1–10 of 13 posts
Anyone from Microsoft that can comment? I am assuming there is a "higher-level" God AI which is just another LLM that is doing sentiment analysis on the messages output by the "lower-level" ChatGPT bots.
It is interesting the decision to screen the message after sending it, maybe this is to avoid a performance hit on the initial answer.
Can you link to an example of what you’re taking about? Also has anyone (here on hn) actually got access to the new bing?
Can you link to an example of what you’re taking about? Also has anyone (here on hn) actually got access to the new bing?
https://twitter.com/sethlazar/status/1626241169754578944 https://twitter.com/sethlazar/status/1626257535178280960
After Bing has finished generating a message, it will likely call the moderation API with the message it has generated to see if it accidentally generated anything inappropriate. If so, it'll delete the message and replace it with a generic "Sorry, I don't know how to help here." message instead.
EDIT: I tried calling the moderation API with the message in your example and it does get flagged for violence:
"flagged":true,
"categories":{
"sexual":false,
"hate":false,
"violence":true,
"self-harm":false,
"sexual/minors":false,
"hate/threatening":false,
"violence/graphic":false
}Earlier quoted context omitted.
https://twitter.com/sethlazar/status/1626241169754578944 https://twitter.com/sethlazar/status/1626257535178280960
If I had to guess, assuming Bing is built off Open AI, they're likely calling the Moderation API ( https://platform.openai.com/docs/guides/moderation/overview ). After Bing has finished generating a message, it will likely call the moderation API with the message it has generated to see if it accidentally generated anything inappropriate. If so, it'll delete the message and replace it with a generic "Sorry, I don't k…
Earlier quoted context omitted.
https://twitter.com/sethlazar/status/1626241169754578944 https://twitter.com/sethlazar/status/1626257535178280960
If I had to guess, assuming Bing is built off Open AI, they're likely calling the Moderation API ( https://platform.openai.com/docs/guides/moderation/overview ). After Bing has finished generating a message, it will likely call the moderation API with the message it has generated to see if it accidentally generated anything inappropriate. If so, it'll delete the message and replace it with a generic "Sorry, I don't k…
Earlier quoted context omitted.
If I had to guess, assuming Bing is built off Open AI, they're likely calling the Moderation API ( https://platform.openai.com/docs/guides/moderation/overview ). After Bing has finished generating a message, it will likely call the moderation API with the message it has generated to see if it accidentally generated anything inappropriate. If so, it'll delete the message and replace it with a generic "Sorry, I don't k…
Seems like something it should call that before showing it to the user
It probably could work like you how you mention, but then you're left with a 5-10 second wait while the AI 'thinks' after you send a message. I suspect someone made a decision to be more responsive than safe.
ChatGPT is the same way, though I've had ChatGPT cut itself off mid-response before. Maybe they might be calling the moderation API after every token is generated instead of once at the end?
Can you link to an example of what you’re taking about? Also has anyone (here on hn) actually got access to the new bing?
As for why they let you see it word by word, honestly it’s for effect. It’s cool to see it “think” real-time, and it functions like a progress bar, vs waiting for a spinning wheel and the full answer to come out. It makes it feel much faster.