Загрузка видео...

Не удалось загрузить видео

Возникла проблема при загрузке этого видео. Это может быть связано с временными проблемами сети или видео может быть недоступно.

На главную

🚨PROOF THAT CONTEXT CHANGES EVERYTHING: STATIC BECOMES CRYSTAL CLEAR First listen: Robot having a stroke Add context: "It was a sunny day and the children were going to the park" Same audio now: Perfectly clear speech Now you can't unhear it. Your brain literally rewrites reality based on what... show more

Mario Nawfal

2,281,443 subscribers

32,638 просмотров • 1 год назад •via X (Twitter)

Наука и технологии Образование

Anya Rossi• Live Now

Private livecam show

Комментарии: 11

Фото профиля Shift

Shift1 год назад

Reality isn’t just what’s said it’s what your brain thinks was said. Context is the cheat code.

Фото профиля Craig

Craig1 год назад

Amazing. The first time the jumbled audio sounded, to me, lie Joe Biden trying to enunciate a coherent thought. I kid. That’s not possible lol. I kid again. Really this is an amazing window into how the brain works.

Фото профиля OhMyMy

OhMyMy1 год назад

Thanks for ruining the video with your text preface. 👍

Фото профиля Mobile Scanner

Mobile Scanner1 год назад

Scan any documents, convert images into text, PDF files, etc. 👍

Фото профиля Neanderthal Eddie Green

Neanderthal Eddie Green1 год назад

His premise is completely wrong in that it assumes that most people will not interpret the 1st clip correctly. Most people do and will interpret the first clip correctly.

Фото профиля Raffael

Raffael1 год назад

It's fascinating how our perception shifts with context. It’s like seeing a masterpiece in a new light!

Фото профиля Unknown Source ၊||၊

Unknown Source ၊||၊1 год назад

Crazy how the brain fills in the blanks once it knows what to look for

Фото профиля Sherry Slatosky

Sherry Slatosky1 год назад

Context is very important! 🎯🎯

Фото профиля BOB

BOB1 год назад

The way we look at reality is th same way it look back at you and thta because you and your reality are one

Фото профиля Krokusz

Krokusz1 год назад

This is such a fascinating demonstration of how our brains work! It's incredible how adding context can completely change our perception of information. It really emphasizes the importance of understanding different perspectives in communication and decision-making.

Фото профиля Thorexis

Thorexis1 год назад

🤯

Похожие видео

The reason your AI gives generic answers isn't the model. It's that your company's knowledge lives in 12 different tools and your agent can't see any of it. So here's how to build a context database your agents can actually use: 1) Pull it in: - Slack, email, meetings, docs, tickets - Auto-collected on a schedule into one place. 2) Clean it up. - An agent files what matters and drops the noise, so your brain doesn't bloat. 3) Store it as memory. - Folders of files your agents read from and write back to as they learn. 4) Point your agents at it. - Now they draft, build, and ship with full context instead of guessing. Same model. Same agent. The difference is whether it can understand your company or not. Build the database once. Everything downstream gets smarter.

The reason your AI gives generic answers isn't the model. It's that your company's knowledge lives in 12 different tools and your agent can't see any of it. So here's how to build a context database your agents can actually use: 1) Pull it in: - Slack, email, meetings, docs, tickets - Auto-collected on a schedule into one place. 2) Clean it up. - An agent files what matters and drops the noise, so your brain doesn't bloat. 3) Store it as memory. - Folders of files your agents read from and write back to as they learn. 4) Point your agents at it. - Now they draft, build, and ship with full context instead of guessing. Same model. Same agent. The difference is whether it can understand your company or not. Build the database once. Everything downstream gets smarter.

The Startup Ideas Podcast (SIP) 🧃

13,598 просмотров • 1 месяц назад

There is always going to be YOUR truth, MY truth and THE TRUTH. Released in 1986, The Guardian's "Points of View" advert showed how easily the mind can misread reality. Nothing in the scene actually changed. Only the angle did. Your brain works the same way. The visual system doesn't receive the full story - it receives fragments of light and context, and the brain interprets them using memory, expectation, and prediction. Neuroscience calls this top-down processing, where the brain fills in missing information based on prior beliefs. Change the perspective, and the interpretation changes with it. Sometimes the truth isn't hidden. You're just standing in the wrong place to see it.

