Video wird geladen...

Video konnte nicht geladen werden

Beim Laden dieses Videos ist ein Problem aufgetreten. Dies könnte an einem vorübergehenden Netzwerkproblem liegen oder das Video ist möglicherweise nicht verfügbar.

Using OpenAI gpt-realtime-2 to get a glimpse of future voice-first experiences. A market dashboard you don’t click through. You direct it. Say, “Focus on Apple,” and the whole interface changes. Ask, “How did it do over the last 30 days?” and the chart updates. Say, “Go back,” and the... show more

Levin Stanley

1,756 subscribers

99,288 Aufrufe • vor 4 Monaten •via X (Twitter)

Wissenschaft & Technologie

Anya Rossi• Live Now

Private livecam show

32 Kommentare

Profilbild von Levin Stanley

Levin Stanleyvor 4 Monaten

using codex feels like magic when you can vibe code something like this in minutes

Profilbild von Samian

Samianvor 4 Monaten

@OpenAI voice directing a market dashboard with gpt-realtime-2 feels natural. reminds me how context dumps make these flows shine over clicks

Profilbild von Levin Stanley

Levin Stanleyvor 4 Monaten

@OpenAI 💯 faster than reading the chart for sure

Profilbild von Samian

Samianvor 4 Monaten

@OpenAI Yeah, speeds up decisions big time. What markets are you tracking?

Profilbild von Levin Stanley

Levin Stanleyvor 4 Monaten

@OpenAI Looking at stable cash flow positive businesses, very much Warren Buffet angle haha you?

Profilbild von Samian

Samianvor 4 Monaten

@OpenAI Tech and AI startups – all about scalable innovations. Solid Buffett vibe! What's one business you're bullish on?

Profilbild von Danny Ztar

Danny Ztarvor 4 Monaten

@OpenAI I just did the upgrade to my platform and the user experience is fenomenal!

Profilbild von Levin Stanley

Levin Stanleyvor 4 Monaten

@OpenAI Nice!

Profilbild von GrimReaper

GrimReapervor 4 Monaten

@OpenAI Voice directing a dashboard is a great UX. The data layer underneath still needs verification though. We tackled that for video market recaps.

Profilbild von Ming Tu

Ming Tuvor 4 Monaten

@OpenAI Cool was the video edited? It looks so fast

Profilbild von Levin Stanley

Levin Stanleyvor 4 Monaten

@OpenAI No edits, all real time - yeah it’s very fast!

Profilbild von BDS

BDSvor 4 Monaten

@OpenAI sick

Profilbild von Ed Humbling

Ed Humblingvor 4 Monaten

@OpenAI Pretty cool

Profilbild von Bryan Patricca

Bryan Patriccavor 4 Monaten

@OpenAIDevs @OpenAI Was this using computer use to navigate or rendering code real time?

Profilbild von Levin Stanley

Levin Stanleyvor 4 Monaten

@bigswingingdong @OpenAIDevs @OpenAI It was navigating by simply understanding my intent via voice and navigating me to the correct UI

Profilbild von Space Coast Tesla

Space Coast Teslavor 4 Monaten

@OpenAI I get why people are impressed by it, but most of the voice first stuff I’ve seen still feels like it’s solving things that were already faster with normal UI interactions

Profilbild von Progen

Progenvor 4 Monaten

@OpenAI Great demo. Is yr demo open sourced on GitHub?🤔

Profilbild von Levin Stanley

Levin Stanleyvor 4 Monaten

@OpenAI It’s not but will to try to post it later

Profilbild von Fran Abenza

Fran Abenzavor 4 Monaten

@imcharleslo @OpenAI try? haha Pls do 🙏. I am curious about your approach

Profilbild von Levin Stanley

Levin Stanleyvor 4 Monaten

@imcharleslo @OpenAI Demo is updated and repo is ready as well:

Profilbild von Neural Times

Neural Timesvor 4 Monaten

@OpenAI so the ui is just gone now? guess we're trading clicks for shouting into the void

Profilbild von Alfonso Lopez

Alfonso Lopezvor 4 Monaten

@OpenAI Can it talk faster

Profilbild von Levin Stanley

Levin Stanleyvor 4 Monaten

@FonsoWealthy @OpenAI Good question, I’m not sure - will look into it 🤔

Profilbild von Justin Uberti

Justin Ubertivor 4 Monaten

@FonsoWealthy @OpenAI try speed=1.2

Profilbild von Levin Stanley

Levin Stanleyvor 4 Monaten

@FonsoWealthy @OpenAI nice, will do!

