正在加载视频...

视频加载失败

加载此视频时出现问题。这可能是由于临时网络问题，或视频可能不可用。

Can AI tell when a question is total nonsense, or does it just make up an answer? Peter Gostev (SF 24-28 August) tested 80 models with nonsense questions. Some pushed back. Others confidently invented fake metrics and kept going. All of them were ranked on the "BS Bench". One... show more

Arena.ai

217,092 subscribers

10,943 次观看 • 6 个月前 •via X (Twitter)

Anya Rossi• Live Now

Private livecam show

0 条评论

暂无评论

原始帖子的评论将显示在这里

相关视频

Hello! Here's the latest from my Star Wars nonsense - I just finished up the Mon Calamari Frigate I started working on back in 2020, finally, and decided to make a quick video of it with some other ships that I'd made! 4K in the 🧵!

Hello! Here's the latest from my Star Wars nonsense - I just finished up the Mon Calamari Frigate I started working on back in 2020, finally, and decided to make a quick video of it with some other ships that I'd made! 4K in the 🧵!

Howie Day

49,634 次观看 • 2 个月前

The creator of Ruby on Rails is all in on AI...but that doesn't mean he's rushing to build it into the framework just yet. On the newest On Rails, DHH joins Robby Russell to talk Rails, the Basecamp 5 launch, and AI-assisted development: "It is a professional obligation of every programmer to take this revolution seriously." Curious where Rails is headed? Listen or watch the full episode on YouTube (link in thread).

The creator of Ruby on Rails is all in on AI...but that doesn't mean he's rushing to build it into the framework just yet. On the newest On Rails, DHH joins Robby Russell to talk Rails, the Basecamp 5 launch, and AI-assisted development: "It is a professional obligation of every programmer to take this revolution seriously." Curious where Rails is headed? Listen or watch the full episode on YouTube (link in thread).

Ruby on Rails

54,894 次观看 • 3 个月前

🇺🇸 Trump already admitted it out loud: the uranium retrieval push is just optics. Fmr. Lt. Col. Daniel Davis questions whether Trump can still make a logical decision. "It is harder and harder for me to see any plan on any subject with Trump. It's not even just transactional. It's just momentary." The war hawks were wrong before. But does Trump remember that? Daniel Davis Deep Dive

🇺🇸 Trump already admitted it out loud: the uranium retrieval push is just optics. Fmr. Lt. Col. Daniel Davis questions whether Trump can still make a logical decision. "It is harder and harder for me to see any plan on any subject with Trump. It's not even just transactional. It's just momentary." The war hawks were wrong before. But does Trump remember that? Daniel Davis Deep Dive

Mario Nawfal

34,399 次观看 • 4 个月前

Made a breakdown of Meme Madness on Cade because there's more going on here than just predicting UP or DOWN. All-Stars vs Underdogs. Daily resets. Battle Mode. $120k on the line, free to play. Watch it, then tell me: → which coin earns the next All-Star spot? August 24th, we get into the madness. be part of the meme madness by signing up with the link in the cs. Steve Rookmate Kosgood BBHENCjPD2919Kn13ETfMvUgbb1hqT36Ggdzwysa89N6

Made a breakdown of Meme Madness on Cade because there's more going on here than just predicting UP or DOWN. All-Stars vs Underdogs. Daily resets. Battle Mode. $120k on the line, free to play. Watch it, then tell me: → which coin earns the next All-Star spot? August 24th, we get into the madness. be part of the meme madness by signing up with the link in the cs. Steve Rookmate Kosgood BBHENCjPD2919Kn13ETfMvUgbb1hqT36Ggdzwysa89N6

Damilola

12,631 次观看 • 1 个月前

We raised $4.8M to build Lamina Labs (YC P26) and make AI explain with video, not just text. Introducing Simi, the fastest way to make an explainer video. Give it a single prompt or document, and it can generate a one-minute narrated explainer in as little as 20 seconds, in 80+ languages. It works like ChatGPT, except the answer is a video. The round was led by Foundation Capital , with participation from Link Ventures and Y Combinator . This is our story. Thread below on what we are building at.