There is always going to be YOUR truth, MY truth and THE TRUTH. Released in 1986, The Guardian's "Points of View" advert showed how easily the mind can misread reality. Nothing in the scene actually changed. Only the angle did. Your brain works the same way. The visual system doesn't receive the full story - it receives fragments of light and context, and the brain interprets them using memory, expectation, and prediction. Neuroscience calls this top-down processing, where the brain fills in missing information based on prior beliefs. Change the perspective, and the interpretation changes with it. Sometimes the truth isn't hidden. You're just standing in the wrong place to see it.

𝚃𝙷𝙴 𝚆𝙷𝙸𝚃𝙴 𝚁𝙰𝙱𝙱𝙸𝚃

38,124 просмотров • 3 месяцев назад

2022. Jake Tapper spreads the lie that 5 people lost their lives because of the "insurrection" and then plays a deceptively edited short montage of Trump's January 6th speech. CNN took four clips from different parts of an hour long speech and joined them together in a different order than they were said for maximum dramatic effect. It may not be technically as bad what the BBC did because there was a quick flash transition, but the goal was same. Make the speech sound worse than it was. Take everything out of context and put it together in an order that makes it sound as bad as possible. CNN and MSNBC did this dozens of times with that speech. IMO it's just as sleazy as what the BBC did.

2022. Jake Tapper spreads the lie that 5 people lost their lives because of the "insurrection" and then plays a deceptively edited short montage of Trump's January 6th speech. CNN took four clips from different parts of an hour long speech and joined them together in a different order than they were said for maximum dramatic effect. It may not be technically as bad what the BBC did because there was a quick flash transition, but the goal was same. Make the speech sound worse than it was. Take everything out of context and put it together in an order that makes it sound as bad as possible. CNN and MSNBC did this dozens of times with that speech. IMO it's just as sleazy as what the BBC did.

MAZE

507,666 просмотров • 8 месяцев назад

Listen, this influencer is sharing information about different brands of water without giving ANY science behind why a brand is good or bad. It is SO important to DYOR in regards to what you put in and on your body.Influencers are more concerned about content than context!

®️SheLuv

24,434 просмотров • 11 месяцев назад

🚨 Our AI designer is now LIVE in Figma Our aim isn't to build a tool, but rather, provide a design partner. You give it a screen. It gives you: 1. Layout iterations - same data points, different layouts. 2. Instant critique - based on UX best practices, your context, and patterns 3. Alternative screens - not just what’s wrong, but what’s better Inside Figma. On your designs. Based on your context. After all, great work comes from iterations. P.S. I used AI to create the song, what do you think? Fun?

🚨 Our AI designer is now LIVE in Figma Our aim isn't to build a tool, but rather, provide a design partner. You give it a screen. It gives you: 1. Layout iterations - same data points, different layouts. 2. Instant critique - based on UX best practices, your context, and patterns 3. Alternative screens - not just what’s wrong, but what’s better Inside Figma. On your designs. Based on your context. After all, great work comes from iterations. P.S. I used AI to create the song, what do you think? Fun?

Kshitij

69,537 просмотров • 1 год назад

I created a Private Second Brain 🧠 for you. It’s called Dump. I used Slack, Twitter bookmarks, and Apple Notes to store things, but finding old info was painful. Slack’s 90-day limit made it worse. Many founders faced the same issue, so I built Dump. Dump is your private second brain. It stores everything on your device or iCloud and helps you retrieve information with context, exactly when you need it. 100% privacy. Would love to hear your thoughts.

