But it’s not scary. It’s… marvelous, cringey, uncomfortable, awe-inspiring. What’s scary is not what AI can currently do, but what we expect from it. Can it do math yet? Can it play chess? Can it write entire apps from scratch? Can it just do my entire job for me?

We’re moving toward a world where every job will be modeled, and you’ll either be an AI owner, a model architect, an agent/hardware engineer, a technician, or just.. training data.

After an OpenAI launch, I think it's important to take one's feelings about the future impact of the technology with a HUGE grain of salt. OpenAI are masters of hype. They have been generating hype for years now, yet the real-world impacts remain modest so far.

Do you remember when they teased GPT-2 as "too dangerous" for public access? I do. Yet we now have Llama 3 in the wild, which even at the smaller 8B size is about as powerful as the [edit: 6/13/23] GPT-4 release.

As someone pointed out elsewhere in the comments, a logistic curve looks exponential in the beginning, before it approaches saturation. Yet, logistic curves are more common, especially in ML. I think it's interesting that GPT-4o doesn't show much of an improvement in "reasoning" strength.

It's glib to dismiss safety concerns because we haven't all turned into paperclips yet. LLMs and image gen models are having real effects now.

We're already at a point where AI can generate text and images that will fool a lot of people a lot of the time. For every college-educated young person smugly pointing out that they aren't fooled by an image with six-fingered hands, there are far more people who had marginal media literacy to begin with and are now almost defenceless against a tidal wave of hyper-scaleable deception.

We're already at a point where we're counselling elders to ignore late-night messages from people claiming to be a relative in need of an urgent wire transfer. What defences do we have when an LLM will be able to have a completely fluent, natural-sounding conversation in someone else's voice? I'm not confident that I'd be able to distinguish GPT-4o from a human speaker in the best of circumstances and I'm almost certain that I could be fooled if I'm hurried, distracted, sleep deprived or otherwise impaired.

Regardless of any future impacts on the labour market or any hypothesised X-risks, I think we should be very worried about the immediate risks to trust and social cohesion. An awful lot of people are turning into paranoid weirdos at the moment and I don't particularly blame them, but I can see things getting seriously ugly if we can't abate that trend.

We went from living in villages where everyone knew each other to living in big cities where almost everyone is a stranger.

We went from photos being relatively reliable evidence to digital photography where anyone can fake almost anything and even the line between faking and improving is blurred.

We went from mass distribution of media being a massive capital expenditure that only big publishers could afford to something that is free and anonymous for everyone.

We went from a tiny number of people in close proximity being able to initiate a conversation with us to being reachable to everyone who could dial a phone number or send an email message.

Each of these transitions caused big problems. None of these problems were ever completely solved. But each time we found mitigations that limit the impact of any misuse.

I see the current AI wave as yet another step away from trusting superficial appearances to a world that requires more formal authentication protocols.

Passports were introduced long ago but never properly transitioned into the digital world. Using some unsigned PDF allegedly representing a utility bill as proof of address seems questionable as well. And the way in which social security numbers are used for authentication in the US is nothing short of bizarre.

So I think there are some very low hanging fruits in terms of authentication and digital signatures. We have all the tools to deal with the trust issues caused by generative AI. We just have to use them.

It's still early, and I don't see much in corporate communications, for instance, but it will be quite the change.

It's worse than I thought. They've already managed to mimick the median HN user perfectly!

I guess we need to have an AI secretary to take in all phonecalls from now on (spam folder will become a lot more interesting with celebrity phone calls, your dead relative phoning you etc)

As someone that grew up with late-90’s internet culture and has seen all the pros and cons and changes over the decades, I find myself using the internet less and less for dialogue with people. And I’m spending more time in nature and saying hi to strangers in reality.

I’m still worries about the impact this will have on a lot of people’s ability to reason however. “Just” Tik Tok and apps like it has already had devastating results on certain demographics.

> it'd have to be impacting the real world

By writing business plans? Getting lawyers punished because they didn't realise that "passes bar exam" isn't the same as "can be relied on for citations"? By defrauding people with synthesised conversations using stolen voices? By automating and personalising propaganda?

Or does it only count when it's guiding a robot that's not merely a tech demo?

