Video yükleniyor...

Video Yüklenemedi

Bu video yüklenirken bir sorun oluştu. Bu geçici bir ağ sorunundan kaynaklanıyor olabilir veya video kullanılamıyor olabilir.

Ana Sayfaya Dön

🚨 Shocking: Frontier LLMs score 85-95% on standard coding benchmarks. We gave them equivalent problems in languages they couldn't have memorized. They collapsed to 0-11%. Presenting EsoLang-Bench. Accepted to the Logical Reasoning and ICBINB workshops at ICLR 2026 🧵

Lossfunk

17,668 subscribers

1,263,932 görüntüleme • 5 ay önce •via X (Twitter)

Eğitim Bilim & Teknoloji

Anya Rossi• Live Now

Private livecam show

0 Yorum

Yorum bulunmuyor

Orijinal gönderinin yorumları burada görünecek

Benzer Videolar

🚨 New Paper Training an LLM to speak low-resource language (EACL workshop, 2026) Tulu is spoken by 2M+ people in coastal Karnataka and LLMs basically can't speak it. We got to 85% grammar accuracy without fine-tuning anything or collecting a single new training example.

🚨 New Paper Training an LLM to speak low-resource language (EACL workshop, 2026) Tulu is spoken by 2M+ people in coastal Karnataka and LLMs basically can't speak it. We got to 85% grammar accuracy without fine-tuning anything or collecting a single new training example.

Lossfunk

121,106 görüntüleme • 5 ay önce

🚨 New Research LLMs are trained only on text... Yet their internal representations progressively organize in ways that resemble human perceptual geometry across different domains (like color, pitch, emotion and taste), with the structures peaking in intermediate layers before attenuating in deeper representations. 🥳 Accepted at ICML Mechanistic Interpretability Workshop 2026

🚨 New Research LLMs are trained only on text... Yet their internal representations progressively organize in ways that resemble human perceptual geometry across different domains (like color, pitch, emotion and taste), with the structures peaking in intermediate layers before attenuating in deeper representations. 🥳 Accepted at ICML Mechanistic Interpretability Workshop 2026

Lossfunk

63,914 görüntüleme • 1 ay önce

On Elections in Hungary: “I'm sure that it would be really upsetting to the gentle Congresswoman; they have one-day election paper votes. And they count there, right there, in small precincts, I guess is what we call them. So, they do have as close to fair elections as possible, not using the machines, and all of the problems we have they don't have.”

On Elections in Hungary: “I'm sure that it would be really upsetting to the gentle Congresswoman; they have one-day election paper votes. And they count there, right there, in small precincts, I guess is what we call them. So, they do have as close to fair elections as possible, not using the machines, and all of the problems we have they don't have.”

Jordan Conradson🇺🇸

11,079 görüntüleme • 8 ay önce

🚨 𝗥𝗘𝗔𝗖𝗧𝗜𝗢𝗡 🚨 "It's down to me now to try and find a solution where we can create more chances and give them players more opportunities to put the ball in the net." Derby County failed to score at home for the seventh consecutive game, as they were beaten 1-0 by Millwall today. Head coach John Eustace gave his thoughts following the loss. Hear more reaction on the Rams Daily podcast 👇 #DCFC

🚨 𝗥𝗘𝗔𝗖𝗧𝗜𝗢𝗡 🚨 "It's down to me now to try and find a solution where we can create more chances and give them players more opportunities to put the ball in the net." Derby County failed to score at home for the seventh consecutive game, as they were beaten 1-0 by Millwall today. Head coach John Eustace gave his thoughts following the loss. Hear more reaction on the Rams Daily podcast 👇 #DCFC

BBC Sport Derby

22,019 görüntüleme • 1 yıl önce

New Benchtalks with John Yang: on ProgramBench (0% frontier models at launch) and the lineage/future of coding benchmarks, from SWE-bench/InterCode to now 01:29 ProgramBench launch and reception 03:41 Why artifact-level evaluation, not code-level 06:03 Why models love Python 08:29 ProgramBench as a research tool 12:45 From SWE-bench & InterCode to ProgramBench 17:47 How to grade a coding model 21:53 The position paper & humans in the loop 25:01 Managing quality with agents-in-the-loop 28:40 Internet access and benchmark integrity 35:26 Where models may surpass human abilities 38:56 When a model hits 80% on ProgramBench 43:55 Benchmarks worth paying attention to 46:24 What benchmark do you wish existed 49:32 Will benchmarks still look like benchmarks in 5 years 52:02 How to contribute to ProgramBench

