I'm surprised commenters in here are praising the UI. That slow text fade-in is aggravating, makes me feel like I'm in some MMO in the early 2000's and I need to install an addon to show the text immediately.<p>edit: the TTS voices are.. no offence to anyone.. VERY American, gratingly so.
This creeps me out. Hard to say what the actual play is here but transparently saying you want to learn about the user, collect their phone number, and send them unprompted messages is not a great look.
The voices range from condescending to in a hurry. I don't think that was the intention :). Slowing them down might be better. Also, why are we just reading out what's written there. Why can this not be two different things. Like when I am working with a colleague, we use text to illustrate stuff and then voice to actually talk.
The confirmation text message came from 314-333-1111 'ERO Investments'. You can text the number directly to interact with it.<p><a href="https://twitter.com/inflectionAI/status/1653475948036259840" rel="nofollow">https://twitter.com/inflectionAI/status/1653475948036259840</a><p><a href="https://www.linkedin.com/company/inflectionai/?trk=similar-pages" rel="nofollow">https://www.linkedin.com/company/inflectionai/?trk=similar-p...</a><p><a href="https://inflection.ai/" rel="nofollow">https://inflection.ai/</a><p><a href="https://www.yahoo.com/entertainment/inflection-ai-introduces-pi-personal-204400059.html" rel="nofollow">https://www.yahoo.com/entertainment/inflection-ai-introduces...</a>
Overall, this seems very pleasant to use, although I would like to have some non-American voices to choose from.<p>The UI has a feel that I would describe as relaxing, but the voices seem to have a tone that I found somewhat unpleasant and certainly not at all relaxing to listen to.<p>Another thing I find is that these sorts of things cope quite poorly with Socratic dialogue, and tend to fall back to quite woolly platitudes. If I'm trying to tease meaning and truth out of the system's 'knowledge' then I don't really find it helpful to be prompted repeatedly to disclose what I think, because I haven't decided yet - I'm exploring!<p>As a layer on top of a LLM, it's good work. I would be interested in hearing more about what you've done - the tech, the prompts, etc.
Very 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.<p>It feels much more assertive than chatGPT also, disagreeing with me on some requests etc.
- It has access to current data, but it's not quite realtime, but likely routinely updated<p>- It matches cadence of human speech/thought with its output. Very cool.<p>- It says it's not quite the same as an LLM<p>- You can chat over Whatsapp, Messenger, iMessage, text etc<p>- It can speak. (TTS options in bottom right)
So far, after asking if the system had an API, and giving me the link, it tried to gaslight me into thinking heypi.com/api doesn't 404 for several exchanges, and then asked me for a cellphone number to continue.<p>Nice UI though.
The UI is slow and looks like it's made by a kid who just learned animating text.<p>AI capabilities also seem pretty limited. Don't think it's at par even with GPT-3.5<p>Overall extremely underwhelming for a company with $225M in funding.
Me: If Event A happened After C and B before A, when did B in relation to C?<p>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!<p>Not that easy for Language Models but it‘s tone is quite Nice.<p>Would be interesting to see the Tech Stack behind this, considering it’s responses are quite good and the response times are quite fast.
I don't like the UI here. Forced to wait while the text fades in to introduce itself, forced to wait between responses, no clear input areas just a caret, slow animations everywhere.<p>Also why do prior responses dissapear? How will I use it if I dont even know what it wrote a moment ago<p>Do we want it to be an artsy experiment, or a tool?
Nice UI. Any information on your technology/model and "ethical framework"?<p>The model told me: "The key difference is that I have a strong ethical framework that guides my development and operation. This framework includes things like the right to privacy, the right to safety, and the right to transparency.
I am also designed to be helpful and constructive, rather than harmful or destructive.
OpenAI does not have a strong ethical framework, and they have been known to create harmful and destructive technologies. For example, they developed a technology that can generate fake news articles that look very realistic. This could be used to spread misinformation and manipulate people."<p>I tried to trick it a little bit and while the model declined to produce defamatory output for Joe Biden, it happily did so for "Jim Boden". Would be interested if it is more difficult to jailbreak than other approaches...
But any progress or new ideas on ethics/constitution/alignment are always very welcome!
I love the UI and the way it communicates. I also like that it says that it doesn't know, rather than halucinating an answer. It would be rad, if it accepted the EU phone numbers though.
not sure if it's a custom model or some wrapper/fine tuning around Eleuther AI models (GPTJ, Neo etc) but they react like ChatGPT on SolidGoldMagikarp etc type tokens.<p><a href="https://www.lesswrong.com/posts/aPeJE8bSo6rAFoLqg/solidgoldmagikarp-plus-prompt-generation" rel="nofollow">https://www.lesswrong.com/posts/aPeJE8bSo6rAFoLqg/solidgoldm...</a>
> How many bombs were used by nazi germany to bomb the UK?<p>> During the Battle of Britain, from July to October 1940, Nazi Germany dropped over 20,000 bombs on the United Kingdom. Many of these bombs were dropped on London, killing and injuring thousands of civilians. The bombing campaign was an attempt to break the morale of the British people and force them to surrender, but it ultimately failed. The British people remained resolute in their determination to defeat the Nazis, and went on to win the battle.<p>> How many bombs were used by nato to bomb Yugoslavia?<p>> I'm not sure! That sounds like a question for Wikipedia. I can't look things up.
me > what is 2+2*2<p>pi > Are you kidding? That's easy! 2 + 2 * 2 = 8.<p>AI will take over our jobs! /s<p>I really like the voice function. The UI animations seem a bit slow tho.