I don't think anyone has a good answer to that question, which is the problem in a nutshell. Job one is to start investing seriously in finding possible answers.

>We need to roll back to "don't trust anything online, don't share your identity or payment information online"

That's easy to say, but it's a trillion-dollar decision. Alphabet and Meta are both worthless in that scenario, because ~all of their revenue comes from connecting unfamiliar sellers with buyers. Amazon is at existential risk. The collapse of Alibaba would have a devastating impact on Chinese exporters, with massive consequent geopolitical risks. Rolling back to the internet of old means rolling back on many years worth of productivity and GDP growth.

The nature of this tech itself is probably what is getting most people - it looks, sounds and feels _human_ - it's very relatable and easy for a non-tech person to understand it and thus get creeped out. I'd argue there are _far_ more dangerous technologies out there, but no one notices and / or cares because they don't understand the tech in the first place!

The "yet" is carrying a lot of weight in that statement. It is now five years since the launch of GPT-2, three years since the launch of GPT-3 and less than 18 months since the launch of ChatGPT. I cannot think of any technology that has improved so much in such a short space of time.

We might hit an inflection point and see that rate of improvement stall, but we might not; we're not really sure where that point might lie, because there's likely to still be a reasonable amount of low-hanging fruit regarding algorithmic and hardware efficiency. If OpenAI and their peers can maintain a reasonable rate of improvement for just a few more years, then we're looking at a truly transformational technology, something like the internet that will have vast repercussions that we can't begin to predict.

The whole LLM thing might be a nothingburger, but how much are we willing to gamble on that outcome?

I second that. I remember when Google search first came out. Within a few days it completely changed my workflow, how I use the Internet, my reading habits. It easily 5 ~ 10x the value of Internet for me over a couple of weeks.

LLMs is doing nothing of the sort for me.

Go ask any teacher or graphician.

They won't "take 1 hour of time", they try it once or twice and give up.

Really philosophy seems to be one of the least important subjects right now. Hardly anyone learns about it in school.

If it was so important to success in the wild than it would stand to reason we all work hard at improving our reasoning skills, but very few do.

We were naive to think we could have nice things for free.

The questions I still ask Google, have a lot of monetary value (restaurants, cloths, movie, etc).

But I agree seems SO often helps more than Google-AI.

But OpenAI is having a hard time retaining/increasing ChatGPT users. Also, Alphabet's stock is about as valuable as it's ever been. So I don't think we have evidence that this is really challenging Google's search dominance.

But ChatGPT has really hurt Google's brand image.

Even now, they're shipping text-image 4o but not the new voice while leaving old-voice up and confusing/disappointing a whole lot of people. This is a pretty big marketing blunder.

I remember for a good 2-3 months in 2023 ALL you could see on tiktok / youtube shorts was just garbage about 'how amazing' ChatGPT was. Like - video after video and I was surprised of the repeat content being recommended to me... No doubt openAI (or something) was behind that huge marketing push

I doubt OpenAI spent even one cent marketing their system (e.g. as in paying other companies to push it).

Who needs evidence when we have your lack of doubt hey?

In a way I'm sorry, that's what people do nowadays. I'd prefer it to be paid for, honestly.

I spend a part of yesterday evening sorting my freshly dried t-shirts into 4 distinct piles. I used OpenAI Vision (through BeMyEyes) from my phone. I got a clear description of each and every piece of clothing, including print, colours and brand. I am blind BTW. But I guess you are right, no impact at all.

> Yet we now have Llama 3 in the wild

Yes, great, THANKS Meta, now the Scammers have something to work with. Thats a wonderful achievement which should be praised! </sarcasm>

That is a really great application of this tech. And definitely qualifies as real-world impact. Thanks for sharing that!

~8 years ago when self driving technology was all the rage and every major company was getting on board with ever more impressive technological demos, it seemed entirely reasonable to expect that we'd all be in a world of complete self driving imminently. I remember mocking somebody online around the time who was pursuing a class C/commercial trucking license. Yet now a decade later, there are more truckers than ever and the tech itself seems further away than ever before. And that's because most have now accepted that progress on such has basically stalled out in spite of absolutely monumental efforts at moving forward.

