyond that, if someone doesn't want their page scraped this isn't a threat to them.

I was most worried about #2 but surprised how much temperature seems to have gotten that under control in my cases. The author added a HallucinationChecker for this but said on Mastodon he hasn't found many real-world cases to test it with yet.

Regarding 3 & 4:

Definitely take a look at the existing examples in the docs, I was particularly surprised at how well it handled nested dicts/etc. (not to say that there aren't tons of cases it won't handle, GPT-4 is just astonishingly good at this task)

Your project looks very cool too btw! I'll have to give it a shot.

It requires API access, temperature=0 means completely deterministic results but possibly worse performance. Higher temperature increases "creativity" for lack of a better word, but with it, hallucination & gibberish.

Not the author, but it seems like the separation of system & user messages actually prevents page content from being used as an instruction. This was one of the first things I tried and IME, couldn't actually get it to work. I'm sure (like all webscraping) it'll be an arms race though.

Perhaps not, the author mentioned on Mastodon that he was exploring simpler models.

It seems like he's setting temperature=0 which also means it is deterministic. Anecdotally, I've been playing with it since he posted an earlier link & it does shockingly well on 3.5 and nearly perfectly on 4 for my use cases.

(to be clear: I submitted but not the author of the library myself)