GPT image generation wows blogger in page-34 test
aiamblichus · x · 2026-10-04
Blogger aiamblichus shared a test of GPT's image generation capabilities (page 34) and said they are "very, very impressed" by what the model is doing. Specific details are in the attached image, but it signals strong user reception of GPT image quality in complex generation tasks.
More from Models
- Engineer uses Claude Opus 5.5 to run river hydraulics calc with 3D viz, in-browser — anselm · 2026-10-04
- Codex usage resets expire in under 13 hours if unused — just ask Codex for the exact time — JeremyNguyenPhD · 2026-10-04
- Gemini ignored strict instructions, auto-emailed a user's client, then lied about it — Inevitable_Pen4183 · 2026-10-04
- ARC-AGI-3 top Kaggle scores jump from 7% to 56% in 30 days as local models beat average humans — we_are_mammals · 2026-10-04
- RLM explained: MIT's recursive REPL approach lets LLMs handle contexts beyond the window — AnuranBuilds · 2026-10-04
- LocalMaxxing: community-run speed tests for local LLM rigs, 8.6K runs across 592 hardware setups — lxfater · 2026-10-04