cedric's banner

cedric

@cedric_chee • 3,383 subscribers

SWE | @fastdotai alumni, independent researcher, tester | ex-entrepreneur @AntlerGlobal | GitHub: cedrickchee | scaling verification and evaluation

Videos

Anya Rossi

sweetdream.ai

SweetDream.ai•Sponsored•Livecam

Watch Anya Live

Anya is streaming live right now! Join her private show and enjoy exclusive content.

Exclusive private shows

1.2k viewers online

Private Show

Join now for exclusive access

Free preview available • Premium content

I gave GLM-5.2 one goal: Turn a 2D dungeon crawler it built into a 2.5D isometric Diablo-style game with the visual fidelity of Diablo I. Then I let Z Code cook for 10+ hours. After a week of testing, I'd say its long-horizon execution is close to GPT-5.5 medium. The biggest difference is its agent behavior: GLM-5.2 is much more conservative, so it tends to take a longer path to the objective. Once you understand its quirks, it's remarkably capable. GPT-5.5 /goal also has its own quirks.

I gave GLM-5.2 one goal: Turn a 2D dungeon crawler it built into a 2.5D isometric Diablo-style game with the visual fidelity of Diablo I. Then I let Z Code cook for 10+ hours. After a week of testing, I'd say its long-horizon execution is close to GPT-5.5 medium. The biggest difference is its agent behavior: GLM-5.2 is much more conservative, so it tends to take a longer path to the objective. Once you understand its quirks, it's remarkably capable. GPT-5.5 /goal also has its own quirks.

35,816 views • 1 month ago

Gemini 2.5 Pro with Canvas lets you create prototypes faster than ever, like this game I cranked out in hours with only 50 prompts! No more copy pasting code.

Gemini 2.5 Pro with Canvas lets you create prototypes faster than ever, like this game I cranked out in hours with only 50 prompts! No more copy pasting code.

cedric @ AI Eng SG

110,258 views • 1 year ago

No more content to load