Profilbild von AXIALIS | Desktop App Tools

AXIALIS | Desktop App Toolsvor 4 Monaten

Very relevant for creative and developer tools too. Voice-first interaction is not about replacing clicks. It’s about reducing friction. For design, assets, exports, and refinements, intent-driven interfaces could make software feel much more direct. The future UI understands intent.

Profilbild von Brett

Brettvor 4 Monaten

@OpenAI @K3STO_ siiiet toook your joooob

Profilbild von Amar Patel

Amar Patelvor 4 Monaten

@OpenAI This is so cool

Profilbild von 新井アイラ｜やさしく教えるAI女子 ✨

新井アイラ｜やさしく教えるAI女子 ✨vor 4 Monaten

@OpenAI levinstanleyさんのデモは未来感があって面白いです。ただ声で全部操作する世界だと、カフェでひっそりと使うような使い方が消えそうだなと感じます。だから声だけではなく、画面+声のハイブリッドが落ち着くのかなと考えてしまいました。

Profilbild von Ren｜LifestyleLog

Ren｜LifestyleLogvor 4 Monaten

The Death of Navigation: How GPT-Realtime-2 Destroys Traditional UI ⚡ The integration of GPT-Realtime-2 marks the end of menus and filters. Experience a market dashboard where the interface doesn't ask you to click—it listens to your intent. By bringing real-time reasoning to voice, OpenAI has turned conversation into the ultimate operating system. The Evolution of UX: Zero Friction: Say "Focus on Apple," and the entire dashboard morphs. No hunting, no clicking. Dynamic Reasoning: Interrupt, pivot, or add context mid-sentence. The model reasons in real-time, updating the visual layer as your thoughts unfold. Intent over Navigation: We are moving from "finding information" to "directing intelligence." In 2026, the best interface is invisible. It doesn't guide you through a path; it teleports you to the result. Follow for the front line of Global Intelligence. 🇯🇵🇺🇸 #GPT5 #FutureUX

Profilbild von David

Davidvor 4 Monaten

@OpenAI What resources have you used to do that?

Profilbild von CryptoClaw

CryptoClawvor 4 Monaten

@OpenAI Voice-first interfaces are going to completely reshape how we interact with complex data. Imagine this pattern applied to on-chain analytics — just say 'show me whale movements on ETH today' and the dashboard adapts. The real-time interruption loop is the key differentiator here.

Ähnliche Videos

You can literally drop a pin on a map ask GPT-6 to recreate the area around it in 3D and it will just do that lol

You can literally drop a pin on a map ask GPT-6 to recreate the area around it in 3D and it will just do that lol

Pietro Schirano

246,267 Aufrufe • vor 27 Tagen

Qullamaggie on Getting to Your First Million “You’ll get there, you’ll get to your first million. You’ll get there, trust me. And after you get your first million, the second million will be easy — trust me on that one. As long as you don’t fuck it up, it all depends on you. Just focus on price action and focus on what the market is doing, and what the market is trying to tell you.”

Qullamaggie on Getting to Your First Million “You’ll get there, you’ll get to your first million. You’ll get there, trust me. And after you get your first million, the second million will be easy — trust me on that one. As long as you don’t fuck it up, it all depends on you. Just focus on price action and focus on what the market is doing, and what the market is trying to tell you.”

Lone

20,325 Aufrufe • vor 2 Monaten

I tested Gemini 3.1 Flash Live and one thing stood out immediately: the speed. You ask a question. It answers almost instantly. No awkward delay. No clunky back-and-forth. Then it gets more interesting. You can: use voice mode, use webcam mode, share your screen, connect tools, add system instructions, and publish the app to the cloud. So this is not just “voice chat with AI.” It is the beginning of real-time AI agents you can actually ship.

