正在加载视频...

视频加载失败

返回首页

🚨 Kimi K2.7-Code is actually insane >#1 on Program Bench >#1 on MLS-Bench Lite (multi-step ML research) >Refreshing to see honest benchmarks instead of cherry-picked After claude fable debacle i want OSS to win FR to save us from dystopian end

chetaslua's profile picture

Chetaslua

27,131 subscribers

37,602 次观看 • 23 天前 •via X (Twitter)

新闻政治科学技术
LIVE

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

running Claude Code w/ local models on my own GPUs at home > vLLM serving GLM-4.5 Air > on 4x RTX 3090s > nvtop showing live GPU load > Claude Code generating code + docs > end-to-end on my AI cluster this is what local AI actually looks like Buy a GPU
1:57

running Claude Code w/ local models on my own GPUs at home > vLLM serving GLM-4.5 Air > on 4x RTX 3090s > nvtop showing live GPU load > Claude Code generating code + docs > end-to-end on my AI cluster this is what local AI actually looks like Buy a GPU

Ahmad

262,090 次观看 • 5 个月前

Kimi K2.6 is godly in terms of webdev and still SOTA chinese model 😼 > best in deep SWE bench even after launches of multiple models from different chinese labs Look at the watery feel one shotted it < using custom harness - 4 kimi in parallel just like grok >
0:34

Kimi K2.6 is godly in terms of webdev and still SOTA chinese model 😼 > best in deep SWE bench even after launches of multiple models from different chinese labs Look at the watery feel one shotted it < using custom harness - 4 kimi in parallel just like grok >

Chetaslua

116,105 次观看 • 28 天前

Want to vibe code games for iOS easily? Steal this workflow. > Love2D engine > 2 agent skills > Write once; works everywhere (mac + simulator + device) > No need to open Xcode I used Claude Code Kimi K2.5, but works with Opus 4.5 / GPT 5.2, etc. FULL step-by-step video 👇
22:46

Want to vibe code games for iOS easily? Steal this workflow. > Love2D engine > 2 agent skills > Write once; works everywhere (mac + simulator + device) > No need to open Xcode I used Claude Code Kimi K2.5, but works with Opus 4.5 / GPT 5.2, etc. FULL step-by-step video 👇

Chong-U

16,929 次观看 • 5 个月前

INCREDIBLE SPEED running Claude Code w/ local models on my own GPUs at home > SGLang serving MiniMax-M2.1 > on 8x RTX 3090s > nvtop showing live GPU load > Claude Code generating code + docs > end-2-end on my AI cluster MiniMax-M2.1 is my favorite model to run locally nowadays
3:28

INCREDIBLE SPEED running Claude Code w/ local models on my own GPUs at home > SGLang serving MiniMax-M2.1 > on 8x RTX 3090s > nvtop showing live GPU load > Claude Code generating code + docs > end-2-end on my AI cluster MiniMax-M2.1 is my favorite model to run locally nowadays

Ahmad

592,866 次观看 • 5 个月前

> Send code from Claude > Explore on the canvas > Prototype with AI > Work through feedback > Roundtrip back to code All in Figma
0:29

> Send code from Claude > Explore on the canvas > Prototype with AI > Work through feedback > Roundtrip back to code All in Figma

Figma

356,501 次观看 • 4 个月前

🚨 Kimi Cooked So Hard with this release This is one Shotted by Kimi k2.7 fast , math guys try kimi i think its better in math too now Fable was able to do this but kimi only took less than a min lol , i had early access to it
0:33

🚨 Kimi Cooked So Hard with this release This is one Shotted by Kimi k2.7 fast , math guys try kimi i think its better in math too now Fable was able to do this but kimi only took less than a min lol , i had early access to it

Chetaslua

55,498 次观看 • 20 天前

Hermes Agent can use Autobrowse to make better browser skills. In this HN example, 2 iterations take us from: 102 seconds -> 35 23 turns -> 8 $1.46 -> $0.28 Instead of clicking step by step it decides to eval JS directly on the page and save that workflow to a skill.
0:24

Hermes Agent can use Autobrowse to make better browser skills. In this HN example, 2 iterations take us from: 102 seconds -> 35 23 turns -> 8 $1.46 -> $0.28 Instead of clicking step by step it decides to eval JS directly on the page and save that workflow to a skill.

Kyle Jeong

318,317 次观看 • 1 个月前

Black hole visualisation by MiniMax M2.5 Holy Shit i have never seen this output 😮 >SOTA performance better than Opus4.6 at coding SWE-Bench Verified 80.2%, BrowseComp 76.3% >$1 per hour with 100 tps i.e 3 times the speed of Opus4.6 > Only 10B active parameter
1:05

Black hole visualisation by MiniMax M2.5 Holy Shit i have never seen this output 😮 >SOTA performance better than Opus4.6 at coding SWE-Bench Verified 80.2%, BrowseComp 76.3% >$1 per hour with 100 tps i.e 3 times the speed of Opus4.6 > Only 10B active parameter

Chetaslua

17,725 次观看 • 4 个月前

Introducing OB-1: the new #1 coding agent on Terminal Bench. After a year of R&D, our agent now outperforms Codex and Claude Code. Early access is rolling out to waitlist users now.
0:23

Introducing OB-1: the new #1 coding agent on Terminal Bench. After a year of R&D, our agent now outperforms Codex and Claude Code. Early access is rolling out to waitlist users now.

