Loading video...

Video Failed to Load

Go Home

Kind of shocking how much better GPT-5-Codex is vs the regular 'Thinking' models in ChatGPT. My subjective rankings for the fruit machine test: 1. GPT-5-Codex-Medium 2. GPT-5-Thinking-Heavy 3. GPT-5-Pro 4. GPT-5-Codex-High 5. GPT-5-Codex-Low 6. GPT-5-Thinking-Standard 7. GPT-5-Thinking-Extended 8. GPT-5-Thinking-Light OpenAI Codex team have suggested 'Medium' should be the default,...

petergostev's profile picture

Peter Gostev

4,181 subscribers

101,848 views • 9 months ago •via X (Twitter)

Science & Technology
LIVE

Anya Rossi• Live Now

Private livecam show

0 Comments

No comments available

Comments from the original post will appear here

Related Videos

how it started (Greg Brockman's gpt-4 launch demo) how it's going (gpt-5-codex)
2:26

how it started (Greg Brockman's gpt-4 launch demo) how it's going (gpt-5-codex)

edwin

20,559 views • 9 months ago

GPT-5 Thinking
3:07

GPT-5 Thinking

Min Choi

434,934 views • 10 months ago

GPT 5.4 has been released... + 1M context window! Here's how to enable in Codex: → 1. ~/.codex/config.toml → 2. model = "gpt-5.4" → 3. model_context_window=1000000 → 4. model_auto_compact_token_limit=9000000 Run codex → 5. /statusline → 6. toggle context-window-size I didn't even realise Codex had a statusline tool!
0:20

GPT 5.4 has been released... + 1M context window! Here's how to enable in Codex: → 1. ~/.codex/config.toml → 2. model = "gpt-5.4" → 3. model_context_window=1000000 → 4. model_auto_compact_token_limit=9000000 Run codex → 5. /statusline → 6. toggle context-window-size I didn't even realise Codex had a statusline tool!

Chong-U

76,354 views • 3 months ago

factory cli now lets you choose a different model for plan mode and execute mode when you switch modes, the model changes too. my go-to right now: plan: gpt-5-high code: gpt-5-codex (auto)
0:21

factory cli now lets you choose a different model for plan mode and execute mode when you switch modes, the model changes too. my go-to right now: plan: gpt-5-high code: gpt-5-codex (auto)

Ian Nuttall

27,156 views • 8 months ago

GPT-5.4 (xhigh) in Codex worked for almost 5 minutes but it did collect some wood
0:30

GPT-5.4 (xhigh) in Codex worked for almost 5 minutes but it did collect some wood

Angel 🌼

205,715 views • 3 months ago

Warp now supports GPT 5.2 Codex 🙌 We worked closely with the OpenAI team to tune our harness for the Codex series. GPT 5.2 Codex builds upon the strengths of GPT 5.2, excelling at long-horizon tasks (think 15 min+) Try GPT 5.2 codex and tell us what you think
0:20

Warp now supports GPT 5.2 Codex 🙌 We worked closely with the OpenAI team to tune our harness for the Codex series. GPT 5.2 Codex builds upon the strengths of GPT 5.2, excelling at long-horizon tasks (think 15 min+) Try GPT 5.2 codex and tell us what you think

Warp

32,708 views • 5 months ago

One shot in codex with gpt-taste skill! GPT 5.4 medium works best :) skill:
0:22

One shot in codex with gpt-taste skill! GPT 5.4 medium works best :) skill:

Leon Lin

158,387 views • 2 months ago

The model is faster, the pelican isn't as good! GPT-5.3 Codex Spark on the left, GPT-5.3 Codex 5.3 on the right - both at medium quality settings
0:08

The model is faster, the pelican isn't as good! GPT-5.3 Codex Spark on the left, GPT-5.3 Codex 5.3 on the right - both at medium quality settings

Simon Willison

57,440 views • 4 months ago

I am really liking the new gpt-5-codex. this is its attempt at one shotting minecraft in three.js
0:29

I am really liking the new gpt-5-codex. this is its attempt at one shotting minecraft in three.js

JB

479,500 views • 9 months ago

🎬 One prompt → a full video GPT-5 + open models, stitched together with OpenAI Codex + HF MCP Server 🤯
0:49

🎬 One prompt → a full video GPT-5 + open models, stitched together with OpenAI Codex + HF MCP Server 🤯

Vaibhav (VB) Srivastav

47,870 views • 9 months ago

OpenAI’s new GPT-5 Codex is impressive at coding tasks. But, in a huge codebase, intelligence isn’t the main bottleneck—context is.
1:11

OpenAI’s new GPT-5 Codex is impressive at coding tasks. But, in a huge codebase, intelligence isn’t the main bottleneck—context is.

Augment Code

1,188,147 views • 9 months ago

Sam Altman says the leap from GPT-4 to GPT-5 will be as big as that of GPT-3 to 4 and the plan is to integrate the GPT and o series of models into one model that can do everything
0:57

Sam Altman says the leap from GPT-4 to GPT-5 will be as big as that of GPT-3 to 4 and the plan is to integrate the GPT and o series of models into one model that can do everything

Tsarathustra

224,102 views • 1 year ago

We’ve been working closely with the OpenAI team to integrate GPT-5 into Devin. Starting today, you can select a preview version of Devin that uses GPT-5 as part of our agent orchestration. GPT-5 eval results 👇
2:04

We’ve been working closely with the OpenAI team to integrate GPT-5 into Devin. Starting today, you can select a preview version of Devin that uses GPT-5 as part of our agent orchestration. GPT-5 eval results 👇