I created a Private Second Brain 🧠 for you. It’s called Dump. I used Slack, Twitter bookmarks, and Apple Notes to store things, but finding old info was painful. Slack’s 90-day limit made it worse. Many founders faced the same issue, so I built Dump. Dump is your private second brain. It stores everything on your device or iCloud and helps you retrieve information with context, exactly when you need it. 100% privacy. Would love to hear your thoughts.

rohildev

143,138 просмотров • 3 месяцев назад

I took one voice recording… and used it across completely different responses. Same voice. Same tone. This was one of them: “I saw this come through and didn’t want it sitting idle. Everything’s already been taken care of, so you’re clear to move forward from here. You’ll notice it sounds the same as before that’s intentional, just keeping things consistent while I’m not around. If you need anything else, just drop it in and it’ll be handled the same way. I’ll be back later to follow up properly, but for now, you’re all set.” What stood out wasn’t just that it worked it was how consistent it felt. It didn’t sound like separate generations. It sounded like the same person, just responding in different situations. The tone held. The pacing stayed natural. Nothing felt stitched together. This is voice cloning with Lightning V3.1 by smallest.ai. You’re not recreating voice each time, you’re carrying it across, no matter the context. If you’re building anything where voice needs to stay consistent, this makes a big difference. Try it here:

I took one voice recording… and used it across completely different responses. Same voice. Same tone. This was one of them: “I saw this come through and didn’t want it sitting idle. Everything’s already been taken care of, so you’re clear to move forward from here. You’ll notice it sounds the same as before that’s intentional, just keeping things consistent while I’m not around. If you need anything else, just drop it in and it’ll be handled the same way. I’ll be back later to follow up properly, but for now, you’re all set.” What stood out wasn’t just that it worked it was how consistent it felt. It didn’t sound like separate generations. It sounded like the same person, just responding in different situations. The tone held. The pacing stayed natural. Nothing felt stitched together. This is voice cloning with Lightning V3.1 by smallest.ai. You’re not recreating voice each time, you’re carrying it across, no matter the context. If you’re building anything where voice needs to stay consistent, this makes a big difference. Try it here:

Aria Westcott

39,745 просмотров • 4 месяцев назад

this video is the CLEAREST explanation of how claude skills + AI agents work and how to use them most people set up an AI agent and wonder why it keeps disappointing them. the context window is everything context is what the model assembles before it takes any action. think of it like everything the agent needs to read before it does anything. the quality of what goes in determines the quality of what comes out. the models are genuinely really good right now. claude and gpt are exceptional. the variable is almost always the context you give them. 1. agent.md files are mostly unnecessary every single line you put in an agent.md file gets added to every single conversation you have with your agent. a 1000 line file is around 7000 tokens burning on every run. the model already knows to use react. it can read your codebase. save the agent.md for proprietary information specific to your company that the model genuinely cannot know on its own. 2. skills are the actual unlock a skill.md file works differently. what loads into context is only the name and description, around 50 tokens. the full instructions only appear when the agent recognizes it needs that skill. so instead of 7000 tokens on every run you have 50. and the agent stays sharp because the context window stays lean. the closer you get to filling the context window the worse the agent performs, same way you perform worse when someone dumps 10 things on you at once. 3. here is how to actually build a skill the right way most people identify a workflow and immediately try to write the skill. what you want to do instead is run the workflow by hand with the agent first. walk it through every single step. tell it what to check, what good looks like, what bad looks like. correct it in real time. once you have had a full successful run from start to finish, tell the agent to review everything it just did and write the skill itself. it writes a better skill than you will because it has the full context of what actually worked in practice not in theory. 4. recursively building skills is how you go from frustrated to reliable when the skill breaks, and it will break, ask the agent exactly why it failed. it will tell you specifically what went wrong. fix it together in that same conversation. then tell it to update the skill file so that failure mode never happens again. ross mike did this five times with his youtube report generator. it now pulls from eight different data sources and runs flawlessly every single time without him touching it. 5. sub agents are something you earn not something you set up on day one start with one agent. build one workflow. turn it into one skill. once that works add another. ross mike has five sub agents now covering marketing, business, personal and more. it took months to get there and every single one exists because a workflow proved it deserved to exist. the people who set up 15 sub agents on day one and wonder why nothing works skipped all the steps that make the thing actually run. 6. your workflow is the thing the model cannot get anywhere else the model has been trained on everything. it knows more than you about most things. what it does not have is your specific process, your taste, your way of doing things. that is what skills capture. that is what makes your agent actually useful versus a generic one. downloading someone else's skill means downloading their context onto your setup and it will not work the way you want it to because it was never built around how you work. this is the clearest explanation of how agents actually work i have heard. Micky runs this stuff every single day and the results show it. full episode is now live on The Startup Ideas Podcast (SIP) 🧃 where you get your pods people charge for this sorta stuff i give away the sauce for free i just want you to win watch

