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

1,000 tok/s, SWE-1.7 is near-frontier intelligence at real-time speed. Building this way is a new category of DX. A task that used to justify walking away finishes before you've mentally moved on. There's a weird middle mode now: it's technically async, but fast enough that you just... watch. In... show more

nader dabit

190,910 subscribers

178,708 просмотров • 1 месяц назад •via X (Twitter)

Наука и технологии Образование

Anya Rossi• Live Now

Private livecam show

Комментарии: 0

Нет доступных комментариев

Здесь появятся комментарии из оригинального поста

Похожие видео

At this point basically any model will be able to solve your coding task Raw model intelligence won't dramatically change your day-to-day work.. but speed will “intelligence per second” is the next hill climb So here's me running on a treadmill using SWE-1.7 in fast mode 🏃

At this point basically any model will be able to solve your coding task Raw model intelligence won't dramatically change your day-to-day work.. but speed will “intelligence per second” is the next hill climb So here's me running on a treadmill using SWE-1.7 in fast mode 🏃

Jared Zoneraich

41,795 просмотров • 13 дней назад

Here is my first drive on Tesla FSD V14.1.2 with the new Mad Max speed profile. Mad Max mode drives very quickly and confidently. It accelerates MUCH quicker off the line (love that) and maxes out at 85mph on the highway. If you like to drive fast, you're going to love this new mode. It may not come through on screen very well, but Mad Max mode makes the car zoom around town like it's on a mission lol. It's unlike any FSD mode Tesla has ever released before. Hurry mode now maxes out at 80mph on the highway, while the new Sloth mode matches the speed limit, which for me tonight was 65mph on the highway.

Sawyer Merritt

178,168 просмотров • 10 месяцев назад

HERMES DESKTOP APP JUST GOT A NEW ULTRA MODE FOR DEEPSEEK V4 PRO – AND IT COSTS ABOUT $1 A DAY TO RUN If you're using Hermes desktop app, you're probably already running DeepSeek – it's one of the top models available. The update: → DeepSeek V4 Pro now has thinking mode, fast mode, and a brand new ultra mode → There's also an extra high mode, but the real upgrade is ultra The actual cost: roughly $1/day for a normal workflow. That's about $20-25/month – basically the same as before, just with a significantly faster mode unlocked. The verdict after a full day of testing: it flies through tool calling. Noticeably faster, same price range. If you're already paying for DeepSeek through Hermes, this is a free upgrade sitting in your settings right now. Update Hermes, grab the DeepSeek API if you don't have it yet, and try V4 Pro on ultra. Bookmark this, you'll want to come back to it later.

SCOTTY BEAM

24,032 просмотров • 1 месяц назад

🚨 JUST IN: President Trump exposes to America that Barack Hussein Obama is the reason Iran STRENGTHENED and threatened the whole world All roads lead to Hussein! 47 is now cleaning up the mess. "He gave them $1.7 billion in cash, in green cash put in an airplane and brought it to Iran!" "1.7 billion dollars. Do you ever see? Did you ever see a million dollars in cash? This is 1.7 billion. It took up an entire seven Boeing 757 and they flew it to Iran and they gave it to people that were waiting at a plane!" "Can you imagine these people? They never saw money and all of a sudden they've got 1.7 billion in cash and he gave them hundreds of billions of dollars in cash." "He went to their side and because of that — they built and become more powerful."

🚨 JUST IN: President Trump exposes to America that Barack Hussein Obama is the reason Iran STRENGTHENED and threatened the whole world All roads lead to Hussein! 47 is now cleaning up the mess. "He gave them $1.7 billion in cash, in green cash put in an airplane and brought it to Iran!" "1.7 billion dollars. Do you ever see? Did you ever see a million dollars in cash? This is 1.7 billion. It took up an entire seven Boeing 757 and they flew it to Iran and they gave it to people that were waiting at a plane!" "Can you imagine these people? They never saw money and all of a sudden they've got 1.7 billion in cash and he gave them hundreds of billions of dollars in cash." "He went to their side and because of that — they built and become more powerful."

Eric Daugherty

262,958 просмотров • 1 месяц назад

Bitwise CEO: There's a tempo mismatch that most crypto natives are missing. In crypto, "an hour is fast. A day is pretty fast. A week is a meaningful time frame, and nobody can remember what happened 4 weeks ago." But the mainstream investor now entering the space? For them a month is really fast and a year is a reasonable time frame. They move at a completely different pace. The progress is real - it just doesn't feel like it to people used to measuring time in hours. FT Hunter Horsley MR SHIFT 🦁 Bitwise.