Cognition

100,251 views • 10 months ago

GPT-5.6 vs GPT-5.5 on my custom spaceship prompt. I gave both models the exact same custom prompt. This is also the same prompt I previously gave to Fable 5. For context, GPT-5.6 Pro worked for 87 minutes, while GPT-5.5 Extra High worked for 34 minutes and 42 seconds. As I’ve said before, based on great authority GPT-5.6 will be an incremental/soldi improvement over GPT-5.5, not a “Fable killer.” My rough expectation has been that it would trade blows with Fable 5 on some benchmarks, maybe win around half depending on the category, but not clearly surpass it overall. And again fable five will have bigger model smell, but this was expected. After testing this coding output, that view feels pretty accurate. GPT-5.6 is clearly better than GPT-5.5 in several visual areas. The lighting, shading, chairs, object details, and exterior of the spaceship looked noticeably stronger. The scene was also easier to test. I do want to give GPT-5.5 credit though. It built out the rooms much much better and the planets looked better than GPT-5.6’s. It was also interesting that both GPT-5.5 and GPT-5.6 produced better-looking planets than Fable 5 in this specific test. The downside with GPT-5.5 was stability. The game was much glitchier and harder to test compared to GPT-5.6. But when it comes to the core of the demo, which is the spaceship itself, Fable 5 still beat both models pretty comfortably. GPT-5.6 is impressive, but from this test, it looks exactly like what I expected which was a meaningful incremental improvement over GPT-5.5, at least for indie game demos, but not something that replaces Fable 5. In collaboration with Chetaslua
0:42

GPT-5.6 vs GPT-5.5 on my custom spaceship prompt. I gave both models the exact same custom prompt. This is also the same prompt I previously gave to Fable 5. For context, GPT-5.6 Pro worked for 87 minutes, while GPT-5.5 Extra High worked for 34 minutes and 42 seconds. As I’ve said before, based on great authority GPT-5.6 will be an incremental/soldi improvement over GPT-5.5, not a “Fable killer.” My rough expectation has been that it would trade blows with Fable 5 on some benchmarks, maybe win around half depending on the category, but not clearly surpass it overall. And again fable five will have bigger model smell, but this was expected. After testing this coding output, that view feels pretty accurate. GPT-5.6 is clearly better than GPT-5.5 in several visual areas. The lighting, shading, chairs, object details, and exterior of the spaceship looked noticeably stronger. The scene was also easier to test. I do want to give GPT-5.5 credit though. It built out the rooms much much better and the planets looked better than GPT-5.6’s. It was also interesting that both GPT-5.5 and GPT-5.6 produced better-looking planets than Fable 5 in this specific test. The downside with GPT-5.5 was stability. The game was much glitchier and harder to test compared to GPT-5.6. But when it comes to the core of the demo, which is the spaceship itself, Fable 5 still beat both models pretty comfortably. GPT-5.6 is impressive, but from this test, it looks exactly like what I expected which was a meaningful incremental improvement over GPT-5.5, at least for indie game demos, but not something that replaces Fable 5. In collaboration with Chetaslua

Chris

193,958 views • 7 days ago

GPT-5 Thinking I like revisiting this prompt every now and then to see how much better models have gotten over time
0:27

GPT-5 Thinking I like revisiting this prompt every now and then to see how much better models have gotten over time

Angel Bogado 🌻

145,322 views • 9 months ago

Evolution of OpenAI Models doing a particle sandbox game From GPT-3.5 to GPT-5
1:15

Evolution of OpenAI Models doing a particle sandbox game From GPT-3.5 to GPT-5

Angel 🌻

215,192 views • 9 months ago

GPT-5 thinking has been incredible at coding so far i'm not a big fan of vibe coding, but just tried a "browser OS" test in one shot - gemini 2.5 pro failed - claude 4.1 handled flow better, but not as good overall - gpt-5 nailed it, and added all the standard features DEMO 👇
1:34

GPT-5 thinking has been incredible at coding so far i'm not a big fan of vibe coding, but just tried a "browser OS" test in one shot - gemini 2.5 pro failed - claude 4.1 handled flow better, but not as good overall - gpt-5 nailed it, and added all the standard features DEMO 👇

Haider.

43,656 views • 10 months ago

Sam Altman on GPT-5 in Berlin today “How many of you think you will still be smarter than GPT-5 ? I don’t think I’m gonna be smarter than GPT-5” #Gpt5 Sam Altman 👀
1:06

Sam Altman on GPT-5 in Berlin today “How many of you think you will still be smarter than GPT-5 ? I don’t think I’m gonna be smarter than GPT-5” #Gpt5 Sam Altman 👀

Raphaël Dabadie (YC P26)

763,793 views • 1 year ago

Sam Altman on GPT 5: “ GPT-5 is the smartest thing. GPT-5 is smarter than us in almost every way. You know, and yet here we are. ” This might be the last podcast before the big release!
0:24

Sam Altman on GPT 5: “ GPT-5 is the smartest thing. GPT-5 is smarter than us in almost every way. You know, and yet here we are. ” This might be the last podcast before the big release!

Chris

134,450 views • 11 months ago

Codex has come a long way since April. Over the next two weeks, we’re releasing a series of videos to help you get better acquainted with Codex — starting with how to use the Codex CLI with GPT-5-Codex.
5:42

Codex has come a long way since April. Over the next two weeks, we’re releasing a series of videos to help you get better acquainted with Codex — starting with how to use the Codex CLI with GPT-5-Codex.

OpenAI Developers

190,153 views • 8 months ago