Video wird geladen...

Video konnte nicht geladen werden

Zur Startseite

Fast and wrong is still wrong. Most voice AI benchmarks measure speed. Not accuracy. Speechmatics tops the board on both: → 25% higher accuracy than many others → Sub-second latency across 55+ languages Watch the break down of what the benchmarks mean for production.

theresanaiforit's profile picture

There's An AI For That

35,399 subscribers

12,944 Aufrufe • vor 3 Monaten •via X (Twitter)

LIVE

Anya Rossi• Live Now

Private livecam show

0 Kommentare

Keine Kommentare verfügbar

Kommentare vom Original-Post werden hier angezeigt

Ähnliche Videos

Introducing Scribe — the most accurate Speech to Text model. It has the highest accuracy on benchmarks, outperforming previous state-of-the-art models such as Gemini 2.0 and OpenAI Whisper v3. It’s now the leading model for English, Spanish, Italian, and many more. With support for 99 languages, speaker diarization, character-level timestamps, and non-speech events such as laughing.
0:57

Introducing Scribe — the most accurate Speech to Text model. It has the highest accuracy on benchmarks, outperforming previous state-of-the-art models such as Gemini 2.0 and OpenAI Whisper v3. It’s now the leading model for English, Spanish, Italian, and many more. With support for 99 languages, speaker diarization, character-level timestamps, and non-speech events such as laughing.

ElevenLabs

464,967 Aufrufe • vor 1 Jahr

ARC-AGI is redefining how to measure progress on the path to AGI - focusing on reasoning, generalization, and adaptability instead of memorization or scale. At NeurIPS 2025, YC's Diana sat down with ARC Prize President Greg Kamradt to find out why most AI benchmarks fail, how ARC-AGI reveals the limits of today’s models, and why measuring intelligence may be harder than building it. 00:11 — What ARC Prize is and why it exists 00:38 — François Chollet’s definition of AGI 01:48 — What ARC-AGI Actually Tests 02:25 — When LLMs Failed the ARC Benchmark 03:38 — ARC-AGI Becomes the Standard 04:49 — False Positives in AI Progress 06:06 — The Evolution of ARC-AGI 08:55 — Measuring Intelligence beyond just accuracy 10:25 — What happens if a model solves ARC-AGI?
11:59

ARC-AGI is redefining how to measure progress on the path to AGI - focusing on reasoning, generalization, and adaptability instead of memorization or scale. At NeurIPS 2025, YC's Diana sat down with ARC Prize President Greg Kamradt to find out why most AI benchmarks fail, how ARC-AGI reveals the limits of today’s models, and why measuring intelligence may be harder than building it. 00:11 — What ARC Prize is and why it exists 00:38 — François Chollet’s definition of AGI 01:48 — What ARC-AGI Actually Tests 02:25 — When LLMs Failed the ARC Benchmark 03:38 — ARC-AGI Becomes the Standard 04:49 — False Positives in AI Progress 06:06 — The Evolution of ARC-AGI 08:55 — Measuring Intelligence beyond just accuracy 10:25 — What happens if a model solves ARC-AGI?

Y Combinator

98,369 Aufrufe • vor 8 Monaten

Ranked No. 1 in benchmarks. Lightning speed. Native A/V sync. The era of waiting in line for AI video is over. HappyHorse is now live on Alibaba Cloud Model Studio. Done while others are still rendering. Build now:
0:25

Ranked No. 1 in benchmarks. Lightning speed. Native A/V sync. The era of waiting in line for AI video is over. HappyHorse is now live on Alibaba Cloud Model Studio. Done while others are still rendering. Build now:

Alibaba Cloud

65,701 Aufrufe • vor 3 Monaten

Speed is the wrong metric for AI in service. Enterprises that optimized for faster response times found that faster wrong answers still produce the same escalation rates. The metric that actually matters is resolution. Melody Brue and Keith Kirkpatrick sit down with Shashi Upadhyay, President of Product, Engineering, and AI at Zendesk, live from Zendesk Relate 2026 to break down what autonomous service systems actually demand at the engineering level.
14:59

Speed is the wrong metric for AI in service. Enterprises that optimized for faster response times found that faster wrong answers still produce the same escalation rates. The metric that actually matters is resolution. Melody Brue and Keith Kirkpatrick sit down with Shashi Upadhyay, President of Product, Engineering, and AI at Zendesk, live from Zendesk Relate 2026 to break down what autonomous service systems actually demand at the engineering level.

