Tag
A user suggests testing Codex's ability by instructing it to open Microsoft Paint and draw, referring to a new pelican test.
The article describes a user testing Google's Gemini Omni model on their own phone footage, evaluating its performance.
A user reports that the evaluation cost for their AI agent tripled after adding four tools, seeking optimization advice.
A user tested OpenAI Codex on the 2025 college entrance exam math paper, restricting it from accessing the internet and only using Python for real computation. It completed the test in 7 minutes, scored a perfect 150 points, and also pointed out contradictions in the official answers.
Figure robot conducts head test, related video clip shared.
A user tested Gemma 4 12B as a coding agent in VSCodium using Pi Agent extension, successfully performing a task to create a Python script that reads logs and outputs JSON. The model handled tool use autonomously with zero bugs.
Meta is testing a Meta AI account on Threads that users can tag for answers, but they cannot block the account, sparking backlash. The feature is initially available in select countries as a test.