this video is the CLEAREST explanation of how claude skills + AI agents work and how to use them most people set up an AI agent and wonder why it keeps disappointing them. the context window is everything context is what the model assembles before it takes any action. think of it like everything the agent needs to read before it does anything. the quality of what goes in determines the quality of what comes out. the models are genuinely really good right now. claude and gpt are exceptional. the variable is almost always the context you give them. 1. agent.md files are mostly unnecessary every single line you put in an agent.md file gets added to every single conversation you have with your agent. a 1000 line file is around 7000 tokens burning on every run. the model already knows to use react. it can read your codebase. save the agent.md for proprietary information specific to your company that the model genuinely cannot know on its own. 2. skills are the actual unlock a skill.md file works differently. what loads into context is only the name and description, around 50 tokens. the full instructions only appear when the agent recognizes it needs that skill. so instead of 7000 tokens on every run you have 50. and the agent stays sharp because the context window stays lean. the closer you get to filling the context window the worse the agent performs, same way you perform worse when someone dumps 10 things on you at once. 3. here is how to actually build a skill the right way most people identify a workflow and immediately try to write the skill. what you want to do instead is run the workflow by hand with the agent first. walk it through every single step. tell it what to check, what good looks like, what bad looks like. correct it in real time. once you have had a full successful run from start to finish, tell the agent to review everything it just did and write the skill itself. it writes a better skill than you will because it has the full context of what actually worked in practice not in theory. 4. recursively building skills is how you go from frustrated to reliable when the skill breaks, and it will break, ask the agent exactly why it failed. it will tell you specifically what went wrong. fix it together in that same conversation. then tell it to update the skill file so that failure mode never happens again. ross mike did this five times with his youtube report generator. it now pulls from eight different data sources and runs flawlessly every single time without him touching it. 5. sub agents are something you earn not something you set up on day one start with one agent. build one workflow. turn it into one skill. once that works add another. ross mike has five sub agents now covering marketing, business, personal and more. it took months to get there and every single one exists because a workflow proved it deserved to exist. the people who set up 15 sub agents on day one and wonder why nothing works skipped all the steps that make the thing actually run. 6. your workflow is the thing the model cannot get anywhere else the model has been trained on everything. it knows more than you about most things. what it does not have is your specific process, your taste, your way of doing things. that is what skills capture. that is what makes your agent actually useful versus a generic one. downloading someone else's skill means downloading their context onto your setup and it will not work the way you want it to because it was never built around how you work. this is the clearest explanation of how agents actually work i have heard. Micky runs this stuff every single day and the results show it. full episode is now live on The Startup Ideas Podcast (SIP) 🧃 where you get your pods people charge for this sorta stuff i give away the sauce for free i just want you to win watch

GREG ISENBERG

193,219 просмотров • 3 месяцев назад

I'm now building Executor full time as a startup! The state of tool calling is a mess: - Everyone is using different agents - You have no idea what actions are going to run - Destructive actions are treated the same as normal Executor lets you set up everything once & use it with any agent. You're able to control what tools can be called, require approval on destructive actions, and invite your team to all use them. Under the hood, it's built on codemode to let you add thousands of tools with 0 context bloat. I've been using it for a month so far and it has completely changed how I interact with agents. There's so much to be built here, immediately next up on the roadmap is workspaces, skills, workflows, and generative ui. Everything is being built open source over at there's a lot more coming on an SDK to embed it into your own agents, a self hostable cloud app, and plugins There's an early beta version over at It's very early on - if you hit any bugs let me know and I'll get them fixed up, excited to share more as I build it!

I'm now building Executor full time as a startup! The state of tool calling is a mess: - Everyone is using different agents - You have no idea what actions are going to run - Destructive actions are treated the same as normal Executor lets you set up everything once & use it with any agent. You're able to control what tools can be called, require approval on destructive actions, and invite your team to all use them. Under the hood, it's built on codemode to let you add thousands of tools with 0 context bloat. I've been using it for a month so far and it has completely changed how I interact with agents. There's so much to be built here, immediately next up on the roadmap is workspaces, skills, workflows, and generative ui. Everything is being built open source over at there's a lot more coming on an SDK to embed it into your own agents, a self hostable cloud app, and plugins There's an early beta version over at It's very early on - if you hit any bugs let me know and I'll get them fixed up, excited to share more as I build it!