Bitwise CEO: There's a tempo mismatch that most crypto natives are missing. In crypto, "an hour is fast. A day is pretty fast. A week is a meaningful time frame, and nobody can remember what happened 4 weeks ago." But the mainstream investor now entering the space? For them a month is really fast and a year is a reasonable time frame. They move at a completely different pace. The progress is real - it just doesn't feel like it to people used to measuring time in hours. FT Hunter Horsley MR SHIFT 🦁 Bitwise.

Milk Road

87,986 просмотров • 2 месяцев назад

Head of Anthropic Labs: "Fable is one of those models you'll just remember - like Sonnet 3.5, Opus 4, Opus 4.5. Fable is way smarter than me. It finishes a task, lists its trade-offs, and I have to ask it to explain them to me." in 20-minute talk, the Anthropic head reveals the full capabilities of the Fable 5 model in practice. Watch it now, then read how to use this frontier model in the article below

Head of Anthropic Labs: "Fable is one of those models you'll just remember - like Sonnet 3.5, Opus 4, Opus 4.5. Fable is way smarter than me. It finishes a task, lists its trade-offs, and I have to ask it to explain them to me." in 20-minute talk, the Anthropic head reveals the full capabilities of the Fable 5 model in practice. Watch it now, then read how to use this frontier model in the article below

Movez

33,774 просмотров • 1 месяц назад

With all the buzz around the Codex App, OpenAI Developers quietly snuck out a new CLI update (0.94.0) as well. And boy is it an important update! Codex Plan mode is now officially released to the general audience! I am very excited about this one as it has a really strong prompt that is unlike any other plan mode I've personally used. Codex Plan mode doesn't necessarily just ask you 3 questions up front. It goes, collects context, asks questions, collects more context, asks more questions (sometimes), and then writes an incredibly high quality plan. It is my favorite implementation of plan mode thus far. It also comes with Codex's own version of "AskUserQuestion!" Although, it only works in Plan mode for now. They really need to allow people to use it in Code mode as well, but one win at a time. npm i -g @openai/codex Below is a demo of how it works. Let me know what you think!

With all the buzz around the Codex App, OpenAI Developers quietly snuck out a new CLI update (0.94.0) as well. And boy is it an important update! Codex Plan mode is now officially released to the general audience! I am very excited about this one as it has a really strong prompt that is unlike any other plan mode I've personally used. Codex Plan mode doesn't necessarily just ask you 3 questions up front. It goes, collects context, asks questions, collects more context, asks more questions (sometimes), and then writes an incredibly high quality plan. It is my favorite implementation of plan mode thus far. It also comes with Codex's own version of "AskUserQuestion!" Although, it only works in Plan mode for now. They really need to allow people to use it in Code mode as well, but one win at a time. npm i -g @openai/codex Below is a demo of how it works. Let me know what you think!

am.will

57,121 просмотров • 6 месяцев назад

People that say the FAMAS is awful just don't get it, you've got to envision yourself as a halo spartan with a battle rifle one bursting everyone in the head whilst running at full speed It's about mentality, the FAMAS is a state of mind The FAMAS never misses, only you miss

People that say the FAMAS is awful just don't get it, you've got to envision yourself as a halo spartan with a battle rifle one bursting everyone in the head whilst running at full speed It's about mentality, the FAMAS is a state of mind The FAMAS never misses, only you miss

Jacky Powers

143,421 просмотров • 1 год назад

Building an app isn’t one-size-fits-all. Watch two habit trackers built side-by-side in Antigravity using two different approaches: Fast Mode is for when the task is straightforward and you just need execution. It’s punchy, functional, and delivers at high velocity. Planning Mode is for taking a more thoughtful, scalable approach. It is designed for those who want to craft custom systems with deep, intricate logic or for follow-up tasks that require thorough context retrieval or reasoning. It may take longer, but in this mode, the Agent starts with thorough reasoning and planning, exposes implementation plan Artifacts, and focuses on self-verification.

Building an app isn’t one-size-fits-all. Watch two habit trackers built side-by-side in Antigravity using two different approaches: Fast Mode is for when the task is straightforward and you just need execution. It’s punchy, functional, and delivers at high velocity. Planning Mode is for taking a more thoughtful, scalable approach. It is designed for those who want to craft custom systems with deep, intricate logic or for follow-up tasks that require thorough context retrieval or reasoning. It may take longer, but in this mode, the Agent starts with thorough reasoning and planning, exposes implementation plan Artifacts, and focuses on self-verification.

