Video wird geladen...

Video konnte nicht geladen werden

Zur Startseite

Opus 4.6 and Codex 5.3 still make stupid decisions

atmoio's profile picture

Mo

76,885 subscribers

65,563 Aufrufe • vor 7 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

It’s time for another Counter-Strike benchmark: GPT 5.3 Codex and Claude 4.6 Opus:
0:39

It’s time for another Counter-Strike benchmark: GPT 5.3 Codex and Claude 4.6 Opus:

Instant

18,962 Aufrufe • vor 7 Monaten

Opus 4.6 and Codex 5.3 just launched, so I did a hexagon test on both of them Opus 4.6 - 1M context - great for research + enterprise work - agent teams + long-range reasoning - weaker on raw code benchmarks Codex 5.3 - wins coding benchmarks - faster + mid-task steering - smaller context window TLDR: Opus = depth + orchestration Codex = speed + code
0:20

Opus 4.6 and Codex 5.3 just launched, so I did a hexagon test on both of them Opus 4.6 - 1M context - great for research + enterprise work - agent teams + long-range reasoning - weaker on raw code benchmarks Codex 5.3 - wins coding benchmarks - faster + mid-task steering - smaller context window TLDR: Opus = depth + orchestration Codex = speed + code

Abhinav

447,873 Aufrufe • vor 7 Monaten

GPT-5.3 Codex is actually pretty insane with Three.js This Minecraft clone works smoothly and it didn't take too long to make I also tried Opus 4.6, but for some reason it got stuck
0:35

GPT-5.3 Codex is actually pretty insane with Three.js This Minecraft clone works smoothly and it didn't take too long to make I also tried Opus 4.6, but for some reason it got stuck

Angel 🌼

1,127,915 Aufrufe • vor 7 Monaten

Claude Opus 4.6 vs GPT-5.3 Codex aren't just different models. They're different engineers. Opus 4.6: → 1M token context window → Reads the whole codebase before deciding → Asks "should we do this?" → Failure mode: overanalyzes, hesitates GPT-5.3 Codex: → 200K tokens, built for speed → Decides fast, acts, iterates → Asks "how fast can I ship this?" → Failure mode: locks in a flawed assumption early Think: Opus = your architect Codex = your operator Pick the one that matches the task.
3:53

Claude Opus 4.6 vs GPT-5.3 Codex aren't just different models. They're different engineers. Opus 4.6: → 1M token context window → Reads the whole codebase before deciding → Asks "should we do this?" → Failure mode: overanalyzes, hesitates GPT-5.3 Codex: → 200K tokens, built for speed → Decides fast, acts, iterates → Asks "how fast can I ship this?" → Failure mode: locks in a flawed assumption early Think: Opus = your architect Codex = your operator Pick the one that matches the task.

The Startup Ideas Podcast (SIP) 🧃

59,604 Aufrufe • vor 7 Monaten

What's better than Claude Opus 4.6 or GPT 5.3 Codex? Running them all, in parallel, with a single GitHub Copilot subscription. And all of this shipped just this week.
0:29

What's better than Claude Opus 4.6 or GPT 5.3 Codex? Running them all, in parallel, with a single GitHub Copilot subscription. And all of this shipped just this week.

Martin Woodward

65,575 Aufrufe • vor 7 Monaten

How it feels to give a task to Opus 4.6 and Codex 5.3 in parallel to see which one can better blast through 3 months of human work in 5 mins
0:24

How it feels to give a task to Opus 4.6 and Codex 5.3 in parallel to see which one can better blast through 3 months of human work in 5 mins

Beff (e/acc)

28,349 Aufrufe • vor 7 Monaten

Claude Sonnet 4.6 vs GPT 5.3 Codex Same Prompt in Cursor (Neutral Harness) - Default Settings! GPT 5.3 Codex took - 2 mins Claude Sonnet 4.6 - 7 mins Cheaper than Sonnet 4.6! Faster than Sonnet 4.6! But I'm not sure if it's more craftier than Sonnet 4.6 because Sonnet's got a taste! Claude Sonnet 4.6 had a better result (aesthetically) and also more solid techstack - GPT 5.3 codes meanwhile just got the job done!
0:36

Claude Sonnet 4.6 vs GPT 5.3 Codex Same Prompt in Cursor (Neutral Harness) - Default Settings! GPT 5.3 Codex took - 2 mins Claude Sonnet 4.6 - 7 mins Cheaper than Sonnet 4.6! Faster than Sonnet 4.6! But I'm not sure if it's more craftier than Sonnet 4.6 because Sonnet's got a taste! Claude Sonnet 4.6 had a better result (aesthetically) and also more solid techstack - GPT 5.3 codes meanwhile just got the job done!