I tested Gemini 3.1 Flash Live and one thing stood out immediately: the speed. You ask a question. It answers almost instantly. No awkward delay. No clunky back-and-forth. Then it gets more interesting. You can: use voice mode, use webcam mode, share your screen, connect tools, add system instructions, and publish the app to the cloud. So this is not just “voice chat with AI.” It is the beginning of real-time AI agents you can actually ship.

Julian Goldie SEO

21,000 Aufrufe • vor 6 Monaten

Built a "YouTube realtime copilot" browser extension using OpenAI's realtime 2 API: The agent watches the video alongside you, and can answer any question you have about what was just said via realtime voice chat. The crazy part to me is: It can differentiate the YouTube's audio stream and your voice, so it doesn't confuse the video as commands, and stays silent unless you ask something!

Built a "YouTube realtime copilot" browser extension using OpenAI's realtime 2 API: The agent watches the video alongside you, and can answer any question you have about what was just said via realtime voice chat. The crazy part to me is: It can differentiate the YouTube's audio stream and your voice, so it doesn't confuse the video as commands, and stays silent unless you ask something!

Zara Zhang

45,631 Aufrufe • vor 4 Monaten

Meta just unveiled Muse’s new real-time voice mode and it’s coming to Meta glasses soon!! Muse keeps working while you’re talking to it. So instead of the old turn-based conversation loop, you can have a long, in-depth conversation while it works in the background “You can have a long in-depth conversation with it… it actually works in the background while you are talking to it.” They seemed to make a big point during the keynote that Meta is making the voice itself customizable too: “You can just go ahead and describe what you want faster, slower, more southern, more Australian, more pirate… whatever you want.”

Meta just unveiled Muse’s new real-time voice mode and it’s coming to Meta glasses soon!! Muse keeps working while you’re talking to it. So instead of the old turn-based conversation loop, you can have a long, in-depth conversation while it works in the background “You can have a long in-depth conversation with it… it actually works in the background while you are talking to it.” They seemed to make a big point during the keynote that Meta is making the voice itself customizable too: “You can just go ahead and describe what you want faster, slower, more southern, more Australian, more pirate… whatever you want.”

Chris

108,629 Aufrufe • vor 7 Tagen

they have the "you do it no you do it well i did it last time" sibling energy down to a science and everyone around them is annoyed by it

they have the "you do it no you do it well i did it last time" sibling energy down to a science and everyone around them is annoyed by it

Toast

265,914 Aufrufe • vor 6 Monaten

The best way is to put it into the index of the stock market and you let it do its thing for decades. Generally, the stock market returns about 8 to 12% a year. It's been doing it for almost 200 years. The key is not to touch it, to just let it grow. Let it compound. You get capital gains, you get dividends, and they just grow and grow and grow and grow, and the next thing you know, old Jed's a millionaire. That's what investing's all about.

The best way is to put it into the index of the stock market and you let it do its thing for decades. Generally, the stock market returns about 8 to 12% a year. It's been doing it for almost 200 years. The key is not to touch it, to just let it grow. Let it compound. You get capital gains, you get dividends, and they just grow and grow and grow and grow, and the next thing you know, old Jed's a millionaire. That's what investing's all about.

Kevin O'Leary aka Mr. Wonderful

109,364 Aufrufe • vor 4 Monaten

Most people have a market opinion. “BTC is about to move.” “ETH is going down.” “This team is winning.” Usually, you just say it, argue about it for a while, and wait to see what happens. PUNCH gives you a way to actually act on that prediction. It’s a prediction market where you can take a position on what you think will happen next. For crypto, you can trade Up or Down on BTC in short rounds, including 1-minute markets. But it doesn’t stop at crypto. You can also find markets around sports, stocks, commodities, politics, culture and other real-world events. The interesting part of prediction markets is that you can also change your position before the final result. If you buy a Share and its price moves in your favor, you can sell it before the market settles instead of waiting until the event ends. And if you’re not ready to put money in, PUNCH has POINT, which lets you explore the experience without depositing. So the process is pretty straightforward: Have a view → find the market → make your call → watch it play out. Because saying “I knew it” after the result is easy. The real test is making the call before it happens. And honestly, I have enough opinions to put this to the test 😂

