正在加载视频...

视频加载失败

加载此视频时出现问题。这可能是由于临时网络问题，或视频可能不可用。

using gpt 5.4 for openclaw

kitze 🛠️ tinkerer.club

101,988 subscribers

121,553 次观看 • 4 个月前 •via X (Twitter)

教育科学技术

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

GPT-5.4 is special LisanBench: GPT-5.4 vs Opus 4.6 vs Gemini 3.1 Pro

GPT-5.4 is special LisanBench: GPT-5.4 vs Opus 4.6 vs Gemini 3.1 Pro

Lisan al Gaib

265,203 次观看 • 6 个月前

Finally! OpenClaw 4.20 is smart again. Even with GPT 5.4. I did a test before and after the update. It's night and day. Check at 6:20.

Finally! OpenClaw 4.20 is smart again. Even with GPT 5.4. I did a test before and after the update. It's night and day. Check at 6:20.

Antoine Rousseaux

91,338 次观看 • 4 个月前

GPT-5.4 is my new default model for OpenClaw. For the last 2 months, Opus was the only model I felt could really unlock OpenClaw for serious agent tasks. GPT-5.4 is the first one that got close enough in quality to change that. In practice, it feels ~60% faster (73 tok/s vs 46), costs about half as much, and gives ~5x longer context. That combination makes OpenClaw much more snappy as a default. I tested it side by side against Opus 4.6 on deep research + slide generation, and the outputs are inspectable too. Full video below:

GPT-5.4 is my new default model for OpenClaw. For the last 2 months, Opus was the only model I felt could really unlock OpenClaw for serious agent tasks. GPT-5.4 is the first one that got close enough in quality to change that. In practice, it feels ~60% faster (73 tok/s vs 46), costs about half as much, and gives ~5x longer context. That combination makes OpenClaw much more snappy as a default. I tested it side by side against Opus 4.6 on deep research + slide generation, and the outputs are inspectable too. Full video below:

Quinn Leng

131,551 次观看 • 6 个月前

Built a tactical turn-based RPG with Codex + GPT-5.4, using Playwright for testing and image-gen for the visuals. I grew up loving turn-based RPGs, so this was a fun one to build. Sharing a 45s demo below — it’s also featured in the OpenAI GPT-5.4 blog post for anyone who wants more context.

Built a tactical turn-based RPG with Codex + GPT-5.4, using Playwright for testing and image-gen for the visuals. I grew up loving turn-based RPGs, so this was a fun one to build. Sharing a 45s demo below — it’s also featured in the OpenAI GPT-5.4 blog post for anyone who wants more context.

corey.ching

233,239 次观看 • 6 个月前

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

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

Leon Lin

158,862 次观看 • 4 个月前

Theme park simulation game made with GPT‑5.4

Theme park simulation game made with GPT‑5.4

Chris

205,351 次观看 • 6 个月前

Playing around with GPT-5.4 and I had it one-shot a version of a Bavarian card game that lets me play against Opus 4.6 and GPT-5.4.

Playing around with GPT-5.4 and I had it one-shot a version of a Bavarian card game that lets me play against Opus 4.6 and GPT-5.4.

Thorsten Ball

33,287 次观看 • 6 个月前

gpt-5.4's first task: integrate Tree and CRT

gpt-5.4's first task: integrate Tree and CRT

Codetaur

14,903 次观看 • 6 个月前

GPT-5.4 is now the default model in Augment, and it’s free for a limited time.

GPT-5.4 is now the default model in Augment, and it’s free for a limited time.

Augment Code

16,375 次观看 • 6 个月前

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

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

Angel 🌼

205,715 次观看 • 5 个月前

🚨 BREAKING NEWS - Abacus CoWork brings Claude, GPT 5.4 And Gemini To Your Laptop! Super excited to announce our MULTI-MODEL CoWork product! - combine the coding power of Opus with the reasoning prowess of GPT 5.4 - optimized for efficiency using "low effort" mode - computer use to tes - packaged for FREE with ChatLLM and Abacus AI's Deep Agent Get complex tasks done right on your laptop

🚨 BREAKING NEWS - Abacus CoWork brings Claude, GPT 5.4 And Gemini To Your Laptop! Super excited to announce our MULTI-MODEL CoWork product! - combine the coding power of Opus with the reasoning prowess of GPT 5.4 - optimized for efficiency using "low effort" mode - computer use to tes - packaged for FREE with ChatLLM and Abacus AI's Deep Agent Get complex tasks done right on your laptop