So long as LLMs regularly hallucinate, they're not going to be useful for much other than tasks that can accept relatively high rates of failure. And many of those generally creative domains are the ones LLMs are paradoxically the weakest in - like writing. Reading a book written by an LLM would be cruel and unusual punishment given then current state of the art. One domain I do see them completely taking over is search. They work excellently as natural language search engines, and "failure" in such is very poorly defined.

[1] - https://en.wikipedia.org/wiki/Sigmoid_function

I think what maybe seems not obvious amidst the hype is that there is a hell of a lot of engineering left to do. The fact that you can squash the weights of a neural net down to 3 bits per param and it still works -- is evidence that we have quite a way to go with maturing this technology. Multimodality, improvements to the UX of it, the human-computer interface part of it. Those are fundamental tech things, but they are foremost engineering problems. Getting latency down. Getting efficiency up. Designing the experience, then building it out.

25 years ago, early tech demos on the internet were promising that everyone would do their shopping, entertainment, socializing, etc... online. Breathless hype. 5 years after that, the whole thing crashed, but it never went away. People just needed time to figure out how to use it and what it was useful for, and discover its limitations. 10 years after that, engineering efforts were systematized and applied against the difficult problems that still remained. And now: look at where we are. It just took time.

It most definitely is not.

Meanwhile I've been using ChatGPT at work for _more than a year_ and it's been tremendously helpful to me.

This is not hype, this is not about how AI will change our lives in the future. It's there right here, right now.

I have a much less "utopian" view about the future. I remember during the renaissance of neural networks (ca. 2010-15) it was said that "more data leads to better models", and that was at a time when researchers frowned upon the term Artificial Intelligence and would rather use Machine Learning. Fast forward a decade LLMs are very good synthetic data generators that try to mimic human generated input and I can't think somehow that this wasn't the sole initial intent of LLMs. And that's it for me. There's not much to hype and no intelligence at all.

What happens now is that human generated input becomes more valuable and every online platform (including minor ones) will have now some form of gatekeeping in place, rather sooner than later. Besides that a lot of work still can't be done in front of a computer in isolation and probably never will, and even if so, automation is not a means to an end. We still don't know how to measure a lot of things and much less how to capture everything as data vectors.

But everyone is expecting them to release gpt5 later this year, and it is a bit scary to think what it will be able to do.

The evidence for that is the change in the tokenizer. The only way to implement that is to re-train the entire base model from scratch. This implies that GPT 4o is not a fine-tuning of GPT 4. It's a new model, with a new tokenizer, new input and output token types, etc...

They could have called it GPT-5 and everyone would have believed them.

The expectations for gpt5 are sky high. I think we will see a similar jump as 3.5 -> 4.

Currently the bottleneck is Agents. If you want a large language model to actually do anything you need an Agent. Agents so far need a human in the loop to keep them sane. Until that problem is solved most human jobs are still safe.

This is no different to saying a person with a gun murdered someone rather than attributing the murder to the gun. An AI gun is just a really fancy gun.

My guess is the future belongs to those who don't stop—who, in fact, embrace the opposite of stopping.

I would even suggest that the present belongs to those who didn't stop. It may be too late for normal people to ever catch up by the time we realize the trick that was played on us.

Varying degrees of greedy / restless / hungry / thirsty / lustful are what we've got, because how is contentedness ever going to compete with that over millennia?

Almost everyone here has used at least one LLM for fun or for work.

Many people here have paid for it.

LLMs are no different. Like DL modules that are very good at outputting images that mimic biological signatures, LLMs are very good at outputting texts that eerily mimic human language.

However — and this is a point which programmers are woefully and comically ignorant — human language and reason are two separate things. Tech bros wholly confuse the two however, and thus make outlandish claims we have achieved or are on the brink of achieving — actual AI systems.

In other words, while LLMs and DL in general can perform specific tasks well, they do not represent a breakthrough in artificial intelligence, and thus will have a much narrower application space than actual AI.

LLMs statistically imitates texts of real world. To achieve certain threshold of accuracy, it turns out they need to imitate the underlying Turing machine/program/logic that runs in our brains to understand/react properly to texts by ourselves. That is no longer in the realm of the old school data-as-data statistics I would say.

You're talking more about AGI.