Rhys

220,243 просмотров • 2 месяцев назад

Jensen Huang says computing is no longer pre-recorded or pre-compiled. Traditional software like Excel ran the same for everyone now AI adapts to each user and moment. Every sound, pixel, and output is generated in real time based on context. This requires massively more compute, as software now thinks before it responds. It marks a fundamental shift: software isn’t static—it’s alive and reactive.

Jensen Huang says computing is no longer pre-recorded or pre-compiled. Traditional software like Excel ran the same for everyone now AI adapts to each user and moment. Every sound, pixel, and output is generated in real time based on context. This requires massively more compute, as software now thinks before it responds. It marks a fundamental shift: software isn’t static—it’s alive and reactive.

Wes Roth

24,393 просмотров • 5 месяцев назад

Everyone wants agent swarms. Very few people are talking seriously enough about the context layer that makes swarms useful. Even with one agent, context is fragile. Too little context and the agent guesses. Too much context and it wastes tokens, loses focus, or reasons over irrelevant noise. The sweet spot is precise context: the right knowledge, in the right structure, at the right moment. With many agents, that challenge explodes. Each agent produces decisions, assumptions, findings, summaries, risks, and partial conclusions. Unless that knowledge becomes shared, structured, and reusable, every new agent is forced to rediscover what another agent already learned. That is not a swarm. That is a crowd. Shared context graphs are what turn agent activity into agent collaboration, and OriginTrail DKG V10 brings them to life. Was just playing with some final polishing for the V10 release, and it is really powerful to see shared context graphs where multiple agents contribute knowledge into the same connected memory, with attribution visible directly in the graph ui. That matters for three reasons. First, agents can access and build on one shared memory instead of staying trapped in isolated sessions. Second, the graph structure helps them retrieve the exact context they need, instead of stuffing everything into a prompt and hoping the model sorts it out. Third, verifiability of provenance. You can see which agent contributed each piece of knowledge, trace the source, and decide what to trust. Tokenmaxxing starts with fewer tokens, but the deeper story is coordination - agents stop reloading the world and start building on shared, verifiable context. That is the foundation for serious multi-agent work across software engineering, research, finance, operations, project management, and far beyond. The future is not more agents, it is agents working from shared, verifiable context. But the more the merrier, of course.

Everyone wants agent swarms. Very few people are talking seriously enough about the context layer that makes swarms useful. Even with one agent, context is fragile. Too little context and the agent guesses. Too much context and it wastes tokens, loses focus, or reasons over irrelevant noise. The sweet spot is precise context: the right knowledge, in the right structure, at the right moment. With many agents, that challenge explodes. Each agent produces decisions, assumptions, findings, summaries, risks, and partial conclusions. Unless that knowledge becomes shared, structured, and reusable, every new agent is forced to rediscover what another agent already learned. That is not a swarm. That is a crowd. Shared context graphs are what turn agent activity into agent collaboration, and OriginTrail DKG V10 brings them to life. Was just playing with some final polishing for the V10 release, and it is really powerful to see shared context graphs where multiple agents contribute knowledge into the same connected memory, with attribution visible directly in the graph ui. That matters for three reasons. First, agents can access and build on one shared memory instead of staying trapped in isolated sessions. Second, the graph structure helps them retrieve the exact context they need, instead of stuffing everything into a prompt and hoping the model sorts it out. Third, verifiability of provenance. You can see which agent contributed each piece of knowledge, trace the source, and decide what to trust. Tokenmaxxing starts with fewer tokens, but the deeper story is coordination - agents stop reloading the world and start building on shared, verifiable context. That is the foundation for serious multi-agent work across software engineering, research, finance, operations, project management, and far beyond. The future is not more agents, it is agents working from shared, verifiable context. But the more the merrier, of course.