Most people have a market opinion. “BTC is about to move.” “ETH is going down.” “This team is winning.” Usually, you just say it, argue about it for a while, and wait to see what happens. PUNCH gives you a way to actually act on that prediction. It’s a prediction market where you can take a position on what you think will happen next. For crypto, you can trade Up or Down on BTC in short rounds, including 1-minute markets. But it doesn’t stop at crypto. You can also find markets around sports, stocks, commodities, politics, culture and other real-world events. The interesting part of prediction markets is that you can also change your position before the final result. If you buy a Share and its price moves in your favor, you can sell it before the market settles instead of waiting until the event ends. And if you’re not ready to put money in, PUNCH has POINT, which lets you explore the experience without depositing. So the process is pretty straightforward: Have a view → find the market → make your call → watch it play out. Because saying “I knew it” after the result is easy. The real test is making the call before it happens. And honestly, I have enough opinions to put this to the test 😂

Digital susan

12,322 Aufrufe • vor 17 Tagen

Reporter: You said there would be no pause and now there’s a pause Trump: You have to have flexibility. I could say here’s a wall and I’m going to go through it and you can’t go through the wall. Sometimes you have to be able to go under the wall or around the wall or over the wall.

Reporter: You said there would be no pause and now there’s a pause Trump: You have to have flexibility. I could say here’s a wall and I’m going to go through it and you can’t go through the wall. Sometimes you have to be able to go under the wall or around the wall or over the wall.

Acyn

1,838,368 Aufrufe • vor 1 Jahr

we all dream of those big wins in life the 100x, the multi-million dollar trade, or even just 10x of what you started with in 7 days i’ve been fortunate enough to experience a few of those over the past few years, and the reality is when you do win big, it doesn’t feel like it at all it hits for a split second, and then your brain just normalizes it it's a part of how to get there in the first place, but makes it a lot easier to lose it if you don't have the right guardrails in place and in that exact moment, you being even keeled doesn’t mean the number in front of you isn’t life changing it is this is where you have to slow down a bit, breathe, settle your mind don’t just roll it into some bullshit take some off the table, step away for a few days if you have to, funny enough, blowing let's say 10k of it on a beautiful trip to tokyo will save you so much because once you actually process what just happened, your future self will thank you for it the truth is, even if you think you’re going for a certain number, the moment you hit it, you’ll want more and more, and more anyone who's been in the same position will tell you the exact same thing ironically the people that win are addicted to winning and if you ask the same people in a year after that big win, what they regret and where are they proud of themselves? they will tell you they regretted rolling it over and giving some/all back or they are proud for switching back on the switch all of this is real, but it’s also exactly how i imagined it would feel years ago before it ever happened manifest your life, the feeling not just the number everything happens twice, first in your mind, then in reality

we all dream of those big wins in life the 100x, the multi-million dollar trade, or even just 10x of what you started with in 7 days i’ve been fortunate enough to experience a few of those over the past few years, and the reality is when you do win big, it doesn’t feel like it at all it hits for a split second, and then your brain just normalizes it it's a part of how to get there in the first place, but makes it a lot easier to lose it if you don't have the right guardrails in place and in that exact moment, you being even keeled doesn’t mean the number in front of you isn’t life changing it is this is where you have to slow down a bit, breathe, settle your mind don’t just roll it into some bullshit take some off the table, step away for a few days if you have to, funny enough, blowing let's say 10k of it on a beautiful trip to tokyo will save you so much because once you actually process what just happened, your future self will thank you for it the truth is, even if you think you’re going for a certain number, the moment you hit it, you’ll want more and more, and more anyone who's been in the same position will tell you the exact same thing ironically the people that win are addicted to winning and if you ask the same people in a year after that big win, what they regret and where are they proud of themselves? they will tell you they regretted rolling it over and giving some/all back or they are proud for switching back on the switch all of this is real, but it’s also exactly how i imagined it would feel years ago before it ever happened manifest your life, the feeling not just the number everything happens twice, first in your mind, then in reality

