GPT-5.3-Codex built this Hytale mod with just a few... prompts 👀show more

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 settingsshow more

GPT-5.3-Codex with image gen skill (NBP) I'm loving this... model so much. This is one-shotshow more

Updating gpt-taste skill ⏳ this site was built with... GPT 5.4 medium in Codex using gpt-taste prompt was "landing page. 8sections. for an AI agency"show more

A simple mechanical and electric system for Hynergy, a... Hytale mod. #Hytale #Blockbench #hytalefanart #modshow more

10 minutes later, GPT-5.3-Codex-Spark has my Raptor Call of... Shadows clone artwork integrated! Here's the beach map. Artwork created with imagegen Skill in Codex app. OpenAI Developersshow more

After a weekend of testing and working on something... with GPT-5.3-Codex & Opus 4.6, ChatGPT Pro + Claude Max 5x are still the best combo in my opinion Using Codex & Claude Code CLI running in tmux (the desktop apps are still a bit buggy) and they're accessible even on the go from iPhone with Termius (and VPN) Usually starting with GPT-5.3-Codex xhigh and Opus 4.6 in plan mode, discussing changes and options, and each writing their plans down to separate Markdown files Then letting GPT-5.3-Codex xhigh (or Opus 4.6) implement the changes as the first draft, then Opus 4.6 reviews them with a team of agents (works pretty well already with tmux even though still experimental) based on both prepared plans, fixes stuff, and then another review by GPT-5.3-Codex xhigh or vice versa Interesting that even Opus 4.6 still occasionally makes silly mistakes like wrong imports, partial or overly broad renaming of variables/functions, etc Fun fact, OpenAI apparently plans to use their Super Bowl ad to promote Codex - curious what that will look likeshow more

this is an incredible HyperFrames example our CEO Joshua... Xu took it and built 2 different restyled HeyGen launch video with it just 2 prompts in Codex also Three.js is so underratedshow more

I don't even need to mention which landing page... was created by Opus 4.6 and which one by GPT-5.3-CODEXshow more

the Calamity mod for Hytale just released in Early Access

One prompt. 6 frontier coding models. "Create a realistic... fireworks show using HTML Canvas and JavaScript. No libraries." Some built a whole celebration. Others... lit a sparkler. The lineup: - GPT-5.3 Codex - Claude Opus 4.6 - Gemini 3.1 Pro - MiniMax M2.7 - GLM-5 - Kimi K2.5show more

Here's how to vibe code your very own 3D... game characters for iOS. > nano banana pro > meshy for rig > export to glb > threejs skill to import > capacitor js for iOS > GPT 5.3 codex Full prompts + workflow in 🧵show more

Introducing WarpGrep v2. #1 on SWE-Bench Pro What if... code search was a separate, specialized model? w/ WarpGrep v2: #1 on SWE-Bench Pro Opus 4.6 → 57.5 (+2.1) Codex 5.3 (cli) → 59.1 (+3.1) MiniMax 2.5 → 57.6 (+3.7) without WarpGrep: Opus 4.6 (high) → 55.4 GPT-5.3 Codex (high) → 56.0 MiniMax 2.5 → 55.4show more

Wow! Codex 5.3 built an enemy editor for my... top down shoot 'em up. Shows the timing and flight patterns.show more

GPT 5.3 vs Opus 4.6: a second win for... Opus! ✔︎ Opus builds the file 2x faster ✔︎ Opus nails a good first version ❌ Codex needs 3x "fix bugs" to have a first working version ❌ Codex UI looks really bad Let's try more things....show more

🐐 Gemini 3 Pro GA One shot prompt is... in comment with the codepen link I repeat no model in this entire world able to implement this level of physics and spatial reasoning Not even Opus 4.6 and Gpt-5.3 codex , this is like a generation gap Sub Woofer submitted thisshow more

This looks straight out of a magical girl anime✨... made with GPT Image 2 + Seedance 2 prompts ⤵️show more

And this is 5.4 xhigh in codex. Much better... than what 5.3 gave me.show more

Built this hero section in 45 mins using Paper... MCP plus a few prompts. the era of AI slop is FINALLY overshow more

This Hytale mod FINALLY activated after 4 hours. It... was NOT WORTH the wait.show more

not getting realistic results with AI? that's cause you're... not using this magnific workflow yet. just 3 prompts for GPT-2 and Seedance 2.0 🧵show more