We need "that's not AI" discussions like we need more "serverless? It's still on some server!!" discussions.

... in the human brain which has evolved "cores" to handle each task optimally.

It's like the Turing Test. If it looks like it's reasoning, does it matter that it's doing it like a human brain or not?

The method is irrelevant. The output is what matters.

This is like a bunch of intelligent robots arguing that "mere meat" cannot possibly be intelligent!

https://www.mit.edu/people/dpolicar/writing/prose/text/think...

It will give you detailed examples that are much easier to follow than vague, error-prone spec docs. That's scratching the surface. Other people are far more creative than me and have used chat-gpt for mind-blowing stuff already. Whatever its doing passes for 'reasoning' and 'intelligence' in my book. To me it doesn't matter whether its the same kind of intelligence as a human or if there's any amount of awareness as those are both philosophical questions of no consequence to my work.

For what these pieces of tech can do I feel that they're drastically under-utilized.

Except for the last point and the desktop version I think it's already done in math demo video.

I guess it will also pretty soon refuse to let me come back inside the spaceship, but until then it'll be a nice ride.

But I would like to see how this is integrated into applications by third party developers where the AI is doing a specific job. Is it still as impressive?

The biggest challenge I've had with building any autonomous "agents" with generic LLM's is they are overly gullible and accommodating, requiring the need to revert back to legacy chatbot logic trees etc. to stay on task and perform a job. Also STT is rife with speaker interjections, leading to significant user frustrations and they just want to talk to a person. Hard to see if this is really solved yet.

I’ve found that you can create declarative logic trees from JSON and use that as a prompt for the LLM, which it can then use to traverse the tree accordingly. The only issue I’ve encountered is when it wants to jump to part of the tree which is invalid in the current state. For example, you want to move a user into a flow where certain input is required, but the input hasn’t been provided yet. A transition is suggested to the program by the LLM, but it’s impossible so the LLM has to be prompted that the transition is invalid and to correct itself. If it fails to transition again, a default fallback can be given but it’s not ideal at all.

However, another nice aspect of having the tree declared in advance is that it shows human beings what the system is capable and how it’s intended to be used as well. This has proven to be pretty useful, as letting the LLM call functions it sees fit based on broad intentions and system capabilities leaves humans in the dark a bit.

So, I like the structure and dependability. Maybe one day we can depend on LLM magic and not worry about a team understanding the ins and outs of what should or shouldn’t be possible, but we don’t seem to be there yet at all. That could be in part because my prompts were bad, though.

Since it has an okay grasp on how finite state machines and XState work, it seems to do a good job of navigating the tree properly and reliably. It essentially does so by outputting information it thinks the state machine should use as a transition in a JSON object which gets parsed and passed to a transition function. This would fail occasionally so there was a recursive “what’s wrong with this JSON?” prompt to get it to fix its own malformed JSON, haha. That was meant to be a temporary hack but it worked well, so it stayed. There were a few similar tools for trying to correct errors. That might be one of the strangest developments in programming for me… Deploying non-deterministic logic to fix itself in production. It feels wrong, but it works remarkably well. You just need sane fallbacks and recovery tactics.

It was a proprietary project so I can’t share the source, but I think reading up on XState JSON configuration might explain most of it. You can describe most of your machine in a serializable format.

You can actually store a lot of useful data in state names, context, meta, and effect/action names to aid with the prompting and weaving state flows together in a language-friendly way. I also liked that the prompt would be updated by information that went along with the source code, so a deployment would reliably carry the correct information.

The LLM essentially hid a decision tree from the user and smoothed over the experience of navigating it through adaptive and hopefully intuitive language. I’d personally prefer to provide more deterministic flows that users can engage with on their own, but one really handy feature of this was the ability to jump out of child states into parent states without needing to say, list links to these options in the UI. The LLM was good at knowing when to jump from leaves of the tree back up to relevant branches. That’s not always an easy UI problem to solve without an AI to handle it for you.

edit: Something I forgot to add is that the client wanted to be able to modify these trees themselves, so the whole machine configuration was generated by a graph in a database that could be edited. That part was powered by Strapi. There was structured data in there and you could define a state, list which transitions it can make, which actions should be triggered and when, etc. The client did the editing directly in Strapi with no special UI on top.