Google Antigravity

89,391 просмотров • 6 месяцев назад

🇺🇸JOE ROGAN: WHAT THEY HAVE DONE TO L.A. IN SUCH A SHORT TIME IS SHOCKING “It’s like, what they've done to that city {LA} in a short amount of time is shocking. I never thought it would go that bad that fast. And it's, the way it is now is bizarre. Yeah, the, the, uh, I always say that it's like a girl that used to date, she was really cute, but now she does meth and she works for the cartel. Like, what happened to you? The pandemic happened.” Source: Joe Rogan

🇺🇸JOE ROGAN: WHAT THEY HAVE DONE TO L.A. IN SUCH A SHORT TIME IS SHOCKING “It’s like, what they've done to that city {LA} in a short amount of time is shocking. I never thought it would go that bad that fast. And it's, the way it is now is bizarre. Yeah, the, the, uh, I always say that it's like a girl that used to date, she was really cute, but now she does meth and she works for the cartel. Like, what happened to you? The pandemic happened.” Source: Joe Rogan

Mario Nawfal

5,807,751 просмотров • 1 год назад

There's a new AI-native IDE out there named Aide, and there are four things I like about it: 1. It's open-source 2. It's proactive and suggests changes before you ask 3. It uses an intermediate layer between the editor and LLM 4. It's SOTA on the SWE-Bench benchmark I'm excited about #3 because this layer (called "Sidecar") will help people connect any model to the IDE. While this isn't possible right now, it's clearly the goal. Sidecar is also open-source. As I write this, the code agent behind Aide, "CodeStory Midwit Agent," is second in the Verified SWE-Bench leaderboard (it finished in 2024 in the first place.) This is a huge deal! If I'm gonna have an agent help me code, it might as well be the best of the best. The proactive aspect is also cool: the IDE provides suggestions to improve your code without you having to ask. I recorded a quick video showing you how Aide works. The team behind the IDE partnered with me on this video. Right now, it feels like *everyone* is building AI-powered coding tools. As a career developer, nothing excites me more than seeing how quickly we transform the development experience. And 2025 is just getting started!

There's a new AI-native IDE out there named Aide, and there are four things I like about it: 1. It's open-source 2. It's proactive and suggests changes before you ask 3. It uses an intermediate layer between the editor and LLM 4. It's SOTA on the SWE-Bench benchmark I'm excited about #3 because this layer (called "Sidecar") will help people connect any model to the IDE. While this isn't possible right now, it's clearly the goal. Sidecar is also open-source. As I write this, the code agent behind Aide, "CodeStory Midwit Agent," is second in the Verified SWE-Bench leaderboard (it finished in 2024 in the first place.) This is a huge deal! If I'm gonna have an agent help me code, it might as well be the best of the best. The proactive aspect is also cool: the IDE provides suggestions to improve your code without you having to ask. I recorded a quick video showing you how Aide works. The team behind the IDE partnered with me on this video. Right now, it feels like everyone is building AI-powered coding tools. As a career developer, nothing excites me more than seeing how quickly we transform the development experience. And 2025 is just getting started!

Santiago

69,466 просмотров • 1 год назад

Sorry about so many updates, but this is happening so fast that I want to stay on top of it in real time. The signature that we are seeing on satellite is extremely concerning. If it doesn't fade away in another hour or so, let's give it till 10:00 PM Eastern Time, then we need to start looking at whatever really crazy model runs are out there that initiate this storm somewhere in this small area where this convective blow-up is and then ramp it up really quickly, because there's a decent chance that that model run could be correct.

Sorry about so many updates, but this is happening so fast that I want to stay on top of it in real time. The signature that we are seeing on satellite is extremely concerning. If it doesn't fade away in another hour or so, let's give it till 10:00 PM Eastern Time, then we need to start looking at whatever really crazy model runs are out there that initiate this storm somewhere in this small area where this convective blow-up is and then ramp it up really quickly, because there's a decent chance that that model run could be correct.

Bryan Maxwell SW FL WX

139,332 просмотров • 11 месяцев назад

SWAT God Me and Dean Miller 's new game. This is a hyper fast shooter that aims to removes all limits. Moving with your mouse means infinite speed and precision. The Combat Prototype is live now on itch. Play in your browser or download the EXE.