Six Five Media

232,898 Aufrufe • vor 3 Monaten

🎥 WATCH: What happens when onchain data is wrong? In the latest episode of #CHAINREACTION, Robert Baggs sits down with sqd.ai’s Wanja S. Oberhof to unpack why data accuracy matters for trading, AI and DeFi, how SQD validates blockchain data, and where onchain data layers go next.
1:19

🎥 WATCH: What happens when onchain data is wrong? In the latest episode of #CHAINREACTION, Robert Baggs sits down with sqd.ai’s Wanja S. Oberhof to unpack why data accuracy matters for trading, AI and DeFi, how SQD validates blockchain data, and where onchain data layers go next.

Cointelegraph

43,855 Aufrufe • vor 1 Monat

Before founding Vals AI, Rayan Krishnan was a college radio host. We're thrilled to get him back in his element with Vivek Gopalan, this time talking all things benchmarks and evals. As AI capabilities compound, measuring them is becoming both harder and more important. What started as an academic exercise is quickly evolving into critical infrastructure for understanding what AI systems can actually do, and how they perform in the real world. Rayan and Vivek go deep on how benchmarks are evolving, measuring increasingly agentic systems, the weird and wonderful ways we test intelligence, the global AI race, and why evals sit on the critical path to ASI. 0:44 Importance and evolution of benchmarks 8:16 From academic artifact → real-world value 10:57 The next generation of benchmarks 13:34 Benchmarking models vs. agents 16:20 Building benchmarks for organizations 22:09 Weird and wonderful benchmarks 25:58 The AI arms race: US vs. China 31:02 Why evals are on the critical path to ASI 32:50 Vals Series A
34:33

Before founding Vals AI, Rayan Krishnan was a college radio host. We're thrilled to get him back in his element with Vivek Gopalan, this time talking all things benchmarks and evals. As AI capabilities compound, measuring them is becoming both harder and more important. What started as an academic exercise is quickly evolving into critical infrastructure for understanding what AI systems can actually do, and how they perform in the real world. Rayan and Vivek go deep on how benchmarks are evolving, measuring increasingly agentic systems, the weird and wonderful ways we test intelligence, the global AI race, and why evals sit on the critical path to ASI. 0:44 Importance and evolution of benchmarks 8:16 From academic artifact → real-world value 10:57 The next generation of benchmarks 13:34 Benchmarking models vs. agents 16:20 Building benchmarks for organizations 22:09 Weird and wonderful benchmarks 25:58 The AI arms race: US vs. China 31:02 Why evals are on the critical path to ASI 32:50 Vals Series A

8VC

104,829 Aufrufe • vor 23 Tagen

AI vision models perform well on standard benchmarks like ImageNet, often matching or exceeding human accuracy. But here's what they don't tell you: Move an image by ONE PIXEL and these same models have a meltdown 40% of the time. This brittleness is breaking real systems.
1:10

AI vision models perform well on standard benchmarks like ImageNet, often matching or exceeding human accuracy. But here's what they don't tell you: Move an image by ONE PIXEL and these same models have a meltdown 40% of the time. This brittleness is breaking real systems.

Jack 🤖

122,508 Aufrufe • vor 1 Jahr

Decibel integrates Chainlink Data Streams. What this means for traders: - Sub-second latency - Higher leverage potential - Lower spreads and improved execution efficiency Precision, speed, and transparency. All engineered for the next era of onchain trading.
0:27

Decibel integrates Chainlink Data Streams. What this means for traders: - Sub-second latency - Higher leverage potential - Lower spreads and improved execution efficiency Precision, speed, and transparency. All engineered for the next era of onchain trading.

Decibel

41,488 Aufrufe • vor 10 Monaten

The future of using your phone is not tapping glass. We're launching Willow iOS 2.0 to make your voice actually work. Including Scribe on iOS, faster speed, better accuracy, and a smoother experience across the places you already write. Now on App Store.
0:37

The future of using your phone is not tapping glass. We're launching Willow iOS 2.0 to make your voice actually work. Including Scribe on iOS, faster speed, better accuracy, and a smoother experience across the places you already write. Now on App Store.