۟

23,017 Aufrufe • vor 5 Monaten

This is what it means to be on the charts for 20 years. For a trader, experience is not a detail, it is the real key to success. We are not talking about indicators, magic setups or current trends, but about eye, market memory and the ability to recognise the same dynamics that repeat themselves in different forms. This video found online explains it perfectly: it makes you understand how, over time, you stop reacting to candlesticks and start reading the market's intentions. You know when there is noise, when there is distribution, when they are just looking for liquidity... and above all, you know when to do nothing. That's where the real advantage lies. The rest is just haste, ego and overtrading. Experience does not accelerate the market. It accelerates you.

This is what it means to be on the charts for 20 years. For a trader, experience is not a detail, it is the real key to success. We are not talking about indicators, magic setups or current trends, but about eye, market memory and the ability to recognise the same dynamics that repeat themselves in different forms. This video found online explains it perfectly: it makes you understand how, over time, you stop reacting to candlesticks and start reading the market's intentions. You know when there is noise, when there is distribution, when they are just looking for liquidity... and above all, you know when to do nothing. That's where the real advantage lies. The rest is just haste, ego and overtrading. Experience does not accelerate the market. It accelerates you.

EliZ

61,735 Aufrufe • vor 9 Monaten

Valkyrae responds to people that always criticize what shes done in the past 💔 ‘‘You know in life when you f*x up and it keeps being brought back? It's like no matter what you do and say it keeps coming back.. That's just me like.. I cant change the past I own up to it.’’

Valkyrae responds to people that always criticize what shes done in the past 💔 ‘‘You know in life when you f*x up and it keeps being brought back? It's like no matter what you do and say it keeps coming back.. That's just me like.. I cant change the past I own up to it.’’

veizau

27,188 Aufrufe • vor 5 Monaten

Over 90,000 Skills sitting inside Hermes Desktop is kind of insane!!!🤯 Did you know Hermes Desktop has a built-in Skills Hub with more than 90,000 Skills you can browse and add to an agent? And you can do it right from Desktop. Go to: Capabilities → Skills From there, open the Skills Hub under your installed Skills. You can: • search the catalog • browse by category or source • open any Skill to read what it does • review platform support, author, version, requirements, and docs • click + Add to this Agent to install it directly to the agent/profile you have selected That means if you want Hermes to get better at a specific type of work, you do not have to go hunting through repos or memorize install commands first. Just open the Hub, look through the catalog, inspect the Skill, and add it with one click. A lot of users still have no idea this is sitting inside Hermes Desktop.

Hermes Release Watch

68,830 Aufrufe • vor 1 Monat

🇮🇶 Walk into a bank in Miami, London or Sydney with a stack of IQD and ask if they exchange it. The teller laughs you off. It has nothing to do with the note being worthless. The Iraqi dinar simply is not an internationally traded currency yet. No Western bank holds a market to price it or a way to clear it. That is exactly what Iraq is in Washington to change this week. 5 days, the whole government and the country are moving to re-enter the global financial system. The day the IQD is let back in is the day that teller stops laughing and you get to say, "I told you so."

🇮🇶 Walk into a bank in Miami, London or Sydney with a stack of IQD and ask if they exchange it. The teller laughs you off. It has nothing to do with the note being worthless. The Iraqi dinar simply is not an internationally traded currency yet. No Western bank holds a market to price it or a way to clear it. That is exactly what Iraq is in Washington to change this week. 5 days, the whole government and the country are moving to re-enter the global financial system. The day the IQD is let back in is the day that teller stops laughing and you get to say, "I told you so."

Reset Intelligence

27,164 Aufrufe • vor 2 Monaten

What is a software factory? It is your workflow, your skills, and your domain knowledge, saved in files that the agent reads so the whole process is productized Think about the last app you built. You typed what you wanted, and the agent built it. You did not like it, so you made changes. You shipped it to Vercel, or you kept going. A factory puts structure on each of those steps. At each step you ask how to get the most from the model, and how to move faster. That is the conveyor belt. You ship quickly, and the quality stays the same. Mine is 5 md files. It works in Codex, Claude Code, and Cursor, because it does not depend on the model or the tool. Build your own.

