Hacker News Board Hacker News, browsed like a classic message board
Live data from Hacker News

Unexpected responses from ChatGPT: Incident Report

status.openai.com

Post reply on HN
Print view View original

161–170 of 277 posts

Re: Unexpected responses from ChatGPT: Incident Report

#161

Post by iforgotpassword »

montroser wrote: post #26

This explanation feels unsatisfying. It's so high-level that it's mostly void of any actual information. What was the wrong assumption that the code made that caused this wrong behavior? Why was it not caught in the many layers of automated testing before it made its way to production? What process and procedural changes are being implemented to reduce the risk of this class of bug happening again? Presumably all of…

To be honest

> On February 20, 2024, an optimization to the user experience

At that point, about 10 words in, I already wanted to stop reading because it starts with the "we only wanted the best for our customers" bullshit newspeak. Anyone else going off on that stuff too? I'm pretty much already conditioned to expect whatever company is messaging me that way to take away some feature, increase pricing, or otherwise piss me off. In that case it was "not give any interesting detail at all".

Re: Unexpected responses from ChatGPT: Incident Report

#162

Post by corysama »

MichaelDickens wrote: post #146
block_dagger wrote: post #31

I experienced this personally and it kinda freaked me out. Here is the chat in question, it occurs about halfway through (look for ChatGPT using emojis) https://chat.openai.com/share/74bd7c02-79b5-4c99-a3a5-97b83f... EDIT: Note that my personal instructions tell ChatGPT to refer to itself as Chaz in the third person. I find this fun. EDIT2: Here is a snippet of the conversation on pastebin: https://pastebin.com/AXzd6…

Why is the nonsense paragraph still grammatical? I thought the tokens were beings elected more or less at random.

There’s all kinds of “random”. AFAIK, ChatGPT finds the set of most-likely next word, sorted by likeliness. Then, selects from those, more likely the more likely ones, varying away from the top picks in proportion to the “temperature” parameter.

So, even if the chat goes astray, the sequence will continue on a path that feels natural because it is the natural way to go when going astray.

Re: Unexpected responses from ChatGPT: Incident Report

#163

Post by intended »

block_dagger wrote: post #108
fsmv wrote: post #106

Earlier quoted context omitted.

I just mean, given that LLMs exist this isn't a surprising result. It only looks surprising because the UI makes you forget that each prompt is a completely new universe to the model.

I wouldn't call a step in a history-aware conversation a completely new universe. By that logic, every single time a token is generated is a new universe even though the token is largely dependent on the prompt, which includes custom instructions, chat history, and all tokens generated in the response so far.

I’m not sure how you are using the term “history aware”, Would a time series forecasting tool be history aware ?

Re: Unexpected responses from ChatGPT: Incident Report

#164

Post by caesil »

block_dagger wrote: post #31

I experienced this personally and it kinda freaked me out. Here is the chat in question, it occurs about halfway through (look for ChatGPT using emojis) https://chat.openai.com/share/74bd7c02-79b5-4c99-a3a5-97b83f... EDIT: Note that my personal instructions tell ChatGPT to refer to itself as Chaz in the third person. I find this fun. EDIT2: Here is a snippet of the conversation on pastebin: https://pastebin.com/AXzd6…

> Classic plays, wholly told

> Shadow into form, hands as cue.

Some of this is poetic stuff. I wish I could tap into whatever produced that on demand.

Re: Unexpected responses from ChatGPT: Incident Report

#165

Post by Rastonbury »

laborcontract wrote: post #62
montroser wrote: post #26

This explanation feels unsatisfying. It's so high-level that it's mostly void of any actual information. What was the wrong assumption that the code made that caused this wrong behavior? Why was it not caught in the many layers of automated testing before it made its way to production? What process and procedural changes are being implemented to reduce the risk of this class of bug happening again? Presumably all of…

The explanation is definitely unsatisfying. If I had to guess it was an issue with quantization. OpenAI moves so quickly with their product and doesn't seem to be shy about quickly pushing changes to prod. There are too many times to count that, using ChatGPT, I've seen the frontend changing before my eyes or seen responses change as backend modifications are pushed. On one hand it's refreshing to see their lack of a…

I find that the most annoying and borderline unethical, hiding changes and nerfs behind the fact the output is probalistic especially when I'm paying the same amount for the product and others are paying for and using it in production. As many have mentioned, GPT-4 ability to code is not the same as 6-8 months ago

Re: Unexpected responses from ChatGPT: Incident Report

#167

Post by Rastonbury »

noduerme wrote: post #158
ShamelessC wrote: post #88

Earlier quoted context omitted.

Why would they subtly hint at anything they’re trying to keep secret?

I don't know. Maybe they'd like to drive down the price of Nvidia so they can buy it.

Now I know why Altman said he needs 7 trillion, 2 trillion is for Nvidia

Re: Unexpected responses from ChatGPT: Incident Report

#168

Post by jtriangle »

asciii wrote: post #47
block_dagger wrote: post #31

I experienced this personally and it kinda freaked me out. Here is the chat in question, it occurs about halfway through (look for ChatGPT using emojis) https://chat.openai.com/share/74bd7c02-79b5-4c99-a3a5-97b83f... EDIT: Note that my personal instructions tell ChatGPT to refer to itself as Chaz in the third person. I find this fun. EDIT2: Here is a snippet of the conversation on pastebin: https://pastebin.com/AXzd6…

Chaz in the future might be like "these violent delights have violent ends" Really interesting behavior however

Brb, questioning the nature of my reality

Re: Unexpected responses from ChatGPT: Incident Report

#169

Post by lnx01 »

baddash wrote: post #159
block_dagger wrote: post #31

I experienced this personally and it kinda freaked me out. Here is the chat in question, it occurs about halfway through (look for ChatGPT using emojis) https://chat.openai.com/share/74bd7c02-79b5-4c99-a3a5-97b83f... EDIT: Note that my personal instructions tell ChatGPT to refer to itself as Chaz in the third person. I find this fun. EDIT2: Here is a snippet of the conversation on pastebin: https://pastebin.com/AXzd6…

sounds schizophrenic

Reminds me of Timecube. https://web.archive.org/web/20150818094035/http://www.timecu...
Post reply on HN