Dev roasts coding models: Gemini thinks too briefly, Claude overthinks, OpenAI ships sloppy code
legit_api · x · 2026-10-15
A developer summarizes the coding quirks of major models: Google caps Gemini's thinking at single-digit minutes, Anthropic makes Claude overthink, and OpenAI's models ship the sloppiest code that breaks within a week or two. Accompanied by a Pepe meme.
More from coding & agent
- Creator builds custom GoPro ingestion tool with Codex: 4-camera array with WiFi trickle ingest — OpenAIDevs · 2026-10-15
- Claude Code 2.1.300 cuts system prompt tokens by 58.5%, drops forced question-asking directive — ClaudeCodeLog · 2026-10-15
- Claude Code 2.1.300 ships 88 CLI changes, drops AskUserQuestion directive from system prompt — ClaudeCodeLog · 2026-10-15
- Tahoe AI opens Tara, a one-prompt plug-in connecting agents to its Tahoe-100M biology datasets — anshulkundaje · 2026-10-15
- sgrep cuts coding agent LLM costs 21.3% on SWE-bench versus ripgrep, fully local in Rust — udmrzn · 2026-10-15
- 10 GitHub repos that turn Claude Code and Codex into elite UI designers — udmrzn · 2026-10-15