1LittleCoder💻

142,933 Aufrufe • vor 7 Monaten

gpt 5.3 (left) vs opus 4.6 (right) - which one is better? full prompt below
0:28

gpt 5.3 (left) vs opus 4.6 (right) - which one is better? full prompt below

Sughu

11,338 Aufrufe • vor 7 Monaten

A behind the scenes look at the level editor: → 1. Set player spawn → 2. Set NPC locations → 3. Adjust navmesh Allows for very quickly integrating new assets into the game. Everything vibe coded... → GPT 5.3 Codex → Opus 4.6 (always use both) You can just make things.
0:33

A behind the scenes look at the level editor: → 1. Set player spawn → 2. Set NPC locations → 3. Adjust navmesh Allows for very quickly integrating new assets into the game. Everything vibe coded... → GPT 5.3 Codex → Opus 4.6 (always use both) You can just make things.

Chong-U

16,579 Aufrufe • vor 7 Monaten

Stop saying that Opus 4.6 is better than Opus 4.8. I just tested Claude Opus 4.8 (Right) and Claude Opus 4.6 (Left) on the same exact prompt. Claude Opus 4.8 completed it in less than 2 minutes. Claude Opus 4.6 "Garnished" for over 7 minutes. Stop using Opus 4.6.
0:23

Stop saying that Opus 4.6 is better than Opus 4.8. I just tested Claude Opus 4.8 (Right) and Claude Opus 4.6 (Left) on the same exact prompt. Claude Opus 4.8 completed it in less than 2 minutes. Claude Opus 4.6 "Garnished" for over 7 minutes. Stop using Opus 4.6.

BridgeMind

53,391 Aufrufe • vor 3 Monaten

Cursor— Codex-5.2 Extra-High vs Opus 4.6 Max’ı Google Earth Mini task’ı ile kıyasladım🔥 Hata: - Opus hatasız tek seferde tamamladı 🎉 Codex 2 kez hatalı yazdı. 👎🏻 Hız: - Codex 10 dakikada yazdı 🎉 Opus 19 dakikada 👎🏻 Agentic Coding; - Opus hiçbir müdahale ve plan olmadan fazlara bölüp yazdı 🎉 Codex direk search ve thinking yaparak yazdı 👎🏻👎🏻
0:47

Cursor— Codex-5.2 Extra-High vs Opus 4.6 Max’ı Google Earth Mini task’ı ile kıyasladım🔥 Hata: - Opus hatasız tek seferde tamamladı 🎉 Codex 2 kez hatalı yazdı. 👎🏻 Hız: - Codex 10 dakikada yazdı 🎉 Opus 19 dakikada 👎🏻 Agentic Coding; - Opus hiçbir müdahale ve plan olmadan fazlara bölüp yazdı 🎉 Codex direk search ve thinking yaparak yazdı 👎🏻👎🏻

Alican Kiraz

49,381 Aufrufe • vor 7 Monaten

GLM 5.3 Max vs Fable 5 vs Qwen 3.8 Max vs Grok 4.6 GLM 5.3 is a massive jump over 5.2. Still not beating Fable 5 for me, but it’s way closer now. And vs Grok 4.6? I’d take GLM 5.3 pretty easily on this test.
0:33

GLM 5.3 Max vs Fable 5 vs Qwen 3.8 Max vs Grok 4.6 GLM 5.3 is a massive jump over 5.2. Still not beating Fable 5 for me, but it’s way closer now. And vs Grok 4.6? I’d take GLM 5.3 pretty easily on this test.

OmedTheVibeCoder

16,648 Aufrufe • vor 1 Monat

Codex 5.3 EXTRA HIGH ve Claude Opus 4.6'yı ringe çıkardım. Sonuç gerçekten çok acayip. Genelde "Extra High" ayarı açınca modellerin kaplumbağaya dönmesini beklersiniz değil mi? Ben de öyle sanıyordum. İki tarafa da birebir aynı promptu verdim, tek bir virgül bile değiştirmedim. Claude'u yeni gelen "agent team" özelliğiyle sahaya sürdüm, Codex'i ise kendi app'i içinde agent ile başlattım. Kenara çekilip kahvemi aldım, izliyorum. Claude paşa paşa çalıştı, işini 22 dakikada bitirdi. Ama Codex? Codex resmen şov yaptı. Extra High modunda olmasına rağmen 14 dakikada görevi tamamladı. Arada 8 dakika fark var, boru değil. Hız konusunda bu kadar fark olacağını hiç beklemiyordum. Video aşağıda, iki tarafın da performansını karşılaştırın. Sizin düşünceleriniz ne? Sol Video Opus 4.6, Sağ Video Codex 5.3 Extra High
0:46