New Benchtalks with John Yang: on ProgramBench (0% frontier models at launch) and the lineage/future of coding benchmarks, from SWE-bench/InterCode to now 01:29 ProgramBench launch and reception 03:41 Why artifact-level evaluation, not code-level 06:03 Why models love Python 08:29 ProgramBench as a research tool 12:45 From SWE-bench & InterCode to ProgramBench 17:47 How to grade a coding model 21:53 The position paper & humans in the loop 25:01 Managing quality with agents-in-the-loop 28:40 Internet access and benchmark integrity 35:26 Where models may surpass human abilities 38:56 When a model hits 80% on ProgramBench 43:55 Benchmarks worth paying attention to 46:24 What benchmark do you wish existed 49:32 Will benchmarks still look like benchmarks in 5 years 52:02 How to contribute to ProgramBench

vincent sunn chen

26,838 görüntüleme • 2 ay önce

🚨🇺🇸 President Trump on Kurds and his order to attack Iran: “I'm very disappointed in the Kurds, we gave them weapons to deliver inside Iran, but they kept them instead. The Kurds take, take, take.”

🚨🇺🇸 President Trump on Kurds and his order to attack Iran: “I'm very disappointed in the Kurds, we gave them weapons to deliver inside Iran, but they kept them instead. The Kurds take, take, take.”

The Saviour

23,755 görüntüleme • 3 ay önce

#WATCH | US President Donald Trump says, "We have the strongest military in the world. And I gave them (Iran) a break at the request of Pakistan... We stopped them from going to war with India. You would have had a nuclear war if it weren't for me. But they became friendly to me. They're close to Iran, and they work, and they still are working on trying to get them to do what's right. But we want a deal that's meaningful. We want a deal that works..." (Source: YouTube/White House)

#WATCH | US President Donald Trump says, "We have the strongest military in the world. And I gave them (Iran) a break at the request of Pakistan... We stopped them from going to war with India. You would have had a nuclear war if it weren't for me. But they became friendly to me. They're close to Iran, and they work, and they still are working on trying to get them to do what's right. But we want a deal that's meaningful. We want a deal that works..." (Source: YouTube/White House)

ANI

186,802 görüntüleme • 2 ay önce

Iranian President Masoud Pezeshkian: The fact that we have problems in our society is something obvious and undeniable. The fact that Israel and foreigners are waiting to exploit and steer our problems is an undeniable reality for anyone with political vision and insight. The very people who were fueling these situations were Netanyahu and Trump. Do they truly want to solve our country's problems? Honestly, besides them creating problems for this nation, has anyone else caused such trouble? They have blocked all paths for us, they don’t let any transactions be made, and they sabotage every initiative we try to implement to keep us from standing on our feet. Then they tell some people, "We want to save you," after having created these painful problems for us. We are at fault; there’s no doubt about it. But we are all at fault. Anyone who tries to distance themselves from responsibility is being unfair—whether they are reformists, principlists, or anyone else making claims.

Iranian President Masoud Pezeshkian: The fact that we have problems in our society is something obvious and undeniable. The fact that Israel and foreigners are waiting to exploit and steer our problems is an undeniable reality for anyone with political vision and insight. The very people who were fueling these situations were Netanyahu and Trump. Do they truly want to solve our country's problems? Honestly, besides them creating problems for this nation, has anyone else caused such trouble? They have blocked all paths for us, they don’t let any transactions be made, and they sabotage every initiative we try to implement to keep us from standing on our feet. Then they tell some people, "We want to save you," after having created these painful problems for us. We are at fault; there’s no doubt about it. But we are all at fault. Anyone who tries to distance themselves from responsibility is being unfair—whether they are reformists, principlists, or anyone else making claims.