SWAT God Me and Dean Miller 's new game. This is a hyper fast shooter that aims to removes all limits. Moving with your mouse means infinite speed and precision. The Combat Prototype is live now on itch. Play in your browser or download the EXE.

phil

369,322 просмотров • 7 месяцев назад

Threadguy explains why the market won't let Bitcoin recover while Saylor's still in "If you put a gun to your head and asked what makes a real emphatic bottom for Bitcoin, it's Strategy deleveraging, forced selling of the Bitcoin, and Michael Saylor on trial for financial crimes. That's a bottom right there." "Strategy has $1.7 billion promised annually to the end of time. Out of 5,000 public companies in America, maybe 100 make $1.7 billion in profit a year, and Strategy owes that forever. They're only worth their balance sheet in Bitcoin and they can't sell the Bitcoin. The whole bit is earnings per share, but the only way they earn is by selling more Strategy, and that only works if Bitcoin goes up, which it can't while Saylor's still in. So the market is just saying say uncle."

Threadguy explains why the market won't let Bitcoin recover while Saylor's still in "If you put a gun to your head and asked what makes a real emphatic bottom for Bitcoin, it's Strategy deleveraging, forced selling of the Bitcoin, and Michael Saylor on trial for financial crimes. That's a bottom right there." "Strategy has $1.7 billion promised annually to the end of time. Out of 5,000 public companies in America, maybe 100 make $1.7 billion in profit a year, and Strategy owes that forever. They're only worth their balance sheet in Bitcoin and they can't sell the Bitcoin. The whole bit is earnings per share, but the only way they earn is by selling more Strategy, and that only works if Bitcoin goes up, which it can't while Saylor's still in. So the market is just saying say uncle."

Kai

52,699 просмотров • 2 месяцев назад

The danger of AI is not just the slop, but what we lose in the process. Michael Pollan explains: "We're moving into this time where we're gonna sub out writing to AI. And AI can write our papers, and professors are dealing with this everywhere now. But what is lost is a way of thinking. Writing does something to your brain. It gives you access to things you can't know just walking around or thinking or planning or outlining. If you were just transcribing what was in your head, it would be kind of onerous. But it really is what you learn in the course of a day spent writing, things you didn't know, ideas that you didn't expect. And that's the thrill of it."

The danger of AI is not just the slop, but what we lose in the process. Michael Pollan explains: "We're moving into this time where we're gonna sub out writing to AI. And AI can write our papers, and professors are dealing with this everywhere now. But what is lost is a way of thinking. Writing does something to your brain. It gives you access to things you can't know just walking around or thinking or planning or outlining. If you were just transcribing what was in your head, it would be kind of onerous. But it really is what you learn in the course of a day spent writing, things you didn't know, ideas that you didn't expect. And that's the thrill of it."

David Perell Clips

18,468 просмотров • 2 месяцев назад

Just look at the new Compositing in Blender 5.2. This is cool. Now the compositor can play sequence animation in real-time right in the compositor, and look at this, I'm doing color grading while the animation is playing. On top of that, the overall performance of the Compositor has grown a lot, and it now works at a level where you don't need to use DaVinci Fusion and can work fully in Blender. Because now Blender can definitely do that. Blender 🔶 This is an awesome update! Maybe you will think about adding the ability to move images in Compositing just by dragging them with the mouse, in some of the next updates...

Just look at the new Compositing in Blender 5.2. This is cool. Now the compositor can play sequence animation in real-time right in the compositor, and look at this, I'm doing color grading while the animation is playing. On top of that, the overall performance of the Compositor has grown a lot, and it now works at a level where you don't need to use DaVinci Fusion and can work fully in Blender. Because now Blender can definitely do that. Blender 🔶 This is an awesome update! Maybe you will think about adding the ability to move images in Compositing just by dragging them with the mouse, in some of the next updates...

