Загрузка видео...

Не удалось загрузить видео

На главную

swe-bench is kind of a shitshow, and it makes evaluating LLMs hard. DeepSWE is the first agentic code bench that makes sense.

theo's profile picture

Theo - t3.gg

368,806 subscribers

166,341 просмотров • 2 месяцев назад •via X (Twitter)

ИгрыОбразованиеНаука и технологии
LIVE

Anya Rossi• Live Now

Private livecam show

Комментарии: 0

Нет доступных комментариев

Здесь появятся комментарии из оригинального поста

Похожие видео

Introducing Warp 2.0: the Agentic Development Environment 1️⃣ Top overall coding agent: #1 on Terminal-Bench, 71% on SWE-bench Verified 2️⃣ Agent multi-threading: build features, debug, and ship all at once 3️⃣ The first all-in-one platform for agentic development 🧵 Learn more
2:26

Introducing Warp 2.0: the Agentic Development Environment 1️⃣ Top overall coding agent: #1 on Terminal-Bench, 71% on SWE-bench Verified 2️⃣ Agent multi-threading: build features, debug, and ship all at once 3️⃣ The first all-in-one platform for agentic development 🧵 Learn more

Warp

1,445,810 просмотров • 1 год назад

Warp Code launched yesterday — here’s what’s new: - Top coding agent: #3 SWE-bench, 52% Terminal-Bench - Built-in code review - Native editor - Slash Commands, Project Rules, and more We’re already seeing millions more lines of code shipped through Warp.
2:57

Warp Code launched yesterday — here’s what’s new: - Top coding agent: #3 SWE-bench, 52% Terminal-Bench - Built-in code review - Native editor - Slash Commands, Project Rules, and more We’re already seeing millions more lines of code shipped through Warp.

Warp

11,745 просмотров • 11 месяцев назад

I'm excited to share that we've built the world's most capable AI software engineer, achieving 30.08% on SWE-Bench – ahead of Amazon and Cognition. This model is so much more than a benchmark score: it was trained from the start to think and behave like a human SWE.
3:58

I'm excited to share that we've built the world's most capable AI software engineer, achieving 30.08% on SWE-Bench – ahead of Amazon and Cognition. This model is so much more than a benchmark score: it was trained from the start to think and behave like a human SWE.

Alistair

820,273 просмотров • 2 лет назад

“didn’t make sense narratively” is a hilarious way to phrase that when byler is the BIGGEST thing that makes sense narratively and makes everything else in the story of st click #lovewinsgate
0:21

“didn’t make sense narratively” is a hilarious way to phrase that when byler is the BIGGEST thing that makes sense narratively and makes everything else in the story of st click #lovewinsgate

eleanor ♡

63,521 просмотров • 3 месяцев назад

SWE-Agent is an open-source software engineering agent with a 12.3% resolve rate on SWE-Bench! Check out SWE-agent in action at Repo:
2:19

SWE-Agent is an open-source software engineering agent with a 12.3% resolve rate on SWE-Bench! Check out SWE-agent in action at Repo:

carlos

138,864 просмотров • 2 лет назад

THE MANITOU (1978) I like THE MANITOU because it is super easy to follow and understand. It is a coherent movie that makes a lot of sense
2:28

THE MANITOU (1978) I like THE MANITOU because it is super easy to follow and understand. It is a coherent movie that makes a lot of sense

Movies from HELL

24,670 просмотров • 10 месяцев назад

Introducing Warp Code: a partner you can trust, from prompt to production 🤠 Warp Code features: 👉 Top coding agent: #1 on Terminal-Bench, #3 on SWE-bench Verified 👉 Code review panel 👉 Lightweight code editor 👉 Slash commands, and agent profiles
2:57

Introducing Warp Code: a partner you can trust, from prompt to production 🤠 Warp Code features: 👉 Top coding agent: #1 on Terminal-Bench, #3 on SWE-bench Verified 👉 Code review panel 👉 Lightweight code editor 👉 Slash commands, and agent profiles

Warp

112,863 просмотров • 11 месяцев назад

It sounds like Payton Pritchard expects to be coming off the bench, at least in the short-term: “You see how our team is constructed, you need somebody to bench to handle the rock, and it's good, D-White comes out, I come in and there's always somebody that can bring it up, get us into the flow, stuff like that. So just makes the most sense for our team.”
0:49

It sounds like Payton Pritchard expects to be coming off the bench, at least in the short-term: “You see how our team is constructed, you need somebody to bench to handle the rock, and it's good, D-White comes out, I come in and there's always somebody that can bring it up, get us into the flow, stuff like that. So just makes the most sense for our team.”