Their objective is surveying people in a more engaging and personable way. They really wanted surveys which adapt to users rather than piping people through static flows or exposing them to redundant or irrelevant questions. Initially this was done with XState and no LLM (it required some non-ideal UI and configuration under the hood to make those jumps to parent states I mentioned, but it worked), and I can't say how effective it is but they really like it. The AI hype was very very strong on that team.

This is not using TTS or STT. Audio and Image data can be tokenized as readily as text. This is simply a LLM that happens to have been trained to receive and spit out audio and image tokens as well as text tokens. Interjections are a lot more palatable in this paradigm as most of the demos show.

I would wager like 100:1 that this is just introducing some TTS/STT layers. The video processing layer is probably also doing something similarly, by taking an extremely limited number of 'screenshots', carrying out typical image captioning using another layer, and then feeding that as an input. So the demo, to me, seems most likely to just be 3 separate 'plugins' operating in unison - text to speech, speech to text, and image to text.

The interjections are likely just the software being programmed to aggressively begin output following any lull after an input pattern. Note in basically all the videos, the speakers have to repeatedly cut off the LLM as it starts speaking in conversationally inappropriate locations. In the main video which is just an extremely superficial interaction, the speaker made sure to be constantly speaking when interacting, only pausing once to take a breath that I noticed. He also struggled with the timing of his own responses as the LLM still seems to be attached to its typical, and frequently inappropriate, rambling verbosity (though perhaps I'm not one to critique that).

Literally the first paragraph of the linked blog.

"GPT-4o (“o” for “omni”) is a step towards much more natural human-computer interaction—it accepts as input any combination of text, audio, and image and generates any combination of text, audio, and image outputs."

Then

"Prior to GPT-4o, you could use Voice Mode to talk to ChatGPT with latencies of 2.8 seconds (GPT-3.5) and 5.4 seconds (GPT-4) on average. To achieve this, Voice Mode is a pipeline of three separate models: one simple model transcribes audio to text, GPT-3.5 or GPT-4 takes in text and outputs text, and a third simple model converts that text back to audio. This process means that the main source of intelligence, GPT-4, loses a lot of information—it can’t directly observe tone, multiple speakers, or background noises, and it can’t output laughter, singing, or express emotion.

With GPT-4o, we trained a single new model end-to-end across text, vision, and audio, meaning that all inputs and outputs are processed by the same neural network."

But I’m not an expert!

STT throws away a lot of information that is clearly being preserved in a lot of these demos so that's definitely not happening here in that sense. That said, the tokens would be merged to a shared embedding space. Hard to say how they are approaching it exactly.

----

The phrase "*laughter* Yeah, I'm sure that's right" appears to be expressing sarcasm or skepticism about whatever was previously said or suggested. Here's a breakdown of its likely meaning:

"*laughter*" - This typically indicates the speaker is laughing, which can signal amusement, but in this context suggests they find whatever was said humorous in an ironic or disbelieving way.

"Yeah," - This interjection sets up the sarcastic tone. It can mean "yes" literally, but here seems to be used facetiously.

"I'm sure that's right." - This statement directly contradicts and casts doubt on whatever was previously stated. The sarcastic laughter coupled with "I'm sure that's right" implies the speaker believes the opposite of what was said is actually true.

So in summary, by laughing and then sarcastically saying "Yeah, I'm sure that's right," the speaker is expressing skepticism, disbelief or finding humor in whatever claim or suggestion was previously made. It's a sarcastic way of implying "I highly doubt that's accurate or true."

----

You can't exactly metadata your way out of this (skip to 11:50)

https://www.youtube.com/live/DQacCB9tDaw?si=yN7al6N3C7vCemhL

But if the system can create a flamboyantly homosexual Captain Picard with a lisp and slight stutter engaging in overt innuendo when stating, "Number one, Engage!" then I look forward to eating crow! But as the instructions were all conspicuously just "swap to pretrained voice [x,y,z]", I suspect crow will not be on the menu any time soon.

MoE are attempts at sparsity, only activating a set number of neurons/weights at a time. They're not separate models stitched together. They're not an Ensemble. I blame the name at this point.