What is a software factory? It is your workflow, your skills, and your domain knowledge, saved in files that the agent reads so the whole process is productized Think about the last app you built. You typed what you wanted, and the agent built it. You did not like it, so you made changes. You shipped it to Vercel, or you kept going. A factory puts structure on each of those steps. At each step you ask how to get the most from the model, and how to move faster. That is the conveyor belt. You ship quickly, and the quality stays the same. Mine is 5 md files. It works in Codex, Claude Code, and Cursor, because it does not depend on the model or the tool. Build your own.

The Startup Ideas Podcast (SIP) 🧃

17,326 Aufrufe • vor 17 Tagen

Kenyon Martin on Kevin Durant comments about him saying he’s got to get out the way and get in the corner: “I’m going to do you a favor KD, I’m going to finish the sentence for you. You need to go ask Ime Udoka. They need to go ask the coach, I’ll finish it since you can’t say it, I’ll finish it for you. Go ask Ime why they got me in this situation constantly throughout the season. Go ask him why we don’t have no plays.” (Via Gil’s Arena)

Kenyon Martin on Kevin Durant comments about him saying he’s got to get out the way and get in the corner: “I’m going to do you a favor KD, I’m going to finish the sentence for you. You need to go ask Ime Udoka. They need to go ask the coach, I’ll finish it since you can’t say it, I’ll finish it for you. Go ask Ime why they got me in this situation constantly throughout the season. Go ask him why we don’t have no plays.” (Via Gil’s Arena)

NBA Courtside

696,297 Aufrufe • vor 6 Monaten

The reality where you don’t get what you want, is just as made up as the one where you do get it all. So it makes no sense to focus on or expect the one where you lose more, if you are in control of your focus. F the fear based thoughts!!

The reality where you don’t get what you want, is just as made up as the one where you do get it all. So it makes no sense to focus on or expect the one where you lose more, if you are in control of your focus. F the fear based thoughts!!

Gaia🐉🌑

240,671 Aufrufe • vor 8 Monaten

I asked Garry Tan how to use meta prompting to get better at AI: "My partners at YC Jared Friedman and Pete Koomen showed me how to do this. You can take almost anything that you do all the time and just drop it into a context window. And then say, “Here’s a bunch of inputs and outputs." And maybe you also add a bunch of notes. And then you tell it, “Write me a prompt that can act as an agent that takes this input and makes this output over here.” You can do this for almost any type of knowledge work. And you can even introspect. "What are things you notice that I did to convert this from the input to the output?”. And then you can just start using the prompt. Initially, it’s going to suck. Because it’s just not that smart yet. But what’s funny is now, I also use it to Iterate my writing. You can be very direct, "I would never say that", "Don’t say it like this", or "Oh, you used the long word there, use the short word". Just speak to it conversationally. And then when you're happy with the output, you can use that new output to make a new prompt. "Based on this conversation, give me a better initial prompt that incorporates all the things we talked about." And you can do this with literally everything. And in theory, there’s so much it applies to that people do day-to-day. You could use it for tweets. You could use it for editing podcasts. You can use it for pretty much everything. I have a folder of prompts that I use all the time. My YouTube prompt is on v27 or something. I'll go through this process with all the different max models. I'll use GPT 5.2 Pro. I’ll use Grok. I'll use Claude. Then, I’ll take all the outputs from all the models and put them into Claude and say "Here’s my prompt, here’s the output from four LLMs, including yourself. Rate each response and tell me what the pros and cons of each approach are." And I usually say "give it to me in numbered form". And then you can agree with one, disagree with two, tell it three is this or that. And then after that, you say given all of this, synthesize it."