We raised $4.8M to build Lamina Labs (YC P26) and make AI explain with video, not just text. Introducing Simi, the fastest way to make an explainer video. Give it a single prompt or document, and it can generate a one-minute narrated explainer in as little as 20 seconds, in 80+ languages. It works like ChatGPT, except the answer is a video. The round was led by Foundation Capital , with participation from Link Ventures and Y Combinator . This is our story. Thread below on what we are building at.

Sudip

1,098,931 次观看 • 2 个月前

I am very excited to share the first-ever "Open Book" monthly Q&A with you all. There were a lot of amazing questions, please keep asking them and I will make this a monthly ritual. You can watch the episode on X or YouTube using the link in the subtweet.

I am very excited to share the first-ever "Open Book" monthly Q&A with you all. There were a lot of amazing questions, please keep asking them and I will make this a monthly ritual. You can watch the episode on X or YouTube using the link in the subtweet.

Anthony Scaramucci

16,467 次观看 • 1 年前

I think this was the height of my happiness last season next to Luka’s game winner vs. Denver. Coming off a back to back walk down on Houston, we come back again, Luka’s going to the line for 60, everyone on the bench happy, celebrating him…just couldn’t beat the vibes at this time, man. All the talk about Bron supposedly ruining the vibes opening night and all that nonsense being put to bed. Remains criminal we were robbed of seeing this team at full strength in the playoffs. Even if OKC or SA were better, we were robbed of the chance to fight for it smh.

I think this was the height of my happiness last season next to Luka’s game winner vs. Denver. Coming off a back to back walk down on Houston, we come back again, Luka’s going to the line for 60, everyone on the bench happy, celebrating him…just couldn’t beat the vibes at this time, man. All the talk about Bron supposedly ruining the vibes opening night and all that nonsense being put to bed. Remains criminal we were robbed of seeing this team at full strength in the playoffs. Even if OKC or SA were better, we were robbed of the chance to fight for it smh.

Richard Staple, BSN, RN🇯🇲

117,979 次观看 • 2 个月前

🪑 BTS BENCH IN SINGAPORE 💜 Last year when we found out the BTS Zoo bench term was over, we were devastated. We loved that bench as a touchstone to visit, and we were determined to make a new one for ARMY in Singapore. We had been eyeing the Esplanade benches for some time already and were gratified to find that fellow ARMY To the Moon and Back | Coco was feeling the same. Together we worked out a plan to co-sponsor most of the adoption fee for the bench and call for donations for the rest of it - we wanted everyone to share in the ownership of this project. This is truly a bench for ARMY, by ARMY, because of BTS. Thanks to all of you for walking with us on this journey! We hope this bench, located in a public area that’s still quiet and tranquil and with one of the best views in Singapore, will continue the legacy of the zoo bench. It’ll be here for the next 10 years - a place where ARMY can come to sit and think, listen to music, enjoy the view, and maybe make an ARMY friend or two. Love, the bora dot the bora dot 🟣 (BTS SG Fanbase) Location: Esplanade Singapore, Level 4 Rooftop

🪑 BTS BENCH IN SINGAPORE 💜 Last year when we found out the BTS Zoo bench term was over, we were devastated. We loved that bench as a touchstone to visit, and we were determined to make a new one for ARMY in Singapore. We had been eyeing the Esplanade benches for some time already and were gratified to find that fellow ARMY To the Moon and Back | Coco was feeling the same. Together we worked out a plan to co-sponsor most of the adoption fee for the bench and call for donations for the rest of it - we wanted everyone to share in the ownership of this project. This is truly a bench for ARMY, by ARMY, because of BTS. Thanks to all of you for walking with us on this journey! We hope this bench, located in a public area that’s still quiet and tranquil and with one of the best views in Singapore, will continue the legacy of the zoo bench. It’ll be here for the next 10 years - a place where ARMY can come to sit and think, listen to music, enjoy the view, and maybe make an ARMY friend or two. Love, the bora dot the bora dot 🟣 (BTS SG Fanbase) Location: Esplanade Singapore, Level 4 Rooftop

the bora dot 🟣 (BTS SG Fanbase)