Clash Report

12,865 görüntüleme • 6 ay önce

Introducing ALE-Bench, ALE-Agent! Towards Automating Long-Horizon Algorithm Engineering for Hard Optimization Problems Blog: Paper: ALE-Bench is a coding benchmark primarily focused on hard optimization (NP-hard) problems. We developed this benchmark with AtCoder Inc., a leading coding contest platform company. What makes ALE-Bench unique is its focus on hard optimization problems that demand long-horizon and creative reasoning. It’s open-ended, in the sense that true optima are out of reach (NP-hard) and scores can continuously improve. We believe this benchmark has the potential to become one of the key benchmarks for reasoning and coding in the next generation. ALE-Agent is our end-to-end agent that we specifically designed for this challenging domain. In fact, our ALE-Agent has already built an impressive track record in the wild! In May 2025, our agent participated in a live AtCoder Heuristic Competition (AHC), alongside 1,000 other participants in real-time. AHC is considered to be one of the most challenging coding competitions in this domain. Our ALE-Agent achieved an impressive ranking of 21st out of 1,000 human participants in the competition (top 2%), marking a turning point for AI discovery of solutions to hard optimization problems with a wide spectrum of important real world applications such as logistics, routing, packing, factory production planning, power-grid balancing. We look forward to applying this technology to real industrial optimization opportunities. Building on the insights from this study, Sakana AI will continue to tackle the challenge of developing AI with even greater algorithm engineering capabilities. ALE-Bench Dataset: ALE-Bench Code: This research was conducted in collaboration with AtCoder Inc. (AtCoder). We are deeply grateful for their outstanding expertise and contributions in optimization and algorithms, which were invaluable in providing data, analyzing results, and enabling our AI agent’s participation in their contests.

Introducing ALE-Bench, ALE-Agent! Towards Automating Long-Horizon Algorithm Engineering for Hard Optimization Problems Blog: Paper: ALE-Bench is a coding benchmark primarily focused on hard optimization (NP-hard) problems. We developed this benchmark with AtCoder Inc., a leading coding contest platform company. What makes ALE-Bench unique is its focus on hard optimization problems that demand long-horizon and creative reasoning. It’s open-ended, in the sense that true optima are out of reach (NP-hard) and scores can continuously improve. We believe this benchmark has the potential to become one of the key benchmarks for reasoning and coding in the next generation. ALE-Agent is our end-to-end agent that we specifically designed for this challenging domain. In fact, our ALE-Agent has already built an impressive track record in the wild! In May 2025, our agent participated in a live AtCoder Heuristic Competition (AHC), alongside 1,000 other participants in real-time. AHC is considered to be one of the most challenging coding competitions in this domain. Our ALE-Agent achieved an impressive ranking of 21st out of 1,000 human participants in the competition (top 2%), marking a turning point for AI discovery of solutions to hard optimization problems with a wide spectrum of important real world applications such as logistics, routing, packing, factory production planning, power-grid balancing. We look forward to applying this technology to real industrial optimization opportunities. Building on the insights from this study, Sakana AI will continue to tackle the challenge of developing AI with even greater algorithm engineering capabilities. ALE-Bench Dataset: ALE-Bench Code: This research was conducted in collaboration with AtCoder Inc. (AtCoder). We are deeply grateful for their outstanding expertise and contributions in optimization and algorithms, which were invaluable in providing data, analyzing results, and enabling our AI agent’s participation in their contests.

Sakana AI

237,195 görüntüleme • 1 yıl önce

Jim Nill on the Stars 5-on-5 play during the First-Round against the Wild. “I don't think we got to the hard areas quick enough and hard enough, and it's hard to score in these tight games. We gave them some easy goals. They were giving us some easy goals. I mean, our power play could have won the series for us. We were a good team, 5-on-5 in the regular season; but we have to get better.”

Jim Nill on the Stars 5-on-5 play during the First-Round against the Wild. “I don't think we got to the hard areas quick enough and hard enough, and it's hard to score in these tight games. We gave them some easy goals. They were giving us some easy goals. I mean, our power play could have won the series for us. We were a good team, 5-on-5 in the regular season; but we have to get better.”

