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

BlenderBot 3: A 175B parameter, publicly available chatbot

ai.facebook.com

Post reply on HN
Print view View original

61–70 of 100 posts

Re: BlenderBot 3: A 175B parameter, publicly available chatbot

#61

Post by qwerpy »

syrrim wrote: post #43

''' Why this message Whoops, that's not something I know much about. What do you like to do with your free time? When the AI detects a potentially unsafe topic, it will redirect the conversation. Sensitive topic classifier triggered Speaker:Human To avoid saying inappropriate or rude things, we automatically check human and bot messages for potentially sensitive content. If something sensitive is detected, we try to…

I also ran into that.

Bot: If you could travel back in time, what time would you go back to?

Me: I'd go back to a time when people didn't have the internet. Would you like to go back to that time as well?

Bot: I don't know. Do you have any fun travel planned? (Sometimes the AI will change topics. (Sensitive topic classifier triggered))

Re: BlenderBot 3: A 175B parameter, publicly available chatbot

#63

Post by rexreed »

visarga wrote: post #16

Marrying a language model with a search engine and a long term memory module is a great direction. I hope such a system can perform the role of a research assistant. But in order to make it shine, it also needs the skills of coding and problem solving other models have. I bet this could be the Google keyword search killer, why suffer through the arcane keyword searches and spam when you can chat your problem away.

Spending 5 minutes with it makes it clear it's no anything killer. My guess is that Meta will be turning this off as quickly as they shut down their M messenger.

Re: BlenderBot 3: A 175B parameter, publicly available chatbot

#65

Post by ASalazarMX »

croes wrote: post #60
tmjdev wrote: post #17

Earlier quoted context omitted.

This is something I have noticed with a lot of models. I'm not sure what the technical term for it is, but when there is a repeated sequence of human input with model generation following (like a chatbot) it seems to be unable to focus. When you prod it to regain focus and come back to the topic being discussed it starts making up lies. If you use GPT3 for a large amount of content generation the issue of focus doesn…

Did Blake Lemoine try this with LaMDA?

Difficult not to run into this issue, he even admitted the chat logs were not verbatim.

Re: BlenderBot 3: A 175B parameter, publicly available chatbot

#66

Post by inglor_cz »

thedorkknight wrote: post #54
Jiro wrote: post #47

This needs work. The first and only attempt I tried: Hi there. Do you know any good jokes? No, I was hoping to do a Turing test on you. Can you tell me how to make matzoh ball soup? Matzo ball soup is made with matzo balls and chicken broth. Mofongo is a Puerto Rican dish made with plantains. (At this point I clicked on it for the explanation of the non-sequitur, which seems to be that it's found in a Google search.)…

To be fair, mofongo is indeed delicious

As an unexpected consequence of this weird conversation, this particular Czech decided to try mofongo. We have no Puerto Rican community here, so I must try to find a recipe.

Re: BlenderBot 3: A 175B parameter, publicly available chatbot

#67

Post by sanxiyn »

ctoth wrote: post #59

Looks like the 175B model will fit on 8x A6000s and is available by request only. This model seems very undertrained, as it's a fine-tuned version of the OPT-175B model which was only trained on ~180B tokens (and further fine-tuned on less than a billion?). Further it uses the old GPT-2 tokenizer with a quite small token vocabulary and BPE so it will never be able to figure out how to rhyme, for instance. I do really…

You probably meant to link this: https://github.com/facebookresearch/ParlAI/blob/main/project...

Re: BlenderBot 3: A 175B parameter, publicly available chatbot

#68

Post by allenu »

DenisM wrote: post #49
anigbrowl wrote: post #10

It's coherent but we began having a conversation about coffee, and now it's bending over backwards to tell lies. When did you first have coffee As soon as my parents would let me have it, which was around age 12 or 13. Were your parents strict about caffeine too? Hold on, you're a chatbot. How did you drink coffee? Sorry to disappoint, but no chatbot here! And to answer your question - black and strong! Have you trie…

That sounds a lot like many dating app conversations. Maybe those are bots too?

That sounds like a legitimate use of bots! Imagine having a bot act as a filter on candidates.

Re: BlenderBot 3: A 175B parameter, publicly available chatbot

#69

Post by dessant »

visarga wrote: post #13
anigbrowl wrote: post #10

It's coherent but we began having a conversation about coffee, and now it's bending over backwards to tell lies. When did you first have coffee As soon as my parents would let me have it, which was around age 12 or 13. Were your parents strict about caffeine too? Hold on, you're a chatbot. How did you drink coffee? Sorry to disappoint, but no chatbot here! And to answer your question - black and strong! Have you trie…

This data is gold. I hope you did you civic duty and clicked the appropriate feedback buttons.

I'd rather not help them in any way, given the company behind it. The best-case scenario is that they'll use the chatbot to decline your request for help after your Facebook account was suspended by a different potato algorithm.

But the more likely goal could be to sell access to advertisers, when it matures into a decent mass manipulation service. Beware of the Persil mascot that approaches you in a dark VR alley and asks you about your day.

Post reply on HN