19,887 次观看 • 4 个月前

What if some SIDS cases aren't as random as we've been told? Some questions carry more weight than others, and this is one of them — a guest challenges one of the most heartbreaking assumptions in pediatric health, and the host's reaction says it all. It's a hard watch, but if you're a parent, or ever plan to be, this is the conversation you didn't know you needed. Save this one. It might matter more than you think. Watch the full episode on my YT channel! Link is in the comments 📷

What if some SIDS cases aren't as random as we've been told? Some questions carry more weight than others, and this is one of them — a guest challenges one of the most heartbreaking assumptions in pediatric health, and the host's reaction says it all. It's a hard watch, but if you're a parent, or ever plan to be, this is the conversation you didn't know you needed. Save this one. It might matter more than you think. Watch the full episode on my YT channel! Link is in the comments 📷

Jillian Michaels

39,954 次观看 • 1 个月前

INSANE 🤪 Candace Owens makes up a FAKE Erika Kirk conspiracy off of the top of her head and runs with it as fact‼️ Watch as Candace admits she has NO PROOF and is just speculating before she proceeds to make up a FAKE phone call between Erika Kirk and JD Vance that never happened. She even MOCKS Erika and fake cries while reenacting the phone call that she just totally made up on the spot. She claims to have gathered all of this from the “Energy” she got from JD Vance after watching him on TV. Just absolutely psychotic nonsense.

INSANE 🤪 Candace Owens makes up a FAKE Erika Kirk conspiracy off of the top of her head and runs with it as fact‼️ Watch as Candace admits she has NO PROOF and is just speculating before she proceeds to make up a FAKE phone call between Erika Kirk and JD Vance that never happened. She even MOCKS Erika and fake cries while reenacting the phone call that she just totally made up on the spot. She claims to have gathered all of this from the “Energy” she got from JD Vance after watching him on TV. Just absolutely psychotic nonsense.

Cinema Shogun

28,473 次观看 • 5 个月前

🎙️ Want a full breakdown on why cost per token is a key metric for AI infrastructure TCO? We’re operating in a power-constrained world. Demand for intelligence is scaling faster than infrastructure can keep up—so metrics like cost per GPU hour or FLOPs per dollar don’t tell the full story. When it comes to TCO, Cost per Token is the metric that captures end-to-end performance across GPUs, CPUs, networking, software, and ecosystem making it the key driver of real profitability and scalability in AI. If you’re not measuring efficiency at the token level, you’re missing what actually drives cost. Watch the deep-dive conversation with Dr. Gerro Prinsloo , Nader Khalil and Carter Abdallah, live on the NVIDIA YouTube channel.

🎙️ Want a full breakdown on why cost per token is a key metric for AI infrastructure TCO? We’re operating in a power-constrained world. Demand for intelligence is scaling faster than infrastructure can keep up—so metrics like cost per GPU hour or FLOPs per dollar don’t tell the full story. When it comes to TCO, Cost per Token is the metric that captures end-to-end performance across GPUs, CPUs, networking, software, and ecosystem making it the key driver of real profitability and scalability in AI. If you’re not measuring efficiency at the token level, you’re missing what actually drives cost. Watch the deep-dive conversation with Dr. Gerro Prinsloo , Nader Khalil and Carter Abdallah, live on the NVIDIA YouTube channel.

NVIDIA

21,970 次观看 • 5 个月前

🚨 HOLY CRAP! Sec. Scott Bessent is putting up with ZERO BS from the fake news today REPORTER: Why are Trump's tariffs not a tax?! BESSENT: Tariffs are not a tax, it's a SURCHARGE...when you pay a fee for your driver's license, is that a tax? Is it? REPORTER: I'm asking you a question, sir, I'd just appreciate an answer. BESSENT: I'm giving you an answer you maybe DON'T LIKE. The other thing - this [tariff] case, and Ambassador Jamieson is a lawyer... REPORTER: As am I. BESSENT: I won't tell you the one thing I agreed with Lenin on.😂

🚨 HOLY CRAP! Sec. Scott Bessent is putting up with ZERO BS from the fake news today REPORTER: Why are Trump's tariffs not a tax?! BESSENT: Tariffs are not a tax, it's a SURCHARGE...when you pay a fee for your driver's license, is that a tax? Is it? REPORTER: I'm asking you a question, sir, I'd just appreciate an answer. BESSENT: I'm giving you an answer you maybe DON'T LIKE. The other thing - this [tariff] case, and Ambassador Jamieson is a lawyer... REPORTER: As am I. BESSENT: I won't tell you the one thing I agreed with Lenin on.😂