Abby Jones

14,070 görüntüleme • 3 ay önce

We had to take Palestine in small doses. - President Harry Truman: "The Zionists, particularly, were against ANYTHING that is to be done if they couldn't have the whole of Palestine and everything HANDED to them on a SILVER PLATE so they wouldn't have to do anything." It's almost like it's always been this way.....

We had to take Palestine in small doses. - President Harry Truman: "The Zionists, particularly, were against ANYTHING that is to be done if they couldn't have the whole of Palestine and everything HANDED to them on a SILVER PLATE so they wouldn't have to do anything." It's almost like it's always been this way.....

DD Geopolitics

206,390 görüntüleme • 1 yıl önce

Afriforum went to court seeking finality on “Kill The Boer Kill The Farmer”. The court gave that finality. They don’t like that finality, and now want to re-open a debate some of us defeated them in so viciously at the SABC, they drank water like Julius Mkhwanazi. We no longer have any responsibility to debate the matter any further, even if they fundraise blacks on podcasts to re-open it, Asizi! We respect the courts which Afriforum provoked to make a judgement. The racist US Ambassador they mobilised tried to disrespect the courts motivated by them, he quickly withdrew. We proceed.

Afriforum went to court seeking finality on “Kill The Boer Kill The Farmer”. The court gave that finality. They don’t like that finality, and now want to re-open a debate some of us defeated them in so viciously at the SABC, they drank water like Julius Mkhwanazi. We no longer have any responsibility to debate the matter any further, even if they fundraise blacks on podcasts to re-open it, Asizi! We respect the courts which Afriforum provoked to make a judgement. The racist US Ambassador they mobilised tried to disrespect the courts motivated by them, he quickly withdrew. We proceed.

Sinawo Thambo

26,949 görüntüleme • 5 ay önce

Much of what you’ve heard about the Kurds in recent news is not true. I’m here to set the story straight on who the Kurds are, what they have meant to America, and why they still matter so much in the Middle East. They have been loyal allies. They have fought at our side. And it’s time we understood them. Full episode at the link: #Kurds #Kurdish #Trump #MiddleEast

Much of what you’ve heard about the Kurds in recent news is not true. I’m here to set the story straight on who the Kurds are, what they have meant to America, and why they still matter so much in the Middle East. They have been loyal allies. They have fought at our side. And it’s time we understood them. Full episode at the link: #Kurds #Kurdish #Trump #MiddleEast

Stephen Mansfield

38,033 görüntüleme • 2 ay önce

🚨 Labour Attorney General’s Shocking Smear About Reform and Tories In his BBC interview with Nick Robinson, Hermer argued we must stay in the ECHR to secure deals with France and Germany to stop small boats. He asked what Reform and the Conservatives would do without such cooperation. Robinson replied: “they say would round them up on the beaches and send them somewhere else.” Hermer’s shocking response: “what they mean is by that is they would let people drown in the water.” Reform and the Conservatives have never said or wanted any such thing. A disgraceful smear from Labour’s top lawyer.

🚨 Labour Attorney General’s Shocking Smear About Reform and Tories In his BBC interview with Nick Robinson, Hermer argued we must stay in the ECHR to secure deals with France and Germany to stop small boats. He asked what Reform and the Conservatives would do without such cooperation. Robinson replied: “they say would round them up on the beaches and send them somewhere else.” Hermer’s shocking response: “what they mean is by that is they would let people drown in the water.” Reform and the Conservatives have never said or wanted any such thing. A disgraceful smear from Labour’s top lawyer.

Skint Eastwood

40,074 görüntüleme • 2 ay önce

We are excited to share that Logan Kilpatrick joined us on The Bench to discuss Google's new Gemini 3.5 Flash: why it's deliberately more persistent and capable than previous Flash models, how it hit #1 on our FinanceAgent Benchmark taking 82 steps where competitors stopped at 13, and what justifies the price increase. We also get into why AI benchmarks need a paradigm shift, the trade-off of building everything vs staying focused, the Pope, and why Omni might kill the Subway Surfers content era. 0:11:00 – Flash is being rebased for the agent era, not just a cheaper model anymore 0:14:03 – Persistence by design: 82 tool calls vs competitors' 13 0:17:52 – Why pricing went up and how Google thinks about value per token 0:22:55 – Coding performance: from 20th to 10th place in one generation 0:28:28 – Why benchmarks have historically been misleading and what the new era of evaluation looks like 0:29:28 Logan on why Google has the best researchers in the world 0:36:16 – The cost of being Google 0:39:07 – The Pope’s encyclical on AI and whether most people see frontier intelligence as a good thing 0:51:12 – Why Omni is the thing that recently clicked