Codex 5.3 EXTRA HIGH ve Claude Opus 4.6'yı ringe çıkardım. Sonuç gerçekten çok acayip. Genelde "Extra High" ayarı açınca modellerin kaplumbağaya dönmesini beklersiniz değil mi? Ben de öyle sanıyordum. İki tarafa da birebir aynı promptu verdim, tek bir virgül bile değiştirmedim. Claude'u yeni gelen "agent team" özelliğiyle sahaya sürdüm, Codex'i ise kendi app'i içinde agent ile başlattım. Kenara çekilip kahvemi aldım, izliyorum. Claude paşa paşa çalıştı, işini 22 dakikada bitirdi. Ama Codex? Codex resmen şov yaptı. Extra High modunda olmasına rağmen 14 dakikada görevi tamamladı. Arada 8 dakika fark var, boru değil. Hız konusunda bu kadar fark olacağını hiç beklemiyordum. Video aşağıda, iki tarafın da performansını karşılaştırın. Sizin düşünceleriniz ne? Sol Video Opus 4.6, Sağ Video Codex 5.3 Extra High

Baha Gökce

18,140 Aufrufe • vor 7 Monaten

It started as ThreeJS 3d character demo... Now it's become a FULLY vibe coded point & click 2.5 adventure game engine! → 1. NBP for Character Art → 2. NBP + Seedance for Bg → 3. Meshy for Rigged Characters → 4. Codex 5.3 + Opus 4.6 for game → 5. CapacitorJs for mobile 👇
0:30

It started as ThreeJS 3d character demo... Now it's become a FULLY vibe coded point & click 2.5 adventure game engine! → 1. NBP for Character Art → 2. NBP + Seedance for Bg → 3. Meshy for Rigged Characters → 4. Codex 5.3 + Opus 4.6 for game → 5. CapacitorJs for mobile 👇

Chong-U

222,030 Aufrufe • vor 7 Monaten

Opus 4.6 is here and it's a beast.
14:20

Opus 4.6 is here and it's a beast.

Matthew Berman

16,124 Aufrufe • vor 7 Monaten

a user had opus 4.6 thinking for 1.5 hours on a sunday non-peak hour first increase token usage, then nerf opus 4.6, and now make it buggy with nonstop feature releases what’s going on with claude code?
0:23

a user had opus 4.6 thinking for 1.5 hours on a sunday non-peak hour first increase token usage, then nerf opus 4.6, and now make it buggy with nonstop feature releases what’s going on with claude code?

aditya🇦🇷

118,419 Aufrufe • vor 5 Monaten

Another one Gemini 3.1 Pro (High) and Claude Opus 4.6 in Antigravity plan - Opus 4.6, code - 3.1 Pro It took < 1 hour to vibecode
0:54

Another one Gemini 3.1 Pro (High) and Claude Opus 4.6 in Antigravity plan - Opus 4.6, code - 3.1 Pro It took < 1 hour to vibecode

Harshith

46,850 Aufrufe • vor 5 Monaten

Clone a functional Billion $$ SAAS Part 2 - Figma. Now that Claude Opus 4.6 and Codex 5.3 are available, I decided to try this again. The result - CanvasKit Tools used - Windsurf (retired) Cascade & OpenAI Codex CLI First agent run - 30 minutes Total time spent w/ extra prompting - 3 hours I think this could be a new metric for model evaluations - TTBS (time to billion $$ SAAS 😂) Code and details below:
0:34

Clone a functional Billion $$ SAAS Part 2 - Figma. Now that Claude Opus 4.6 and Codex 5.3 are available, I decided to try this again. The result - CanvasKit Tools used - Windsurf (retired) Cascade & OpenAI Codex CLI First agent run - 30 minutes Total time spent w/ extra prompting - 3 hours I think this could be a new metric for model evaluations - TTBS (time to billion $$ SAAS 😂) Code and details below:

nader dabit

30,271 Aufrufe • vor 7 Monaten

Claude opus 4.6 logró desarrollar un compilador de C… Claude opus 4.6 logró desarrollar un... compilador de C Claude opus 4.6 logró desarrollar un... compilador de C… yo:
0:25

Claude opus 4.6 logró desarrollar un compilador de C… Claude opus 4.6 logró desarrollar un... compilador de C Claude opus 4.6 logró desarrollar un... compilador de C… yo:

Juan

43,598 Aufrufe • vor 7 Monaten

This is what you get when Gemini 3.1 Pro (High) and Claude Opus 4.6 work together in Antigravity plan by Opus 4.6, code by 3.1 Pro
1:09

This is what you get when Gemini 3.1 Pro (High) and Claude Opus 4.6 work together in Antigravity plan by Opus 4.6, code by 3.1 Pro

Harshith

72,450 Aufrufe • vor 5 Monaten