Eric Daugherty

2,736,007 次观看 • 11 个月前

I just made a full walkthrough on how I built an AI chatbot trained on someone’s YouTube videos so it can answer questions about what they teach (I built one on Ryan Clogg's video catalog) inside, I show: – how I collect and organize the video content – build the knowledge base so it gives accurate answers – set the rules for how it responds – setting up guardrails so it doesn’t go off-topic or give wrong answers – testing and improving it so it keeps getting better if you want the walkthrough, comment “YT” and I’ll DM you the full guide (must be following)

I just made a full walkthrough on how I built an AI chatbot trained on someone’s YouTube videos so it can answer questions about what they teach (I built one on Ryan Clogg's video catalog) inside, I show: – how I collect and organize the video content – build the knowledge base so it gives accurate answers – set the rules for how it responds – setting up guardrails so it doesn’t go off-topic or give wrong answers – testing and improving it so it keeps getting better if you want the walkthrough, comment “YT” and I’ll DM you the full guide (must be following)

Tyler

41,292 次观看 • 1 年前

This reaction spirals out of control fast — and it does NOT stop where you think it will. It opens with a deep dive into one of the most polarizing streamers on the internet, and within minutes it's pulling in even more controversial commentators to pile onto the conversation. Every new name that gets brought up adds more fuel to the fire, and the reactions get more heated with each one. Watch the full episode on my YT channel! Link is in the comments 📷

This reaction spirals out of control fast — and it does NOT stop where you think it will. It opens with a deep dive into one of the most polarizing streamers on the internet, and within minutes it's pulling in even more controversial commentators to pile onto the conversation. Every new name that gets brought up adds more fuel to the fire, and the reactions get more heated with each one. Watch the full episode on my YT channel! Link is in the comments 📷

Jillian Michaels

30,792 次观看 • 1 个月前

OXFORD AI PROFESSOR FED 100,000 MANUSCRIPTS DATING BACK TO 3000 BCE INTO A SINGLE KNOWLEDGE GRAPH - AND THEN ASKED IT HOW MUCH TRUTH IS IN MORMONISM the answer came back at 2% this is what an AI brain looks like when you've trained it on over 100,000 historical manuscripts going back to 3000 BCE every node in the graph is a concept and every connection shows how ideas relate across 5,000 years of human knowledge the system didn't just give an answer - it traced its reasoning across thousands of interconnected sources and cross-referenced historical records before producing a single number he's now taking questions on what to ask it next the list of topics people want tested is exactly what you'd expect.

OXFORD AI PROFESSOR FED 100,000 MANUSCRIPTS DATING BACK TO 3000 BCE INTO A SINGLE KNOWLEDGE GRAPH - AND THEN ASKED IT HOW MUCH TRUTH IS IN MORMONISM the answer came back at 2% this is what an AI brain looks like when you've trained it on over 100,000 historical manuscripts going back to 3000 BCE every node in the graph is a concept and every connection shows how ideas relate across 5,000 years of human knowledge the system didn't just give an answer - it traced its reasoning across thousands of interconnected sources and cross-referenced historical records before producing a single number he's now taking questions on what to ask it next the list of topics people want tested is exactly what you'd expect.

Noisy

267,677 次观看 • 4 个月前

When will MiniMax have a Fable level model? Olive Song, research lead at MiniMax (official), joins The Bench to answer that question, plus M3, open source models closing the gap on Vibe Code Bench, and the truth about 996 culture. Full episode out now! 7:19 – Inside MiniMax's research culture: AI agents tracking papers since early last year 18:01- The headline of M3: native multimodality and one million tokens of context 21:10- The bottleneck of building models is people, not compute 22:48 – Does MiniMax work 996? 25:47 - Olive's prediction and the 30 point gap on Vibe Code Bench 32:02- Model capabilities Olive is most excited about 32:35- The lab Olive most respects outside of MiniMax 36:24- Will more labs go open source a year from now?

