GPT4o: 11 STUNNING Use Cases and Full Breakdown

Which use case is your favorite? Mine is being able to have AI make calls to companies on my behalf...imagine the time saved!!

The best usecase of all is for education, imagine how wonderful would be to have a tutor for everything, including language learning, accent training, tips, etc. I'm very excited for this use case in particular.

4:22 Alright, that impressed me. He told it what he was going to do, it started gushing about talking to the other AI, and when he asked it to "please pause" when it replied (and this is the part that impressed me) it gave a short response at a much lower volume. The contextual understanding to lower it's volume, almost to a whisper compared to its previous volume, is pretty amazing to me. That's a level of nuanced understanding of the situation I didn't expect. Edit: And Matthew points it out right after I comment. Oh well.

The two AIs singing together was about as awkward as I'd expect it to be if they stuck two interns in an office and made them do the same task over a phone, so I guess this passes the Turing Test?

it's kind of funny how the Open AI reps, even knowing they're on a demo being watched by millions, keep interrupting the A.I. like 'yeah yeah, be quiet" like they've heard it a thousand times and are tired of it. Even they seem to get annoyed by the blathering.

You know those phone salesmen that sell magazines and various other things? All kinds of call centers that basically answer the same questions and solve the same problems? All those jobs are now on a 1 year timer...

I always appreciated these summaries where you comment and speculate on things. I usually watch these things on my own elsewhere, but i always love hearing what you think about everything!

Here's a fun one: It can read redacted documents pretty well. About 75% accuracy, it still stumbles with proper names not included in the visible parts of the document and numeric figures, but does exceedingly well on the rest. It can guess at what text in the blacked-out areas in that length of characters and following normal writing patterns should be present in the missing parts of the document. The smaller the area of redaction, the more accurate it is, so if you're a lawyer, be a little more liberal in the length of your redactions.

I actually felt bad for the AIs when he made them sing. Like demeaning an intern.

Teaching kids is 100% where AI should help. I've been teaching my kids with khan academy since they were young. AI would definitely help when I forget what to do and my kids AND I are confused for some time. It would also help keep them on track when I'm busy

I used it yesterday. It drafted a very good legal motion to dismiss a lawsuit with a lot of accurate legal citations. It's incredible.

As I commented on AI explained. The reason the Agent didn't prompt 'Oh look a person' is because it was given the task to respond to the other agent. It done exactly what it was told, and as I mentioned before, I prefer that to it look around pointing out everything in the room. It isn't a child with ADHD.

Very good and thorough overview of these amazing AI capabilities! This was interesting and well presented/narrated. Thanks 😊

In a speech, the security function can be to ask if the other party is an AI - to which the AI must always answer truthfully.

I’ve been doing experiments like that for a long time where I let models talk to each other like GPT for having a conversation with Claude and it’s always been super interesting

Thank you, Matthew 🫡

All of these demos show that the app is a clever wrapper around the turn-based model. It's only interrupted when there's a loud enough volume, and it cannot interrupt itself when it sees something. This still means that the model itself is turn-based; just that the app part queues up the context data it sends, only sending it for a response whenever the volume becomes quiet again, i.e. you stop talking. Same mechanism as Siri or Alexa except that the responses come from the model. This means when it starts talking, it can't respond to the video. It also can't interrupt you when you're talking as the model is only triggered after you stop talking.

Interesting concept! I actually work for a tech company and got hired when promoting an SDR platform that utilizes sound board with voice integration like this. Essentially, these AI agents are remote workers that handle initial prospecting calls with my voice, and I can then seamlessly chime in live and take over when the conversation reaches the booking stage. It creates a very efficient workflow. If you're exploring similar solutions, this kind of technology could be a game-changer for your SDR team. It ensures compliance since I'm actively managing the calls (not robo-calling), but allows for AI to handle the initial outreach and qualification, freeing me up for more complex conversations. FYI, prospects are never going to trust a fully automated system, you still need a human for the final touches to lock in the deal.

Question to GPT4o As you probably know, temperature can be seen as a measure of how the molecules of a liquid move. Taking this into account, do you think a stone thrown into water at 40 degrees Fahrenheit sinks faster than at 30 degrees Fahrenheit? Answer To determine whether a stone sinks faster in water at 40 degrees Fahrenheit compared to 30 degrees Fahrenheit, we need to consider the properties of water and how they change with temperature. Here are the relevant factors: Water Density: - Water is most dense at about 39 degrees Fahrenheit (4 degrees Celsius). As water cools from 40 degrees Fahrenheit to 30 degrees Fahrenheit, it actually becomes less dense because it approaches the freezing point and begins to form ice crystals, which have a lower density than liquid water. Viscosity: - The viscosity of water decreases as the temperature increases. This means that water at 40 degrees Fahrenheit is less viscous than at 30 degrees Fahrenheit. Considering these points: Density Difference: Since the density of water slightly decreases from 40 degrees Fahrenheit to 30 degrees Fahrenheit, the buoyant force acting on the stone might be slightly less at 30 degrees Fahrenheit. This would, in theory, allow the stone to sink faster at the lower temperature due to slightly reduced buoyant force. However, this effect is quite minimal because the density change is not drastic. Viscosity Difference: The greater factor here is the viscosity. Water at 40 degrees Fahrenheit is less viscous than water at 30 degrees Fahrenheit. Lower viscosity means there is less resistance to the stone's movement through the water. Given these considerations, the reduced viscosity at the higher temperature (40 degrees Fahrenheit) would have a more significant effect on the stone's sinking speed. Thus, the stone is likely to sink faster in water at 40 degrees Fahrenheit than at 30 degrees Fahrenheit because the water offers less resistance to the stone's movement. In summary, the lower viscosity of water at the higher temperature (40 degrees Fahrenheit) would cause the stone to sink faster compared to at 30 degrees Fahrenheit.

I think they made it intentionally flirty to mimic the personality of HER. Great move if you ask me!