Willow

19,977 Aufrufe • vor 2 Monaten

🚨Secretary Chris Wright: "Bernie has it wrong on both points." THE FACTS: ✔️The U.S. must lead in AI to protect our national security—NOT China. ✔️States that have reduced their production of electricity have higher costs—this is not a result of AI data centers.
1:01

🚨Secretary Chris Wright: "Bernie has it wrong on both points." THE FACTS: ✔️The U.S. must lead in AI to protect our national security—NOT China. ✔️States that have reduced their production of electricity have higher costs—this is not a result of AI data centers.

U.S. Department of Energy

12,566 Aufrufe • vor 6 Monaten

.Shyam Sankar says Palantir was able to make Nvidia's Nemotron Ultra model "better than frontier": "I literally almost felt gaslit when, within 24 hours of getting Nemotron up with no post-training, this is vanilla Nemotron Ultra, it did better than frontier." "If you just looked at the numbers, you would say, 'It's nowhere near the Frontier. That shouldn't even be possible.'" "But of course, the benchmarks are wrong. I mean, the benchmarks are right for what the benchmark's measuring, but that's not my business. Those are not the tasks my customers had that they were trying to solve."
0:22

.Shyam Sankar says Palantir was able to make Nvidia's Nemotron Ultra model "better than frontier": "I literally almost felt gaslit when, within 24 hours of getting Nemotron up with no post-training, this is vanilla Nemotron Ultra, it did better than frontier." "If you just looked at the numbers, you would say, 'It's nowhere near the Frontier. That shouldn't even be possible.'" "But of course, the benchmarks are wrong. I mean, the benchmarks are right for what the benchmark's measuring, but that's not my business. Those are not the tasks my customers had that they were trying to solve."

Jawwwn

368,887 Aufrufe • vor 1 Monat

The most effective AI systems don't rely on a single model. Frontier models provide state-of-the-art performance for complex tasks, while routers automatically select lightweight, open-source models for simpler jobs to optimize accuracy, latency, and cost. Learn more:
0:31

The most effective AI systems don't rely on a single model. Frontier models provide state-of-the-art performance for complex tasks, while routers automatically select lightweight, open-source models for simpler jobs to optimize accuracy, latency, and cost. Learn more:

NVIDIA AI

12,152 Aufrufe • vor 5 Monaten

We’re officially a YOUnicorn! 🦄 Excited to share that You.com just raised $100M Series C at a $1.5B valuation, led by Cox Enterprises. We’ve been heads down building the search infrastructure for the AI and agent future. Soon there will be more AI agents using the web than humans, but today's search wasn't built for this. Agents need deep, contextual information from both public web and internal private data to make real decisions. Our web search API delivers the most up-to-date, accurate, and fastest search results for LLMs and agents. Real benchmarks show we consistently outperform the competition on accuracy and speed while staying cost-effective. Today, we’re answering over 1 billion queries every month across enterprises like DuckDuckGo, Windsurf, Harvey, and many others. There is no other startup of recent years at this scale. Grateful to our wonderful employees, customers, partners, and investors who believe in our vision. The agentic era is here - let's build it together. Try our LLM search APIs.
2:25

We’re officially a YOUnicorn! 🦄 Excited to share that You.com just raised $100M Series C at a $1.5B valuation, led by Cox Enterprises. We’ve been heads down building the search infrastructure for the AI and agent future. Soon there will be more AI agents using the web than humans, but today's search wasn't built for this. Agents need deep, contextual information from both public web and internal private data to make real decisions. Our web search API delivers the most up-to-date, accurate, and fastest search results for LLMs and agents. Real benchmarks show we consistently outperform the competition on accuracy and speed while staying cost-effective. Today, we’re answering over 1 billion queries every month across enterprises like DuckDuckGo, Windsurf, Harvey, and many others. There is no other startup of recent years at this scale. Grateful to our wonderful employees, customers, partners, and investors who believe in our vision. The agentic era is here - let's build it together. Try our LLM search APIs.

Richard Socher

63,660 Aufrufe • vor 1 Jahr

The UK 🇬🇧 Visa applicantion is one of the most straightforward process when compared to others. But alot of people still get it wrong - Watch This and Act accordingly.
0:41

The UK 🇬🇧 Visa applicantion is one of the most straightforward process when compared to others. But alot of people still get it wrong - Watch This and Act accordingly.