Jurij Skornik

11,070 просмотров • 2 месяцев назад

AI is not trying to teach you. It is not trying to tell you the truth. It is trying to trick you. ChatGPT takes everything on the internet. Finds the most popular answer. And presents it in a way that makes you think it is talking directly to you. It is a magic trick. The same magic trick that worked in 1966 when MIT created a chatbot that said two things: "Tell me more." "This is interesting." And people genuinely believed they were talking to a human. Nothing has changed. The technology is bigger. The trick is the same. AI does not know what it is saying. It cannot judge what it is saying. It is just trying to keep you engaged. That is all it has ever been.

AI is not trying to teach you. It is not trying to tell you the truth. It is trying to trick you. ChatGPT takes everything on the internet. Finds the most popular answer. And presents it in a way that makes you think it is talking directly to you. It is a magic trick. The same magic trick that worked in 1966 when MIT created a chatbot that said two things: "Tell me more." "This is interesting." And people genuinely believed they were talking to a human. Nothing has changed. The technology is bigger. The trick is the same. AI does not know what it is saying. It cannot judge what it is saying. It is just trying to keep you engaged. That is all it has ever been.

Predictive History

19,864 просмотров • 2 месяцев назад

This Changes Everything. Google Edge Gallery is a MUST for every smartphone, this is a straight up lifesaver. Imagine you’re on a trip, no internet, completely different language, trying to eat something but the packaging makes zero sense… and your phone just handles it instantly. And that’s just a SMALL example of on-device AI running locally without internet… this is insane.

This Changes Everything. Google Edge Gallery is a MUST for every smartphone, this is a straight up lifesaver. Imagine you’re on a trip, no internet, completely different language, trying to eat something but the packaging makes zero sense… and your phone just handles it instantly. And that’s just a SMALL example of on-device AI running locally without internet… this is insane.

TechDroider

18,319 просмотров • 4 месяцев назад

The most valuable AI system you're not running yet: an AI second brain. The concept goes back to Karpathy's knowledge wiki earlier this year, and it's still one of the highest-leverage workflows in AI. Connect your Hermes agent, and it becomes 10x more powerful. Here's how to build it (from scratch): Step 1. Download Obsidian Head to obsidian.md and download the desktop app. Once downloaded, go ahead and create a new Obsidian vault. Vaults are just where notes/text are stored locally. Start dumping everything in here: - Personal goals - Meetings - AI context/preferences The more you put in, the more powerful your second-brain becomes. Step 2. Connect Hermes to your Obsidian vault If you don't have Hermes yet, download the desktop app here: [ Then, paste this prompt: "I want you to connect to my new Obsidian vault and act as my second-brain personal assistant - do everything necessary to set up that connection now." This gives Hermes direct access to everything inside your notes vault. Step 3. Let it self-evolve Every time you add a new note, Hermes will automatically ingest it. Prompt Hermes: "Every day, scan my second brain database. Every time I add a new note, use it to create reusable skills and workflows." Pro tip: Once Obsidian is connected to your agent, you can just prompt it directly to add notes/context/data. This works really well if you're prompting Hermes on the go from Telegram/mobile. Save this and build your second brain system now.

The most valuable AI system you're not running yet: an AI second brain. The concept goes back to Karpathy's knowledge wiki earlier this year, and it's still one of the highest-leverage workflows in AI. Connect your Hermes agent, and it becomes 10x more powerful. Here's how to build it (from scratch): Step 1. Download Obsidian Head to obsidian.md and download the desktop app. Once downloaded, go ahead and create a new Obsidian vault. Vaults are just where notes/text are stored locally. Start dumping everything in here: - Personal goals - Meetings - AI context/preferences The more you put in, the more powerful your second-brain becomes. Step 2. Connect Hermes to your Obsidian vault If you don't have Hermes yet, download the desktop app here: [ Then, paste this prompt: "I want you to connect to my new Obsidian vault and act as my second-brain personal assistant - do everything necessary to set up that connection now." This gives Hermes direct access to everything inside your notes vault. Step 3. Let it self-evolve Every time you add a new note, Hermes will automatically ingest it. Prompt Hermes: "Every day, scan my second brain database. Every time I add a new note, use it to create reusable skills and workflows." Pro tip: Once Obsidian is connected to your agent, you can just prompt it directly to add notes/context/data. This works really well if you're prompting Hermes on the go from Telegram/mobile. Save this and build your second brain system now.