We are excited to share that Logan Kilpatrick joined us on The Bench to discuss Google's new Gemini 3.5 Flash: why it's deliberately more persistent and capable than previous Flash models, how it hit #1 on our FinanceAgent Benchmark taking 82 steps where competitors stopped at 13, and what justifies the price increase. We also get into why AI benchmarks need a paradigm shift, the trade-off of building everything vs staying focused, the Pope, and why Omni might kill the Subway Surfers content era. 0:11:00 – Flash is being rebased for the agent era, not just a cheaper model anymore 0:14:03 – Persistence by design: 82 tool calls vs competitors' 13 0:17:52 – Why pricing went up and how Google thinks about value per token 0:22:55 – Coding performance: from 20th to 10th place in one generation 0:28:28 – Why benchmarks have historically been misleading and what the new era of evaluation looks like 0:29:28 Logan on why Google has the best researchers in the world 0:36:16 – The cost of being Google 0:39:07 – The Pope’s encyclical on AI and whether most people see frontier intelligence as a good thing 0:51:12 – Why Omni is the thing that recently clicked

Vals AI

16,486 görüntüleme • 2 ay önce

🚨🇺🇸 BREAKING — Trump Admits Socialism Works "I have to say, I respect China, because it’s incredible that with a system that, in theory, shouldn’t work—you know, we go to school, we go to the best business schools, we do well in those schools, and we read about free entrepreneurship, and we read about all these different things— But if you look at China, how well they do, how much they produce. I mean, they produce so many cars that they actually have competitions over who can produce the fewest cars because they have so many cars. You have to have great respect for China for the work they do. Whether you like them or not, you have to respect them."

🚨🇺🇸 BREAKING — Trump Admits Socialism Works "I have to say, I respect China, because it’s incredible that with a system that, in theory, shouldn’t work—you know, we go to school, we go to the best business schools, we do well in those schools, and we read about free entrepreneurship, and we read about all these different things— But if you look at China, how well they do, how much they produce. I mean, they produce so many cars that they actually have competitions over who can produce the fewest cars because they have so many cars. You have to have great respect for China for the work they do. Whether you like them or not, you have to respect them."

Pamphlets

1,568,632 görüntüleme • 5 ay önce

President Tinubu today criticized the opposition on electricity privatization: “We have leaders who have privatized electricity that is not working. They gave us darkness, and we are trying to get ourselves through that to build a nation of bright hope and joyful people, leaving our children with a life worthy of pride. But, they don’t even believe in the democracy they preach, don’t pay attention to them.”

President Tinubu today criticized the opposition on electricity privatization: “We have leaders who have privatized electricity that is not working. They gave us darkness, and we are trying to get ourselves through that to build a nation of bright hope and joyful people, leaving our children with a life worthy of pride. But, they don’t even believe in the democracy they preach, don’t pay attention to them.”

Imran Muhammad

558,507 görüntüleme • 4 ay önce

🚨 PRESIDENT TRUMP JUST NAILED IT: "Democrats SCREAM, 'affordability, affordability!' They got one good line of BULLSH*T!" 🤣🔥 "THEY'RE the ones who caused the problem!" "You HAVE to get out and vote in the midterms!" "We brought prices way down. They gave us tremendously high prices, and they'll give them to you again if they take over."

🚨 PRESIDENT TRUMP JUST NAILED IT: "Democrats SCREAM, 'affordability, affordability!' They got one good line of BULLSH*T!" 🤣🔥 "THEY'RE the ones who caused the problem!" "You HAVE to get out and vote in the midterms!" "We brought prices way down. They gave us tremendously high prices, and they'll give them to you again if they take over."

Eric Daugherty

30,491 görüntüleme • 3 ay önce