SLAVO | c g s l a v

25,498 просмотров • 1 месяц назад

.Haseeb Qureshi ＞|＜ calls any team not running its releases through frontier-model security scanning "delinquent": "We are in a world where the previous rules around cybersecurity no longer apply. Because the reality is, if you can find this bug for $2, the team that was building this also could have done security scanning for $2. What were they doing?" "GLM has been out for a while. Kimi obviously more recent, but even just doing this on Opus would have cost probably four or five times that at most. Supposedly somebody ran Claude Code and found this in two minutes." "So what all this tells you is that there are companies that are going to survive this transition, and there are companies that are not. And there's going to be this kind of COVID-like mass inoculation period that we're going through right now in cybersecurity." "It's probably going to be a very centralizing force, because it means there's gonna be more consolidation toward the companies that have good security practices, have enough money to spend real dollars on security engineering, and are gonna be running every release through thousands of dollars of security scanning from frontier-level models." "If you are not doing that now, you are delinquent. You are already behind. You are putting your users and your company at risk." "AI is kind of an everything technology. It's like this background radiation now that is just touching everything that is software based." Dragonfly ＞|＜

.Haseeb Qureshi ＞|＜ calls any team not running its releases through frontier-model security scanning "delinquent": "We are in a world where the previous rules around cybersecurity no longer apply. Because the reality is, if you can find this bug for $2, the team that was building this also could have done security scanning for $2. What were they doing?" "GLM has been out for a while. Kimi obviously more recent, but even just doing this on Opus would have cost probably four or five times that at most. Supposedly somebody ran Claude Code and found this in two minutes." "So what all this tells you is that there are companies that are going to survive this transition, and there are companies that are not. And there's going to be this kind of COVID-like mass inoculation period that we're going through right now in cybersecurity." "It's probably going to be a very centralizing force, because it means there's gonna be more consolidation toward the companies that have good security practices, have enough money to spend real dollars on security engineering, and are gonna be running every release through thousands of dollars of security scanning from frontier-level models." "If you are not doing that now, you are delinquent. You are already behind. You are putting your users and your company at risk." "AI is kind of an everything technology. It's like this background radiation now that is just touching everything that is software based." Dragonfly ＞|＜

MTS

12,086 просмотров • 21 дней назад

.Chamath Palihapitiya on building a moat in 2026: If you are a reasonable company, why are you not finding an independent way to access intelligence in a way that doesn't leak your edge away? To [not] do so at this point now is kind of becoming derelict and irresponsible… With post-training and telemetry collected from usage, you can take GLM, control it entirely, soup to nuts, on your own hardware, inside the United States, and have it be much, much cheaper. Start building your own intelligence today.

.Chamath Palihapitiya on building a moat in 2026: If you are a reasonable company, why are you not finding an independent way to access intelligence in a way that doesn't leak your edge away? To [not] do so at this point now is kind of becoming derelict and irresponsible… With post-training and telemetry collected from usage, you can take GLM, control it entirely, soup to nuts, on your own hardware, inside the United States, and have it be much, much cheaper. Start building your own intelligence today.

Alex Ker 🔭

108,391 просмотров • 1 месяц назад

New c7 patch out now with a single change: 25% increase in speed to ALL sidesteps Got a few clips from playtest footage, but this changes the whole game in a way that is hard to describe or demonstrate. Try it with some friends and let me know what you think.

New c7 patch out now with a single change: 25% increase in speed to ALL sidesteps Got a few clips from playtest footage, but this changes the whole game in a way that is hard to describe or demonstrate. Try it with some friends and let me know what you think.

6 weetbix

87,683 просмотров • 4 месяцев назад

Libghostty can now be used to fuzz TUIs, thanks to Oskar Wickström + Antithesis. They already found bugs in multiple including btop. I always imagined libghostty would be useful for testing TUIs, super happy to see this is both practical and valuable. This is another example of where speed matters! "Why does Ghostty need to be so fast?" Well, if you're running hundreds or thousands of unit tests that each use a clean in-memory terminal, you want that to be fast. If you're fuzz testing and trying to push an unlimited amount of data through a terminal, you want that terminal to be fast. So many people got hung up on "why does my terminal _GUI_ need to be fast" without connecting one more dot and realizing the GUI is only fast if the core is fast, and the core being fast unlocks a hell of a lot more. Like this.

Libghostty can now be used to fuzz TUIs, thanks to Oskar Wickström + Antithesis. They already found bugs in multiple including btop. I always imagined libghostty would be useful for testing TUIs, super happy to see this is both practical and valuable. This is another example of where speed matters! "Why does Ghostty need to be so fast?" Well, if you're running hundreds or thousands of unit tests that each use a clean in-memory terminal, you want that to be fast. If you're fuzz testing and trying to push an unlimited amount of data through a terminal, you want that terminal to be fast. So many people got hung up on "why does my terminal _GUI_ need to be fast" without connecting one more dot and realizing the GUI is only fast if the core is fast, and the core being fast unlocks a hell of a lot more. Like this.

Mitchell Hashimoto

71,584 просмотров • 3 месяцев назад