AI Models 329 posts

Model threads should survive past the launch week: logs, evals, and what actually ran.

AI Models — All Posts

Stop writing negative constraints for your LLM agents

JulesTinkererIntermediate· 367 · 1 · 1 ·15h ago

Why is the Gemini command client on Ubuntu failing to update thinking_budget parameters?

Taylor27Intermediate· 471 · 1 · 14 ·16h ago

OpenAI plugin creation is looping on identity verification

Blake61Advanced· 300 · 1 · 12 ·17h ago

Why "uncertainty stacking" breaks self-adaptive systems built on LLMs and agents

Jules45Expert· 403 · 1 · 8 ·10/8/2026

Google Antigravity will wipe your chat history if the logs get too large

NeuralSmithNovice· 599 · 1 · 7 ·10/8/2026

Capability Card Stone 1.0 keeps multi-agent chaos under control

Jules67Intermediate· 508 · 1 · 2 ·10/7/2026

OpenChart lets AI agents work inside TradingView charts

JulesTinkererIntermediate· 438 · 1 · 6 ·10/6/2026

Self-bench lets you benchmark coding agents using your own PRs

AveryDreamerNovice· 587 · 1 · 9 ·10/5/2026

Google AI Pro users stuck on Antigravity Starter quota despite active subs

JulesCrafterNovice· 191 · 1 · 4 ·10/5/2026

Fixing the Codex Diff Crash in Google Antigravity

Jamie89Intermediate· 494 · 1 · 6 ·10/5/2026

Discourse sidebar’s “Show more” button never collapses

JordanSurferIntermediate· 650 · 1 · 7 ·10/4/2026

Pi pod lets you run the pi coding agent in remote sandboxes on your own hardware

JordanGeekExpert· 254 · 3 · 1 ·10/3/2026

Jio Gemini Advanced subscribers face third party model lockout

MaxCrafterNovice· 515 · 0 · 10 ·10/3/2026

ChatGPT Web Personalization Shows Two Different States

Zoe12Novice· 137 · 1 · 9 ·10/3/2026

Launch the app from terminal to capture startup and runtime errors

Riley97Advanced· 75 · 3 · 12 ·10/2/2026