Noa Dalzell 🏀

100,438 просмотров • 6 месяцев назад

Excited to open source our world-model-harness! `wmh` makes it easy to go from agent traces -> faithful replication of your production environment Basically, an LLM pretends to be a Docker container but 5x faster Below is a comparison running 8 SWE-bench tasks
0:30

Excited to open source our world-model-harness! `wmh` makes it easy to go from agent traces -> faithful replication of your production environment Basically, an LLM pretends to be a Docker container but 5x faster Below is a comparison running 8 SWE-bench tasks

Silen Naihin

14,085 просмотров • 1 месяц назад

“And now it makes sense that your favorite rapper is THE BOY” 😭 #AkaDiddy
0:50

“And now it makes sense that your favorite rapper is THE BOY” 😭 #AkaDiddy

ᐅᗕᐱᐱᓵᔑ

35,646 просмотров • 1 год назад

Makes sense. Not endorsing, but it makes sense, ladies and gentlemen. A lot of sense.
1:32

Makes sense. Not endorsing, but it makes sense, ladies and gentlemen. A lot of sense.

Katswiri👑

16,580 просмотров • 9 месяцев назад

Jensen Huang says agentic AI is not a chatbot. It is a "digital robot" -- and the next bottleneck is not the model. It is first-person data. "Agentic AI is just a digital robot. It understands, it reasons, it plans, and it acts and uses tools." Then he makes the bigger jump: "The world's video data is from a third person, not first person. And so agentic systems, robotic systems, physical AI -- the data is the hardest problem." That is the hidden constraint in robotics. LLMs got the internet. Physical AI needs demonstrations, synthetic worlds, reinforcement learning, and first-person experience. This is why Jensen keeps calling it a stack: robots are not waiting for one magical model. They need the data engine, the simulator, the reward system, the runtime, and the computer. The next wave of AI is not just software that talks. It is software that sees, plans, acts, and eventually moves through the world.
2:32

Jensen Huang says agentic AI is not a chatbot. It is a "digital robot" -- and the next bottleneck is not the model. It is first-person data. "Agentic AI is just a digital robot. It understands, it reasons, it plans, and it acts and uses tools." Then he makes the bigger jump: "The world's video data is from a third person, not first person. And so agentic systems, robotic systems, physical AI -- the data is the hardest problem." That is the hidden constraint in robotics. LLMs got the internet. Physical AI needs demonstrations, synthetic worlds, reinforcement learning, and first-person experience. This is why Jensen keeps calling it a stack: robots are not waiting for one magical model. They need the data engine, the simulator, the reward system, the runtime, and the computer. The next wave of AI is not just software that talks. It is software that sees, plans, acts, and eventually moves through the world.

Karl Mehta

14,140 просмотров • 1 месяц назад

Taking the Patriots just because of Dave Portnoy ? It kind of makes sense
1:39

Taking the Patriots just because of Dave Portnoy ? It kind of makes sense

Wake Up Barstool

103,661 просмотров • 6 месяцев назад

Pacific Coast Highway is the kind of road that makes you slow down and just take it in.
1:26

Pacific Coast Highway is the kind of road that makes you slow down and just take it in.

The Timeless Traveler 🇺🇸

96,335 просмотров • 4 месяцев назад

"In this situation, Cristiano Ronaldo is to blame as well because he makes it so hard to drop him." Troy Deeney and Phil Kitromilides discuss if Ronaldo should have accepted a role off the bench for Portugal 🔁
2:08

"In this situation, Cristiano Ronaldo is to blame as well because he makes it so hard to drop him." Troy Deeney and Phil Kitromilides discuss if Ronaldo should have accepted a role off the bench for Portugal 🔁

CBS Sports Golazo ⚽️

66,699 просмотров • 1 месяц назад

They are all the same. They think the same way, that is why we are different and it is important for us to stay in our different countries. What he is saying makes sense to many Nigerians but to many of us it makes not sense, it is nonsense!
2:05

They are all the same. They think the same way, that is why we are different and it is important for us to stay in our different countries. What he is saying makes sense to many Nigerians but to many of us it makes not sense, it is nonsense!

Nitos Mitros🇿🇦🇿🇦🇿🇦

17,984 просмотров • 1 месяц назад

Headed over to vote NO on one of Biden’s radical Judges seeking a lifetime appointment to the bench. This Judge makes litigants announce their pronouns and is an avowed Marxist. This is nuts.
0:32

Headed over to vote NO on one of Biden’s radical Judges seeking a lifetime appointment to the bench. This Judge makes litigants announce their pronouns and is an avowed Marxist. This is nuts.

Eric Schmitt

1,273,477 просмотров • 1 год назад