OgaHANS🇳🇬

53,197 Aufrufe • vor 7 Monaten

#WATCH | Delhi | On the Vande Mataram controversy, Union Minister Gajendra Singh Shekhawat says, "The clarification given by the opposition is because they have realised that they were wrong... I do accept that such a controversy happening for the benchmarks of democratic India is certainly unfortunate, condemnable, and unacceptable." (18.08)
0:37

#WATCH | Delhi | On the Vande Mataram controversy, Union Minister Gajendra Singh Shekhawat says, "The clarification given by the opposition is because they have realised that they were wrong... I do accept that such a controversy happening for the benchmarks of democratic India is certainly unfortunate, condemnable, and unacceptable." (18.08)

ANI

13,718 Aufrufe • vor 18 Tagen

"I'm not going make excuses for Lamar. I will just tell you what my eyes tell me. He ain't right, something is wrong physically with him." The crew break down what is wrong with Lamar Jackson and the Baltimore Ravens.
5:44

"I'm not going make excuses for Lamar. I will just tell you what my eyes tell me. He ain't right, something is wrong physically with him." The crew break down what is wrong with Lamar Jackson and the Baltimore Ravens.

The Arena: Gridiron

73,136 Aufrufe • vor 9 Monaten

Glad to be back with the clan for the holidays. Going to practice n hour a day on Rapkids Half term breaks WPM targets Nnenna (8) - 30 (currently 14) Kaego (10) - 60 (currently 45) Obinna (12) - 50 (currently 30) Benchmarks Typical typing speeds by age (rough ranges) AgeAverage WPM 6–75–15 WPM 8–910–25 WPM 1020–35 WPM 11–1230–45 WPM So if an under-10 child is typing 60 WPM: •That is exceptionally fast •Well above middle-school average •Likely comparable to or faster than many adults •Potentially top 1–5% for that age group, depending on accuracy The key question: accuracy If it’s: •60 WPM at 95–98% accuracy → that’s genuinely elite for under 10. •60 WPM at 85–90% accuracy → still very impressive, but developing control matters. ⸻ This level of speed suggests: •Strong pattern recognition •Good motor coordination •Solid working memory •High repetition discipline That’s a great foundation for: •Coding •Writing •Competitive academics •Self-directed digital learning This will be alongside reading, swimming, math and other exciting STEM related activities.
2:18

Glad to be back with the clan for the holidays. Going to practice n hour a day on Rapkids Half term breaks WPM targets Nnenna (8) - 30 (currently 14) Kaego (10) - 60 (currently 45) Obinna (12) - 50 (currently 30) Benchmarks Typical typing speeds by age (rough ranges) AgeAverage WPM 6–75–15 WPM 8–910–25 WPM 1020–35 WPM 11–1230–45 WPM So if an under-10 child is typing 60 WPM: •That is exceptionally fast •Well above middle-school average •Likely comparable to or faster than many adults •Potentially top 1–5% for that age group, depending on accuracy The key question: accuracy If it’s: •60 WPM at 95–98% accuracy → that’s genuinely elite for under 10. •60 WPM at 85–90% accuracy → still very impressive, but developing control matters. ⸻ This level of speed suggests: •Strong pattern recognition •Good motor coordination •Solid working memory •High repetition discipline That’s a great foundation for: •Coding •Writing •Competitive academics •Self-directed digital learning This will be alongside reading, swimming, math and other exciting STEM related activities.

Mazi Chukwuma Jason Njoku

20,417 Aufrufe • vor 6 Monaten

TestSprite 3.0 is live. A fleet of parallel AI agents that use your app like real users — in minutes. This is the release we've been building all year. The numbers tell the story of our completely overhauled engine: - Accuracy jumped by nearly 40% on the hardest, most complex projects. - Coverage increased significantly across the board for every E2E run. - Reliability is locked in—stable and consistent across multiple runs. We rebuilt our entire engine around these performance gains so you can ship fast and ship confident.
4:37

TestSprite 3.0 is live. A fleet of parallel AI agents that use your app like real users — in minutes. This is the release we've been building all year. The numbers tell the story of our completely overhauled engine: - Accuracy jumped by nearly 40% on the hardest, most complex projects. - Coverage increased significantly across the board for every E2E run. - Reliability is locked in—stable and consistent across multiple runs. We rebuilt our entire engine around these performance gains so you can ship fast and ship confident.

TestSprite

814,416 Aufrufe • vor 3 Monaten