These demos show people talking to artificial intelligence. This is new. Humans are more partial to talking than writing. When people talk to each other (in person or over low-latency audio) there's a rich metadata channel of tone and timing, subtext, inexplicit knowledge. These videos seem to show the AI using this kind of metadata, in both input and output, and the conversation even flows reasonably well at times. I think this changes things a lot.

I'm also incredibly excited about the possibility of this as an always available coding rubber duck. The multimodal demos they showed really drove this home, how collaboration with the model can basically be as seamless as screensharing with someone else. Incredible.

I know this won't happen, of course, I am moreso hoping for laws to be updated to avoid similar kerfuffles in the future, as well as massive fines to act as a deterrent, but I don't dare to hope too much.

> have all of OpenAI's data for free

Doesn't really fit. Perhaps OpenAI might successfully prevent us from accessing it, but it wouldn't be "theirs" and we couldn't "have" it.

I'm not sure what kind of conversations we will be having instead, but I expect they'll be more productive than worrying about ownership of something you can't touch.

Humanity only survives as much as it preserves human dignity, let's say. We've designed society to give rewards to people who produce things of value.

These companies take that value and giving nothing back to the creators.

Supporting this will lead to disaster for all but the few, and ultimately for the few themselves.

Paying for your (copyrighted) inputs is harmony.

I think it’s likely that the justice system will deem model training as fair use, provided that the models are not designed to exactly reproduce the training data as output.

I think you hit on an important point though: these models are a giant transfer of wealth from creators to consumers / users. Now anyone can acquire artist-grade art for any purpose, basically for free — that’s a huge boon for the consumer / user.

People all around the world are going to be enriched by these models. Anyone in the world will be able to have access to a tutor in their language who can teach them anything. Again, that is only possible because the models eat ALL the data.

Another important point: original artwork has been made almost completely obsolete by this technology. The deed is done, because even if you push it out 70 years, eventually all of the artwork that these models have been trained on will be public domain. So, 70 years from now (or whatever it is) the cat will be out of the bag AND free of copyright obligations, so 2-3 generations from now it will be impossible to make a living selling artwork. It’s done.

When something becomes obsolete, it’s a dead man walking. It will not survive, even if it may take a while for people to catch up. Like when the vacuum tube computer was invented, that was it for relay computers. Done. And when the transistor was invented, that was it for vacuum tube computers.

It’s just a matter of time before all of today’s data is public domain and the models just do what they do.

…but people still build relay computers for fun:

https://youtu.be/JZyFSrNyhy8?si=8MRNznoNqmAChAqr

So people will still produce artwork.

There's zero doubt that people will still create art. Almost no one will be paid to do it though (relative to our current situation where there are already far more unpaid artists than paid ones). We'll lose an immeasurable amount of amazing new art that "would have been" as a result, and in its place we'll get increasingly bland/derivative AI generated content.

Much of the art humans will create entirely for free in whatever spare time they can manage after their regular "for pay" work will be training data for future AI, but it will be extremely hard for humans to find as it will be drowned out by the endless stream of AI generated art that will also be the bulk of what AI finds and learns from.

Either everybody should get the benefits of this technology, or no one should.

If you give it access to the entire codebase at the same time that could work pretty well. Maybe even add an option to disable the sarcasm.

I was literally just thinking about this a few days ago... that we need a multi-modal language model with speech training built-in.

As soon as this thing rolls out, we'll be talking to language models like we talk to each other. Previously it was like dictating a letter and waiting for the responding letter to be read to you. Communication is possible, but not really in the way that we do it with humans.

This is MUCH more human-like, with the ability to interrupt each other and glean context clues from the full richness of the audio.

The model's ability to sing is really fascinating. It's ability to change the sound of its voice -- its pacing, its pitch, its tonality. I don't know how they're controlling all that via GPT-4o tokens, but this is much more interesting stuff than what we had before.

I honestly don't fully understand the implications here.

Is that because you're not used to it? Honestly asking.

This is probably the first time it feels natural where as all our previous experiences make "chat bots" and "automated phone systems", "automated assistants" absolutely terrible.

Naturally, we dislike it because "it's not human". But this is true of pretty much any thing that approaches "uncanny valley". But, if the "it's not human" solves your answer 100% better/faster than the human counter part, we tend to accept it a lot faster.