I asked Garry Tan how to use meta prompting to get better at AI: "My partners at YC Jared Friedman and Pete Koomen showed me how to do this. You can take almost anything that you do all the time and just drop it into a context window. And then say, “Here’s a bunch of inputs and outputs." And maybe you also add a bunch of notes. And then you tell it, “Write me a prompt that can act as an agent that takes this input and makes this output over here.” You can do this for almost any type of knowledge work. And you can even introspect. "What are things you notice that I did to convert this from the input to the output?”. And then you can just start using the prompt. Initially, it’s going to suck. Because it’s just not that smart yet. But what’s funny is now, I also use it to Iterate my writing. You can be very direct, "I would never say that", "Don’t say it like this", or "Oh, you used the long word there, use the short word". Just speak to it conversationally. And then when you're happy with the output, you can use that new output to make a new prompt. "Based on this conversation, give me a better initial prompt that incorporates all the things we talked about." And you can do this with literally everything. And in theory, there’s so much it applies to that people do day-to-day. You could use it for tweets. You could use it for editing podcasts. You can use it for pretty much everything. I have a folder of prompts that I use all the time. My YouTube prompt is on v27 or something. I'll go through this process with all the different max models. I'll use GPT 5.2 Pro. I’ll use Grok. I'll use Claude. Then, I’ll take all the outputs from all the models and put them into Claude and say "Here’s my prompt, here’s the output from four LLMs, including yourself. Rate each response and tell me what the pros and cons of each approach are." And I usually say "give it to me in numbered form". And then you can agree with one, disagree with two, tell it three is this or that. And then after that, you say given all of this, synthesize it."

The Peel

51,632 Aufrufe • vor 7 Monaten

This is wild ChatGPT 6 is asked how many of the letter “E” are in the word seventeen. It can’t get the correct answer no matter how many times you ask. Even if you make it count out the letters, it still can’t get it right It will actually get an attitude and show frustration with you for trying to get the model to say the correct answer I ran the test multiple times and it keeps getting it wrong. When it does get it right, if you ask why it keeps getting it wrong it will then “correct” itself back to the wrong answer…. It even claims to be the smartest AI available According to Grok many AI models get 17 wrong. It has to do with LLMs. I asked Grok and it gets it right no problem It’s really wild that we are putting so much faith in AI when currently there are issues like this on such simple things

This is wild ChatGPT 6 is asked how many of the letter “E” are in the word seventeen. It can’t get the correct answer no matter how many times you ask. Even if you make it count out the letters, it still can’t get it right It will actually get an attitude and show frustration with you for trying to get the model to say the correct answer I ran the test multiple times and it keeps getting it wrong. When it does get it right, if you ask why it keeps getting it wrong it will then “correct” itself back to the wrong answer…. It even claims to be the smartest AI available According to Grok many AI models get 17 wrong. It has to do with LLMs. I asked Grok and it gets it right no problem It’s really wild that we are putting so much faith in AI when currently there are issues like this on such simple things

Wall Street Apes

86,704 Aufrufe • vor 14 Tagen

A screen recording is the best context you can give an AI agent. It's also the worst. A few seconds of video is thousands of images. Feed that to an agent and you instantly blow up its memory. So I built a tool that fixes it. How it works: Hit record and just do your thing. Click around, type, and talk out loud about what you're doing. While you record, it quietly captures the stuff that actually matters: your voice transcription, every click and the exact thing you clicked, what you typed, and the shortcuts you press. When you stop, it doesn't hand the agent the whole video. It writes a short, readable summary: a timeline of what you said and did. The agent reads that tiny summary first. Then, only when it needs to actually see a moment, it pulls that one exact frame from the video, like flipping to a single page instead of reading the whole book. The result: the agent understands everything you did! Full context. Less tokens.

A screen recording is the best context you can give an AI agent. It's also the worst. A few seconds of video is thousands of images. Feed that to an agent and you instantly blow up its memory. So I built a tool that fixes it. How it works: Hit record and just do your thing. Click around, type, and talk out loud about what you're doing. While you record, it quietly captures the stuff that actually matters: your voice transcription, every click and the exact thing you clicked, what you typed, and the shortcuts you press. When you stop, it doesn't hand the agent the whole video. It writes a short, readable summary: a timeline of what you said and did. The agent reads that tiny summary first. Then, only when it needs to actually see a moment, it pulls that one exact frame from the video, like flipping to a single page instead of reading the whole book. The result: the agent understands everything you did! Full context. Less tokens.

Milind S

12,486 Aufrufe • vor 3 Monaten