OpenBlock

75,892 次观看 • 10 个月前

I was scheduled to do a talk on the best way to use Fable 5 today. Here's how that went: > I got rugpulled by the US government (0:00) > what I'm using Fable for (1:38) > looping, and why few can afford it (4:14) > my affordable looping strategy (6:30) > LLM canaries (17:29)
19:46

I was scheduled to do a talk on the best way to use Fable 5 today. Here's how that went: > I got rugpulled by the US government (0:00) > what I'm using Fable for (1:38) > looping, and why few can afford it (4:14) > my affordable looping strategy (6:30) > LLM canaries (17:29)

Rob Hallam

32,211 次观看 • 23 天前

KIMI K2.5 JUST MOGGED EVERYONE. > 1T PARAMETERS. > NATIVE MULTI MODAL. > BEATS CLAUDE 4.5 OPUS. > OPEN SOURCE.
0:29

KIMI K2.5 JUST MOGGED EVERYONE. > 1T PARAMETERS. > NATIVE MULTI MODAL. > BEATS CLAUDE 4.5 OPUS. > OPEN SOURCE.

sui ☄️

394,682 次观看 • 5 个月前

🚨 Gemini 3.0 Flash > one shotted this trip on globe planner > super fast and to the point > i think this will be beast in gemini cli for faster and to the point coding
0:21

🚨 Gemini 3.0 Flash > one shotted this trip on globe planner > super fast and to the point > i think this will be beast in gemini cli for faster and to the point coding

Chetaslua

36,421 次观看 • 9 个月前

End-to-end app build, episode 1 From idea -> logic -> data infra
49:44

End-to-end app build, episode 1 From idea -> logic -> data infra

matt palmer

49,118 次观看 • 7 个月前

Claude code + Skills >>>> Claude code We created a skill that, - Makes Claude Code read your past conversations - Understands what code issues you struggled at - Generates a detailed report on Slack Works with Rube Here's the link to the Skill:
0:51

Claude code + Skills >>>> Claude code We created a skill that, - Makes Claude Code read your past conversations - Understands what code issues you struggled at - Generates a detailed report on Slack Works with Rube Here's the link to the Skill:

Karan Vaidya

39,199 次观看 • 7 个月前

> be you > work in figma sites but want the power of make > see this tweet and realize code now belongs; make a mess, rev, refine > start to use code layers > actually finish your site
3:05

> be you > work in figma sites but want the power of make > see this tweet and realize code now belongs; make a mess, rev, refine > start to use code layers > actually finish your site

Niko

51,551 次观看 • 1 年前

What I was actually trying to do: >Agony: Deal 1% Max HP damage on enemy turn >Inflicting Ailments inflicts 4 Agony >Makoto can inflict 5 Ailments at once >Inflicting Agony has 50% to inflict it again >Stacks 100 times, win
0:30

What I was actually trying to do: >Agony: Deal 1% Max HP damage on enemy turn >Inflicting Ailments inflicts 4 Agony >Makoto can inflict 5 Ailments at once >Inflicting Agony has 50% to inflict it again >Stacks 100 times, win

MeovvCAT

57,873 次观看 • 6 个月前

The Rockets coming back from a 3-1 deficit to beat the Phoenix Suns in the WCSF and going on to win the 1995 NBA Finals>>>
0:39

The Rockets coming back from a 3-1 deficit to beat the Phoenix Suns in the WCSF and going on to win the 1995 NBA Finals>>>

Bradeaux

81,430 次观看 • 4 个月前

🚨On Saturday, I travelled to Dover to see if the rumours of an invasion is true. After 4 hours… i can confirm the UK is FULLY under invasion. ‼️FULL VIDEO LINK >>
1:27

🚨On Saturday, I travelled to Dover to see if the rumours of an invasion is true. After 4 hours… i can confirm the UK is FULLY under invasion. ‼️FULL VIDEO LINK >>

BASEDANDBOUGIE

12,150 次观看 • 2 个月前

Actually surprised more gymnasts don't glide 1/2 after their Pak saltos. The top gymnasts tend to Shap or Shap 1/2 back up but a glide 1/2 would be a net gain for many who end up casting 1/2 to shoot to HB. 0.10 for amplitude >>> angle, amplitude and alignment on cast 1/2
0:24

Actually surprised more gymnasts don't glide 1/2 after their Pak saltos. The top gymnasts tend to Shap or Shap 1/2 back up but a glide 1/2 would be a net gain for many who end up casting 1/2 to shoot to HB. 0.10 for amplitude >>> angle, amplitude and alignment on cast 1/2

Pamchenkova

18,269 次观看 • 1 年前