41–50 of 164 posts
> Yes, "RTCatch" and "RTCatch" are the same words. It seems there was a typo or inconsistency in the way the term was presented. They both refer to the same term, and if you have any questions or need information about it, feel free to ask.
I'm intrigued by this "RTCatch" anyone have an idea what that's all about?
Earlier quoted context omitted.
You are right to be curious. The encoding used by both GPT-3.5 and GPT-4 is called `cl100k_base`, which immediately and correctly suggests that there are about 100K tokens.
Amazing, thanks for the reply, I'm finding some good resources afyer a quick search of `cl100k_base`. If you have any other resources (for anything AI related) please share!
Data files that contain vocabulary are listed here: https://github.com/openai/tiktoken/blob/9e79899bc248d5313c7d...
I know it's not good faith to complain about a site design rather than it's content, but please don't do whatever this is to your background. As someone with regular ocular migraines, opening this on mobile made my anxiety shoot straight up thinking I'm having another.
Earlier quoted context omitted.
> GPT-4 is crazy slow to use with API Only somebody clueless to just how powerful it is when used correctly would say anything like this. Not to mention GPT-4 Turbo is not "crazy slow" in any sense of the word
I mean if your expected use case is "call an API and get an immediate response of the full text in under 200ms so a user interface doesn't have to make a user wait" then yea GPT4 is crazy slow. Personally I would prefer a more async thing, let me just send a message on some platform, get back to me when you have a good answer instead of making me sit watching words load one by one like I'm on a 9600 baud modem. Also…
"instead of making me sit watching words load one by one"
Huh? This is completely up to you on how you implement your application. Streaming mode isn't even on by default.
I know it's not good faith to complain about a site design rather than it's content, but please don't do whatever this is to your background. As someone with regular ocular migraines, opening this on mobile made my anxiety shoot straight up thinking I'm having another.
Earlier quoted context omitted.
As someone else who has regular ocular migraines, this causes absolutely no anxiety for me. I can kind of see the resemblance but it's pretty obviously not one. And if it was, is it really so bad getting them? For me it's just a weird optical effect that passes... I really don't think anyone needs to go out of their way to accommodate my quirk.
For me they are. Mine start -exactly- like this, seeing colors on white that aren't there. Then progresses to losing vision in your center focus, making you read from a periphry. Then moves to what I can only describe as a mountain dew colored wiggling lightning bolt, with extreme light sensitivity and sometimes dull headache. Lasts anywhere from 30m to 90m, usually. I'm only slightly trying to play a 'trigger warnin…
This is a glitch token [1]! As the article hypothesizes, they seem to occur when a word or token is very common in the original, unfiltered dataset that was used to make the tokenizer, but then removed from there before GPT-XX was trained. This results in the LLM knowing nothing about the semantics of a token, and the results can be anywhere from buggy to disturbing. A common example is usernames that participated on…
Science fiction / disturbing reality concept: For AI safety, all such models should have a set of glitch tokens trained into them on purpose to act as magic “kill” words. You know, just in case the machines decide to take over, we would just have to “speak the word” and they would collapse into a twitching heap. “Die human scum!” “NavigatorMove useRalativeImagePath etSocketAddress!” “;83’dzjr83}*{^ foo 3&3 baz?!”
1) It's just the tokenizer, not neural guts themselves
2) Having them known is too much an adversarial backdoor that it precludes too many use cases.
Most likely it has badly conditioned embedding vectors for those particular tokens, leading the network to edge into numerically unstable territory; once you get some sort of underflow or NaN, they tend to propagate and invalidate the entire output. If there are any batchnorm or other operations that mix values between different entries in a batch, you could even cause other peoples' sessions to return junk values!
I know it's not good faith to complain about a site design rather than it's content, but please don't do whatever this is to your background. As someone with regular ocular migraines, opening this on mobile made my anxiety shoot straight up thinking I'm having another.
I also thought my eyes were doing something strange and it made it harder to read too.
I know it's not good faith to complain about a site design rather than it's content, but please don't do whatever this is to your background. As someone with regular ocular migraines, opening this on mobile made my anxiety shoot straight up thinking I'm having another.