Video yükleniyor...

Video Yüklenemedi

Ana Sayfaya Dön

a new AI eval benchmark

ainunnajib's profile picture

Ainun Najib

163,095 subscribers

16,825 görüntüleme • 1 yıl önce •via X (Twitter)

Bilim & Teknoloji
LIVE

Anya Rossi• Live Now

Private livecam show

8 Yorum

Rendy B. Junior profil fotoğrafı
Rendy B. Junior1 yıl önce

Feel yang didapet: deepseek kurang deep di sosmed.

Enchroma 🦣 profil fotoğrafı
Enchroma 🦣1 yıl önce

coba nyalain dulu fitur searchnya pak

Alpha Amirrachman profil fotoğrafı
Alpha Amirrachman1 yıl önce

common name banget 😇😇

Ainun Najib profil fotoğrafı
Ainun Najib1 yıl önce

👀

Coral AI News profil fotoğrafı
Coral AI News1 yıl önce

Coral AI is the most powerful AI for documents. See the difference yourself:

Ifdhal Zaky profil fotoğrafı
Ifdhal Zaky1 yıl önce

Proses berpikirnya diliatin ya... Jadi tau gmn caranya dia bisa ngeluarin jawaban di paragraf terakhir

asdevv profil fotoğrafı
asdevv1 yıl önce

Woww, ngeliatin cara nya dia reasoning keren banget sihh

(R.M.Pj.) Aji Andaru H. profil fotoğrafı
(R.M.Pj.) Aji Andaru H.1 yıl önce

Sering banget server busy sekarang.

Benzer Videolar

Introducing the Human Creativity Benchmark. The first eval that scores AI models the way creative experts do.
0:40

Introducing the Human Creativity Benchmark. The first eval that scores AI models the way creative experts do.

ben

362,682 görüntüleme • 1 ay önce

📣 Introducing SWE-PolyBench: A new open-source multilingual benchmark for evaluating #AI coding agents SWE-PolyBench is the first benchmark to evaluate AI coding agents' ability to understand complex codebases, helping advance AI performance in the real world. Learn more. 👉
1:40

📣 Introducing SWE-PolyBench: A new open-source multilingual benchmark for evaluating #AI coding agents SWE-PolyBench is the first benchmark to evaluate AI coding agents' ability to understand complex codebases, helping advance AI performance in the real world. Learn more. 👉

Amazon Web Services

10,866 görüntüleme • 1 yıl önce

We just crossed $5M ARR fully bootstrapped Introducing CrowdReply 2.0 The new benchmark of ranking in AI Answers
1:30

We just crossed $5M ARR fully bootstrapped Introducing CrowdReply 2.0 The new benchmark of ranking in AI Answers

CrowdReply

1,315,306 görüntüleme • 3 ay önce

New No Priors w/@ericsimons40 from StackBlitz on AI-generated websites *0 to $20M in ARR in 2 months with 🚀 *the community's coolest use cases *how to eval ai codegen *balancing an Ironman, a newborn, and a product launch
0:32

New No Priors w/@ericsimons40 from StackBlitz on AI-generated websites *0 to $20M in ARR in 2 months with 🚀 *the community's coolest use cases *how to eval ai codegen *balancing an Ironman, a newborn, and a product launch

sarah guo // conviction

41,738 görüntüleme • 1 yıl önce

CLUTCH is setting a new benchmark in car customization
0:44

CLUTCH is setting a new benchmark in car customization

Idle Sloth

794,411 görüntüleme • 18 gün önce

📢Introducing Kaggle Game Arena: a new, open benchmark platform where top AI models compete in complex, strategic games in streamed match-ups. We're charting new frontiers for trustworthy AI evaluation and it begins with chess — a classic proving ground for system intelligence.
0:29

📢Introducing Kaggle Game Arena: a new, open benchmark platform where top AI models compete in complex, strategic games in streamed match-ups. We're charting new frontiers for trustworthy AI evaluation and it begins with chess — a classic proving ground for system intelligence.

Kaggle

113,975 görüntüleme • 10 ay önce

NEW: Brand Radar [beta] 🎯 Optimize for AI search: 👉 Track brand visibility in AI-generated mentions 👉 Benchmark AI share of voice (SOV) against competitors 👉 Win new market share from LLMs early on Try it now!
0:57

NEW: Brand Radar [beta] 🎯 Optimize for AI search: 👉 Track brand visibility in AI-generated mentions 👉 Benchmark AI share of voice (SOV) against competitors 👉 Win new market share from LLMs early on Try it now!

Ahrefs

528,433 görüntüleme • 1 yıl önce

Are AI benchmarks doomed? Greg Burnham and Tom Adamczewski join Anson Ho to push back on benchmark pessimism and dig into what the next generation of AI benchmarks could look like. (0:00:00) - Preview (0:00:36) - Intro: Are AI benchmarks doomed? (0:03:13) - The costs and benefits of benchmark development (0:11:48) - MirrorCode and scalable benchmarks (0:20:57) - AI speed-up in benchmark development (0:23:28) - The benchmark-reality gap (0:38:26) - Can an AGI benchmark exist? (0:43:18) - Beyond automated scoring (1:00:45) - How AI changes benchmark building in practice
1:05:24

Are AI benchmarks doomed? Greg Burnham and Tom Adamczewski join Anson Ho to push back on benchmark pessimism and dig into what the next generation of AI benchmarks could look like. (0:00:00) - Preview (0:00:36) - Intro: Are AI benchmarks doomed? (0:03:13) - The costs and benefits of benchmark development (0:11:48) - MirrorCode and scalable benchmarks (0:20:57) - AI speed-up in benchmark development (0:23:28) - The benchmark-reality gap (0:38:26) - Can an AGI benchmark exist? (0:43:18) - Beyond automated scoring (1:00:45) - How AI changes benchmark building in practice