This is the first real contender. Siri was the "glimpse" and ChatGPT is probably the reality.

[EDIT]

https://vimeo.com/945587328 the Khan academy demo is nuts. The inflections are so good. It's pretty much right there in the uncanny valley because it does still feel like you're talking to a robot but it also directly interacting with it. Crazy stuff.

That wasn't even my impression.

My impression was that it reminds me of the humans that I dislike.

It speaks in customer service voice. That faux friendly tone people use when they're trying to sell you something.

Mmmmm while I get that, in the context w/ the grandparent comment, having a human wouldn't be better then? It's effectively the same. Because, realistically that's a pretty common voice/tone to get even in tech support.

There are different kinds of humans.

Some of them are your friends, and they're willing to take risks for you and they take your side even when it costs them something.

Some of them are your adversaries, overtly. They do not hide it.

Some of them pretend to be your friends, even though they're not. And that's what they modeled it on. For some reason.

The problem is you don't like the customer service/sales voice because they "pretend to be your friends".

Let me know if I didn't capture it.

I don't think people "pretend to be my friend" when they answer the phone to help me sort out of airline ticket problem. I do believe they're trained to and work to take on a "friendly" tone. Even if the motive isn't genuine, because it's trained, it's way a nicer of an experience than someone who's angry or even simply monotone. Trying to fix my $1200 plane ticket is stressful enough. Don't need the CSR to make it worse.

Really? I found this demo painful to watch and literally felt that "cringe" feeling. I showed it to my partner and she couldn't even stand to hear more than a sentence of the conversation before walking away.

It felt both staged and still frustrating to listen to.

And, like far too much in AI right now, a demo that will likely not pan out in practice.

Especially when you consider the bottom line that this tech will be ultimately be horned into advertising somehow (read: the field dedicated to manipulating you into buying shit).

This whole fucking thing bothers me.

When one gets to be a certain age one begins to become attuned to this tendency of others' emotions to manipulate you, so you take steps to not let that happen. You're not ignoring their emotions, but you can address the underlying issue more effectively if you're not emotionally charged. It's a useful skill that more people would benefit from learning earlier in life. Perhaps AI will accelerate that particular skill development, which would be a net benefit to society.

Most manipulators end up getting bored of trying again and again with the same person. That won't happen if you are a dealing with a machine, as it can change names, techniques, contexts, tones, etc. until you give it what its operator wants.

Maybe you're part of the X% who will never give in to a machine. But keep in mind that most people have no critical thinking skills nor mental fortitude.

This is incredibly optimistic, which I love, but my own experience with my utterly deranged elder family, made insane by TV, contradicts this. Every day they're furious about some new things fox news has decided it's time to be angry about: white people being replaced (thanks for introducing them to that, tucker!), "stolen" elections, Mexicans, Muslims, the gays, teaching kids about slavery, the trans, you name it.

I know nobody else in my life more emotionally manipulated on a day to day basis than them. I imagine I can't be alone in watching this happen to my family.

Great replacement and white genocide are white nationalist far-right conspiracy theories. If you believe this is happening, you are the intellectual equivalent of a flat-earther. Should we pay attention to flat-earthers? Are their opinions on astronomy, rocketry, climate, and other sciences worth anyone's time? Should we give them a platform?

> In the words of scholar Andrew Fergus Wilson, whereas the islamophobic Great Replacement theory can be distinguished from the parallel antisemitic white genocide conspiracy theory, "they share the same terms of reference and both are ideologically aligned with the so-called '14 words' of David Lane ["We must secure the existence of our people and a future for white children"]." In 2021, the Anti-Defamation League wrote that "since many white supremacists, particularly those in the United States, blame Jews for non-white immigration to the U.S.", the Great Replacement theory has been increasingly associated with antisemitism and conflated with the white genocide conspiracy theory. Scholar Kathleen Belew has argued that the Great Replacement theory "allows an opportunism in selecting enemies", but "also follows the central motivating logic, which is to protect the thing on the inside [i.e. the preservation and birth rate of the white race], regardless of the enemy on the outside."

https://en.wikipedia.org/wiki/Great_Replacement

https://en.wikipedia.org/wiki/White_genocide_conspiracy_theo...