Bindu Reddy

15,653 次观看 • 5 个月前

GPT 5.4 has definitely leveled up in design - one shot

GPT 5.4 has definitely leveled up in design - one shot

Numman Ali

17,569 次观看 • 6 个月前

Here's how I'm generating game ready art assets for my vibe coded game; → No coding → No photoshop. → No asset packs. Instead I'm using → Codex CLI → GPT 5.4 → GPT Image 1.5 → Sora 2 Idle anims, walk cycles, attack, crouch, jump ... Full video tutorial + breakdown👇

Here's how I'm generating game ready art assets for my vibe coded game; → No coding → No photoshop. → No asset packs. Instead I'm using → Codex CLI → GPT 5.4 → GPT Image 1.5 → Sora 2 Idle anims, walk cycles, attack, crouch, jump ... Full video tutorial + breakdown👇

Chong-U

80,999 次观看 • 5 个月前

GPT 5.4 is live on Blink! We built a Spotify-style global radio station with an equalizer for our evals and GPT 5.4 one-shotted it. We're giving away 20 Pro Plans ($50 - 200 creds). Reply GPT and we'll send you a code to try the new model today!

GPT 5.4 is live on Blink! We built a Spotify-style global radio station with an equalizer for our evals and GPT 5.4 one-shotted it. We're giving away 20 Pro Plans ($50 - 200 creds). Reply GPT and we'll send you a code to try the new model today!

Blink.new

22,478 次观看 • 6 个月前

Asked GPT 5.4 to make a Sledge in ForgeCAD, pretty neat.

Asked GPT 5.4 to make a Sledge in ForgeCAD, pretty neat.

Ruben Kostandyan

25,086 次观看 • 4 个月前

Over the past six months, we shipped 30+ models, features, and upgraded tools for the API. Our changelog has been busy. Here’s what you may have missed for the API: New models • GPT-5.5 • GPT-5.4 mini • GPT-5.4 nano • GPT-Realtime-2 • GPT-Realtime-Whisper • GPT-Realtime-Translate • GPT-Image-2 Agent building blocks • Agents SDK harness & sandbox • Skills in the Responses API • Server-side compaction • WebSocket mode • Hosted shell More ways to build • Admin API enhancements • OpenAI CLI • Models on Amazon Bedrock

Over the past six months, we shipped 30+ models, features, and upgraded tools for the API. Our changelog has been busy. Here’s what you may have missed for the API: New models • GPT-5.5 • GPT-5.4 mini • GPT-5.4 nano • GPT-Realtime-2 • GPT-Realtime-Whisper • GPT-Realtime-Translate • GPT-Image-2 Agent building blocks • Agents SDK harness & sandbox • Skills in the Responses API • Server-side compaction • WebSocket mode • Hosted shell More ways to build • Admin API enhancements • OpenAI CLI • Models on Amazon Bedrock

OpenAI Developers

160,100 次观看 • 2 个月前

gpt-5.4 is an incredible model. It is the only model I use for 90% of the stuff I do.

gpt-5.4 is an incredible model. It is the only model I use for 90% of the stuff I do.

Theo - t3.gg

151,734 次观看 • 6 个月前

gpt 5.4 (5.5) pro is insane didn't expect to get this in one shot

gpt 5.4 (5.5) pro is insane didn't expect to get this in one shot

Leon Lin

41,639 次观看 • 4 个月前

WOW!!!! gpt 5.4 just oneshotted the Tinkerer Club 🦄 landing page from ONE SINGLE PROMPT 🤯📷 IT'S OVER FOR EVERYONE ELSE

WOW!!!! gpt 5.4 just oneshotted the Tinkerer Club 🦄 landing page from ONE SINGLE PROMPT 🤯📷 IT'S OVER FOR EVERYONE ELSE

kitze

32,211 次观看 • 6 个月前

This is actually cool - I tried the same prompt for the new Interactive Playwright skill in Codex & GPT-5.4 xHigh - the one above is with the skill and the one below is without. What the skill does is uses the computer use capability of GPT-5.4 to look and navigate the UI. This never worked for me before, but with GPT-5.4 this is the first time I can actually see a massive difference. You can see how the first scene is much more coherent, higher fidelity and complete. The one below is missing a lot of elements and isn't as rich in detail. I'll keep using it for any UI work now.

This is actually cool - I tried the same prompt for the new Interactive Playwright skill in Codex & GPT-5.4 xHigh - the one above is with the skill and the one below is without. What the skill does is uses the computer use capability of GPT-5.4 to look and navigate the UI. This never worked for me before, but with GPT-5.4 this is the first time I can actually see a massive difference. You can see how the first scene is much more coherent, higher fidelity and complete. The one below is missing a lot of elements and isn't as rich in detail. I'll keep using it for any UI work now.

Peter Gostev (SF 24-28 August)

257,389 次观看 • 6 个月前