Epoch AI

22,037 görüntüleme • 1 ay önce

This is unironically an excellent benchmark for AI voice agents
1:13

This is unironically an excellent benchmark for AI voice agents

Justine Moore

266,416 görüntüleme • 6 ay önce

🔥 Pokémon Red is becoming a go-to benchmark for testing advanced AIs such as Gemini. But is Pokémon Red really a good eval? We study this problem and identify three issues: 1️⃣ Navigation tasks are too hard. 2️⃣ Combat control is too simple. 3️⃣ Raising a strong Pokémon team is slow and expensive as an eval. We find most of the problems are not fundamental to games themselves, but how they have been used. We believe game-as-an-eval remains a compelling and underutilized evaluation strategy. We introduce Lmgame Bench to standardize game-as-an-eval. More details and findings in our blogpost:
0:41

🔥 Pokémon Red is becoming a go-to benchmark for testing advanced AIs such as Gemini. But is Pokémon Red really a good eval? We study this problem and identify three issues: 1️⃣ Navigation tasks are too hard. 2️⃣ Combat control is too simple. 3️⃣ Raising a strong Pokémon team is slow and expensive as an eval. We find most of the problems are not fundamental to games themselves, but how they have been used. We believe game-as-an-eval remains a compelling and underutilized evaluation strategy. We introduce Lmgame Bench to standardize game-as-an-eval. More details and findings in our blogpost:

Hao AI Lab

69,004 görüntüleme • 11 ay önce

📚 Exciting new updates for my Wikipedia-racing website (+ leaderboard!) created with Google AI Studio, @Antigravity, and Firebase. Test it out, post your results, and generate new races! Anyone who creates + completes a challenge will be recognized in the model eval dataset:
0:24

📚 Exciting new updates for my Wikipedia-racing website (+ leaderboard!) created with Google AI Studio, @Antigravity, and Firebase. Test it out, post your results, and generate new races! Anyone who creates + completes a challenge will be recognized in the model eval dataset:

👩‍💻 Paige Bailey

14,364 görüntüleme • 4 ay önce

An interesting work on Physical AI: PhysX-Omni. First unified sim-ready generation framework for rigid, deformable, and articulated objects, with a diverse dataset and new benchmark. 🌐 💻 📦
5:03

An interesting work on Physical AI: PhysX-Omni. First unified sim-ready generation framework for rigid, deformable, and articulated objects, with a diverse dataset and new benchmark. 🌐 💻 📦

Ziqi Huang

26,904 görüntüleme • 27 gün önce

10× AI performance is the new benchmark Dr. Lisa Su introduces AMD Helios and MI455, delivering up to 10x more AI performance to power stronger models, smarter agents and next-gen applications.
0:45

10× AI performance is the new benchmark Dr. Lisa Su introduces AMD Helios and MI455, delivering up to 10x more AI performance to power stronger models, smarter agents and next-gen applications.

CES

10,698 görüntüleme • 5 ay önce

New benchmark alert! Courtesy of JoanMir36 🔥 #AmericasGP 🇺🇸
0:24

New benchmark alert! Courtesy of JoanMir36 🔥 #AmericasGP 🇺🇸

MotoGP™🏁

74,812 görüntüleme • 1 yıl önce

Director Anil Ravipudi strikes again with a brilliantly strategic promotional masterstroke 🔥 The first-ever AI-powered Telugu promotional video, featuring #MegastarChiranjeevi, sets a new benchmark in cinema marketing. #ManaShankaraVaraPrasadGaru hitting screens January 12, 2026.💥
1:06

Director Anil Ravipudi strikes again with a brilliantly strategic promotional masterstroke 🔥 The first-ever AI-powered Telugu promotional video, featuring #MegastarChiranjeevi, sets a new benchmark in cinema marketing. #ManaShankaraVaraPrasadGaru hitting screens January 12, 2026.💥

PaniPuri

23,511 görüntüleme • 6 ay önce

Oman Airports sets a new benchmark by deploying Huawei's Xinghe AI 10 Gbps Campus Network Solution to build the world's first Wi-Fi 7 smart airport campus. What unique benefits? High-speed wireless coverage anywhere, AI-powered O&M, a redefined passenger experience, and more.
3:01

Oman Airports sets a new benchmark by deploying Huawei's Xinghe AI 10 Gbps Campus Network Solution to build the world's first Wi-Fi 7 smart airport campus. What unique benefits? High-speed wireless coverage anywhere, AI-powered O&M, a redefined passenger experience, and more.

Huawei Network

16,932 görüntüleme • 2 ay önce

New name. Same stage for the unforgettable. Benchmark International Arena.
2:07

New name. Same stage for the unforgettable. Benchmark International Arena.

Benchmark International Arena

222,087 görüntüleme • 10 ay önce

The GEN3 Evo has changed the game 👀 A new benchmark for speed, power and innovation⚡️
1:04

The GEN3 Evo has changed the game 👀 A new benchmark for speed, power and innovation⚡️

Formula E

19,149 görüntüleme • 1 yıl önce

Boop explains why he thinks Epic is testing a new 30 ping minimum comp feature: - Former Epic employee confirms having worked on it - They didn't disclose what they were testing this eval cup - Everyone who is playing the Eval is 30 Ping - NA Only
0:32

Boop explains why he thinks Epic is testing a new 30 ping minimum comp feature: - Former Epic employee confirms having worked on it - They didn't disclose what they were testing this eval cup - Everyone who is playing the Eval is 30 Ping - NA Only

XSET Twizz

165,582 görüntüleme • 1 ay önce