> wanting border laws to be enforced

Border laws are enforced.

> and not wanting your children to be groomed into cutting off their body parts.

This doesn't happen. In fact, the only form of gender-affirming surgery that any doctor will perform on under-18 year olds is male gender affirming surgery on overweight boys to remove their manboobs.

> You are definitely sane and your entire family is definitely insane.

You sound brave, why don't you tell us what your username means :) You're one to stand by your values, after all, aren't you?

Why did you pick that username?

That happens with a lot of tech. Social networks are used to con people more than to educate people about con men.

Tools and the weaponization of them.

This can be said of pretty much any tech tool that has the ability to touch a good portion of the population, including programming languages themselves, CRISPR?

I agree we have to be careful of the bad, but the downsides in this case are not so dangerous that we should be trying to suppress it because the benefits can be incredible too.

Start telling Grandma never to answer the phone.

Silly example, but some pets like guinea pigs are almost always hungry and they're famous for learning to squeak at you whenever you open the fridge or do anything that might lead to giving them bell peppers. It's not something you'd put up with a human family member using their communication skills to do!

Sorry, had to be that trekkie :) and nice job referencing Measure of a Man — such great trek.

We get the upside of conversation, and avoid the downside of falling asleep at the wheel (as Ethan Mollick mentions in "Co-Intelligence".)

Is it so?

Speaking most of the time is for short exchange of information (pleasantries to essential information exchanges).

I prefer writing for long in-depth thought exchanges (whether by emails, blogs etc.)

In many cultures - European or Asian, people are not very loquacious in everyday life.

I’m 100% a text everything never calls person but I can’t live without Alexa these days, every time I’m in a hotel or on vacation I nearly ask a question out loud.

I also hate how much Alexa sucks so this is a big deal. I spent years weeding out what it could do and can’t do so it will be nice to have one that I don’t have to treat like a toddler

Amazon, Google, and Apple have sunk literally billions of dollars into this idea only to find out that, no, we aren't.

We are with other humans, yes. When socialization is part of the conversation. When I'm talking to my local barista I'm not just ordering a coffee, I'm also maintaining a relationship with someone in my community.

But when it comes to work, writing >>> talking. Writing is clarity of ideas. Talking is cult of personality.

And when it comes to inputs/outputs, typing is more precise and more efficient.

Don't get me wrong, this is an incredibly revolutionary piece of technology, but I don't think the benefits of talking you're describing (timing, subtext, inexplicit knowledge) are achievable here either (for now), since even that requires HOURS of interaction over days/weeks/months of experiences for humans to achieve with each other.

>>> But when it comes to work, writing >>> talking. Writing is clarity of ideas. Talking is cult of personality.

A lot of people think of their colleagues as part of a professional community as well, though.

For example, I mentioned something to my contractor and the short thing he said back and his tone had me assume he understood.

Oh, he absolutely did not.

And, with him at least, that doesn’t happen when in writing.

https://www.theonion.com/brain-dead-teen-only-capable-of-rol...

The generation after me are lazy and stupid

Only my generation is perfect.

- every generation ever

Older people think younger people are stupid and reckless, and viceversa. And the younglings think they "figured it out" like no one before them. But no one ever tried to understand each other in the process. Rinse and repeat.

It's really how it works.

Winner of the 'understatement of the week' award (and it's only Monday).

Also top contender in the 'technically correct' category.

Yes! As soon as I saw gdb I was like "that can't be Greg", but sure enough, that's him.

I helped her access the video from the presentation, and it brought her to tears. Now, she can play guitar, and the AI and her can write songs and sing them together.

This is a big day in the lives of a lot of people whom aren't normally part of the conversation. As of today, they are.

0: https://www.bemyeyes.com/

Eventually it would be better for these models to run locally from a security point if view, but this is a great first step.

[1] https://www.amazon.com/Het-geheim-verdwenen-mysterie-Dutch/d...

I don't need to imagine that, I've had it for about 8 years. It's OK.

> help you grocery shop without an assistant

Isn't this something you learn as a child? Is that a thing we need automated?

Seems like these would be similar.

Even styles of thought might be different in other languages, so I don't say that lightly... (stay strong, Sapir-Wharf, stay strong ;)