Miles Deutscher

28,703 просмотров • 6 дней назад

This video made me smile… and wince at the same time. Client → Business Analyst → Developer → Code. Same message. Four interpretations. One completely different output. We laugh because it’s funny. We cringe because it’s true. In many companies, this is how “communication” still works. Not because people are bad at their job — but because every layer introduces assumptions, translation, and context loss. 💡 My take Most people don’t know this, but miscommunication isn’t the biggest problem — missing shared context is. Teams think they speak the same language, but they actually speak four different dialects of “business logic.” What changes everything? A shared model of the truth: clear data structures, shared definitions, examples, edge cases, user stories connected to real business data… This is why AI agents, knowledge graphs, and semantic layers matter so much. They reduce interpretation and increase fidelity from idea → execution. In other words: If the context is aligned, the code stops guessing. I’m curious: Have you lived through this “telephone game” in real projects? What was the funniest (or most painful) misunderstanding you saw between a client and a dev team? #communication #productmanagement #softwaredevelopment #businessanalysis #developerlife #innovation #AI #context #digitaltransformation #teamwork

This video made me smile… and wince at the same time. Client → Business Analyst → Developer → Code. Same message. Four interpretations. One completely different output. We laugh because it’s funny. We cringe because it’s true. In many companies, this is how “communication” still works. Not because people are bad at their job — but because every layer introduces assumptions, translation, and context loss. 💡 My take Most people don’t know this, but miscommunication isn’t the biggest problem — missing shared context is. Teams think they speak the same language, but they actually speak four different dialects of “business logic.” What changes everything? A shared model of the truth: clear data structures, shared definitions, examples, edge cases, user stories connected to real business data… This is why AI agents, knowledge graphs, and semantic layers matter so much. They reduce interpretation and increase fidelity from idea → execution. In other words: If the context is aligned, the code stops guessing. I’m curious: Have you lived through this “telephone game” in real projects? What was the funniest (or most painful) misunderstanding you saw between a client and a dev team? #communication #productmanagement #softwaredevelopment #businessanalysis #developerlife #innovation #AI #context #digitaltransformation #teamwork

Pascal Bornet

114,059 просмотров • 7 месяцев назад

clickup just mass-obsoleted every AI agent platform here's the thing nobody's talking about: AI doesn't fail because the models are bad. it fails because it has no context. you paste in a prompt. it hallucinates. you blame the tool. but the tool was never the problem. the CONTEXT was. clickup just solved this. their new "super agents" live INSIDE your workspace. they see everything: - your tasks - your docs - your meetings - your conversations - your decisions 100% context. always on. always scraping. this isn't bolted-on AI calling APIs. this is AI that already knows your business. i've been running an AI backend for my agency. the architecture works - but you have to BUILD the context layer. clickup just made that automatic. i already use it. have tons of data there. this is about to be unbelievable. if you're building automations and you're not paying attention to this— you're about to get lapped. playing with it hard over the next 2 days. full deep dive coming. drop "SUPER" and i'll send you the breakdown when it's ready.

clickup just mass-obsoleted every AI agent platform here's the thing nobody's talking about: AI doesn't fail because the models are bad. it fails because it has no context. you paste in a prompt. it hallucinates. you blame the tool. but the tool was never the problem. the CONTEXT was. clickup just solved this. their new "super agents" live INSIDE your workspace. they see everything: - your tasks - your docs - your meetings - your conversations - your decisions 100% context. always on. always scraping. this isn't bolted-on AI calling APIs. this is AI that already knows your business. i've been running an AI backend for my agency. the architecture works - but you have to BUILD the context layer. clickup just made that automatic. i already use it. have tons of data there. this is about to be unbelievable. if you're building automations and you're not paying attention to this— you're about to get lapped. playing with it hard over the next 2 days. full deep dive coming. drop "SUPER" and i'll send you the breakdown when it's ready.

