Tag: openai

All the articles with the tag "openai".

• Codex Subagents Just Got Much Better. Custom Agents Are Finally Worth Trying.

  17 Mar, 2026

  The latest Codex App update makes subagents far more visible and steerable. The real win is that custom agents are finally practical to observe, tune, and use in everyday workflows.

• Fragile Research: When Your Lab Runs on Someone Else’s Safety Filters

  28 Jan, 2026

  Two small account-ban stories (and one biology-redline essay) changed how I think about building research workflows on closed models.

• Codex Multi-Agents: My Image Pipeline Stress Test

  24 Jan, 2026

  Codex’s experimental subagents cut my 131-image workflow from 1–2 hours to ~36 minutes—and improved accuracy.

• GPT Image 1.5 vs Nano Banana Pro: What My Prompts Actually Showed

  20 Dec, 2025

  GPT Image 1.5 tops Image Arena, but X says it’s worse than Nano Banana Pro. I ran identical prompts—illustration, posters, English/Chinese typography, and a TravelBrain itinerary JSON—to see where each model wins.