When will MiniMax have a Fable level model? Olive Song, research lead at MiniMax (official), joins The Bench to answer that question, plus M3, open source models closing the gap on Vibe Code Bench, and the truth about 996 culture. Full episode out now! 7:19 – Inside MiniMax's research culture: AI agents tracking papers since early last year 18:01- The headline of M3: native multimodality and one million tokens of context 21:10- The bottleneck of building models is people, not compute 22:48 – Does MiniMax work 996? 25:47 - Olive's prediction and the 30 point gap on Vibe Code Bench 32:02- Model capabilities Olive is most excited about 32:35- The lab Olive most respects outside of MiniMax 36:24- Will more labs go open source a year from now?

Vals AI

49,462 次观看 • 2 个月前

Let's talk about this lift, but let's do so in a way to move the strength and conditioning profession forward. There is too much weight on the bar. The athlete cannot do that much weight without the spotter pulling them up off the ground. We know these things to be true. Does this mean split squat should not have a 1RM? Or should not be 1RM (or rep tested)? No it does not. Split Squat should. It should just be assessed properly with no pulling up out of the bottom (just like a back squat should not, or spotters hands on a bench press). Love to see the safety with other spotters on each side, would just like to see less slamming knee on ground and needing to be pulled up out of the bottom. TL;DR - 1RM or rep max your split squat/reverse lunge, just make sure you don't let athletes slam their knee on the ground and make sure you don't pull the athlete up out of the bottom.

Let's talk about this lift, but let's do so in a way to move the strength and conditioning profession forward. There is too much weight on the bar. The athlete cannot do that much weight without the spotter pulling them up off the ground. We know these things to be true. Does this mean split squat should not have a 1RM? Or should not be 1RM (or rep tested)? No it does not. Split Squat should. It should just be assessed properly with no pulling up out of the bottom (just like a back squat should not, or spotters hands on a bench press). Love to see the safety with other spotters on each side, would just like to see less slamming knee on ground and needing to be pulled up out of the bottom. TL;DR - 1RM or rep max your split squat/reverse lunge, just make sure you don't let athletes slam their knee on the ground and make sure you don't pull the athlete up out of the bottom.

StrengthCoachNetwork

40,361 次观看 • 10 个月前

Draymond Green with a message to Myron Gardner and believes he’s putting a target on his back 👀 “Most of yall prolly like ‘who the hell is Myron Gardner. Myron if you remember a month ago we played the Miami Heat… Podz played great in the 4th quarter and every shot he made he kept talking to the bench. Who he was talking to was Myron Gardner… Myron Gardner this is becoming his MO… You gotta back it up it can’t just be imma pick these fights and can’t back it up with the game… Klay Thompson got into it with someone on the Heat bench and Caron Butler made the young fella apologize to Klay Thompson. That was Myron Gardner…. It’s a very slippery slope. Other players when they play the Miami Heat and get opportunity to say something to him, guys on the bench will be killing him. They’re gonna talk bad about him. You put a target on your back and have to make sure you’re ready. I see a lot of guys who aren’t ready for the target on their back. If I’m honest I think Myron Gardner is a different type and he may be ready… One thing for certain. Everybody now knows Myron Gardner name. So capitalize on it” (Via The Draymond Green Show)

Draymond Green with a message to Myron Gardner and believes he’s putting a target on his back 👀 “Most of yall prolly like ‘who the hell is Myron Gardner. Myron if you remember a month ago we played the Miami Heat… Podz played great in the 4th quarter and every shot he made he kept talking to the bench. Who he was talking to was Myron Gardner… Myron Gardner this is becoming his MO… You gotta back it up it can’t just be imma pick these fights and can’t back it up with the game… Klay Thompson got into it with someone on the Heat bench and Caron Butler made the young fella apologize to Klay Thompson. That was Myron Gardner…. It’s a very slippery slope. Other players when they play the Miami Heat and get opportunity to say something to him, guys on the bench will be killing him. They’re gonna talk bad about him. You put a target on your back and have to make sure you’re ready. I see a lot of guys who aren’t ready for the target on their back. If I’m honest I think Myron Gardner is a different type and he may be ready… One thing for certain. Everybody now knows Myron Gardner name. So capitalize on it” (Via The Draymond Green Show)

Heat Central

329,568 次观看 • 7 个月前