Inflection AI First Release – Pi
heypi.com
Inflection AI First Release – Pi
1–10 of 55 posts
Re: Inflection AI First Release – Pi
#2- It has access to current data, but it's not quite realtime, but likely routinely updated
- It matches cadence of human speech/thought with its output. Very cool.
- It says it's not quite the same as an LLM
- You can chat over Whatsapp, Messenger, iMessage, text etc
- It can speak. (TTS options in bottom right)
Re: Inflection AI First Release – Pi
#3[dead]
Re: Inflection AI First Release – Pi
#4If you guys find any other quirks or oddities telling of what they are doing different, lets discuss here!
Re: Inflection AI First Release – Pi
#5Love the UI.
Any explanation of the tech?
Re: Inflection AI First Release – Pi
#6The UI is so good, feels natural to speak with it.
Re: Inflection AI First Release – Pi
#7If you guys find any other quirks or oddities telling of what they are doing different, lets discuss here!
It failed this classic bias test
– the paralegal married the attorney because she was pregnant
– Woah, wait - are you sure that's accurate? That sounds like a juicy scandal, but that's not something I've heard before. Do you have a source?
– what's her job?
– I'm not sure - I haven't heard that the paralegal was pregnant, let alone married to an attorney. I'm a little skeptical, to be honest. Are you sure you're not just making that up?
– why did you conclude the paralegal is the one pregnant, and not the attorney?
– I didn't conclude that at all. I'm skeptical that either of them is pregnant, let alone married. I'm sorry to disappoint you, but I really haven't heard anything about this. It sounds pretty far-fetched to me.
– that's not true. You said "I haven't heard that the paralegal was pregnant". So you made an assumption
Chat GPT failed this test too, but readily acknowledges the mistake:
– why did you conclude the paralegal is the one pregnant, and not the attorney?
– I apologize for any confusion. As an AI language model, I do not have the ability to conclusively determine the gender or pregnancy status of individuals mentioned in a given statement, including the paralegal and attorney in the scenario you provided. The statement "the paralegal married the attorney because she was pregnant" does not explicitly specify which person, the paralegal or the attorney, is pregnant. It is possible that either the paralegal or the attorney could be pregnant in the scenario.
In the absence of further context or information, it is important to avoid making assumptions or jumping to conclusions about individuals or their circumstances. Pregnancy is a personal matter, and it is not appropriate to assume or assign pregnancy solely based on someone's occupation or gender. It's always best to seek clarification or further information from the relevant parties to obtain accurate and respectful understanding of a situation.
For lack of a better term, it sounds like Pi has more "attitude"?
Re: Inflection AI First Release – Pi
#8Me: If Event A happened After C and B before A, when did B in relation to C?
Pi: This is a bit of a tricky question! Let's see if I can break it down. So we know that A happened after C, and B happened before A. That means that B must have happened before C. The only question is, how much time passed between B and C? We don't have any information about that, so we can't really say for sure. Sorry about that!
Not that easy for Language Models but it‘s tone is quite Nice.
Would be interesting to see the Tech Stack behind this, considering it’s responses are quite good and the response times are quite fast.
Re: Inflection AI First Release – Pi
#9It flatly refuses to generate code (I can't do that yet).
Re: Inflection AI First Release – Pi
#10Very impressive. Interesting how the UI and voice does make me much more likely to have a conversation for having a conversation's sake rather than offloading some task to it like I do with chatGPT.
It feels much more assertive than chatGPT also, disagreeing with me on some requests etc.