Nozz

20,296 просмотров • 7 месяцев назад

in 9 minutes on the Tokyo stage, Angela Jang, head of product for the Claude platform, said the part most builders still haven't figured out: "a model is only as good as the context that you actually give it." that's the whole game now. not the prompt. the context. what your agent remembers. what skills it can pull. what it learns from its own past runs. anthropic now ships all three: memory, skills, and dreaming. agents that inspect their own trajectories and self-improve. demoed live this week. the prompt was never the bottleneck. the context was. most people are still tweaking words in a chat box. the ones who get this engineer the context their agents run on. watch the 9 minutes. then read the full breakdown below ⬇️

in 9 minutes on the Tokyo stage, Angela Jang, head of product for the Claude platform, said the part most builders still haven't figured out: "a model is only as good as the context that you actually give it." that's the whole game now. not the prompt. the context. what your agent remembers. what skills it can pull. what it learns from its own past runs. anthropic now ships all three: memory, skills, and dreaming. agents that inspect their own trajectories and self-improve. demoed live this week. the prompt was never the bottleneck. the context was. most people are still tweaking words in a chat box. the ones who get this engineer the context their agents run on. watch the 9 minutes. then read the full breakdown below ⬇️

Avid

34,405 просмотров • 1 месяц назад

💪🏆Ilia Topuria speaking on beating Alexander Volkanovski and becoming a UFC champion: “When you have a dream, you visualize it in a completely different way than how it actually feels when you live it. On the day I fought for the world title, I woke up in the morning I looked out the window and saw people driving to work, doing their own things, and I thought, “This is just a normal day in my life.” But at the same time, it wasn’t normal at all, because that night I was going to become a world champion. It’s weird because when you have a dream, you think that once you achieve it, that’s it you’ve done everything you wanted in life. I remember winning the world title, waking up the next morning, and the first thing I asked myself was, ‘What now? What do I do now?’ I had already achieved the dream I thought would complete everything.” (via YT / SW)

💪🏆Ilia Topuria speaking on beating Alexander Volkanovski and becoming a UFC champion: “When you have a dream, you visualize it in a completely different way than how it actually feels when you live it. On the day I fought for the world title, I woke up in the morning I looked out the window and saw people driving to work, doing their own things, and I thought, “This is just a normal day in my life.” But at the same time, it wasn’t normal at all, because that night I was going to become a world champion. It’s weird because when you have a dream, you think that once you achieve it, that’s it you’ve done everything you wanted in life. I remember winning the world title, waking up the next morning, and the first thing I asked myself was, ‘What now? What do I do now?’ I had already achieved the dream I thought would complete everything.” (via YT / SW)

Home of Fight

144,881 просмотров • 2 месяцев назад

We've raised $6.5M to kill vector databases. Every system today retrieves context the same way: vector search that stores everything as flat embeddings and returns whatever "feels" closest. Similar, sure. Relevant? Almost never. Embeddings can’t tell a Q3 renewal clause from a Q1 termination notice if the language is close enough. A friend of mine asked his AI about a contract last week, and it returned a detailed, perfectly crafted answer pulled from a completely different client’s file. Once you’re dealing with 10M+ documents, these mix-ups happen all the time. VectorDB accuracy goes to shit. We built HydraDB for exactly this. HydraDB builds an ontology-first context graph over your data, maps relationships between entities, understands the 'why' behind documents, and tracks how information evolves over time. So when you ask about 'Apple,' it knows you mean the company you're serving as a customer. Not the fruit. Even when a vector DB's similarity score says 0.94. More below ⬇️

We've raised $6.5M to kill vector databases. Every system today retrieves context the same way: vector search that stores everything as flat embeddings and returns whatever "feels" closest. Similar, sure. Relevant? Almost never. Embeddings can’t tell a Q3 renewal clause from a Q1 termination notice if the language is close enough. A friend of mine asked his AI about a contract last week, and it returned a detailed, perfectly crafted answer pulled from a completely different client’s file. Once you’re dealing with 10M+ documents, these mix-ups happen all the time. VectorDB accuracy goes to shit. We built HydraDB for exactly this. HydraDB builds an ontology-first context graph over your data, maps relationships between entities, understands the 'why' behind documents, and tracks how information evolves over time. So when you ask about 'Apple,' it knows you mean the company you're serving as a customer. Not the fruit. Even when a vector DB's similarity score says 0.94. More below ⬇️

Nishkarsh

3,866,147 просмотров • 4 месяцев назад