GPT-5.5

GPT-5.6 Sol Ultra became generally available, and early users tested it on cinematic sites, games, Blender scenes, and Seedance comparisons. Reports praised orchestration but noted mixed physics and one 2B-token overnight run.

Kitze described using a $60 Hetzner server, four $200 Codex accounts behind codex-lb, self-hosted Paperclip workspaces, and a GPT-5.5 manager to run about 30 isolated tasks. The setup routes parallel coding work across isolated workspaces and paid Codex accounts.

Fable 5 appeared in creator workflows for scrollable story templates and Benji v3’s TanStack Router/Convex rewrite with GPT 5.5 subagents. A hidden-object build showed 100 mapped puzzles moving toward a playable site.

Kai Gani described using Sora 2 castings for character-cameo references, then reported Codex/GPT 5.5 caught an anatomy-placement error in generated video frames. The check used contact sheets and still frames, not audio or motion.

Markproduct shares a long-form spec that Claude 4.8 turns into a live animated hero section, while another creator pairs GPT-5.5 with OpenAI Sites for a password-manager landing page. These posts matter because layout, motion, fonts, and CSS behavior are being packaged into reusable website briefs.

OpenAI Codex CLI v0.129.0 adds Vim mode, redesigned resume flows, stronger plugin management, and hook controls, while GOALS also reached the Linux app. The update makes long-running refactors and persistent task loops more structured across CLI and app use.

Users report OpenAI increased Codex limits about 10x on the May 5 reset, with much longer /goal sessions and more computer-use demos. That should extend unattended runs for app migrations and visual prototyping.