SOTA models quietly nerfed ~15 times in 2025, dev suggests dual Codex+Claude subscriptions
StewartalsopIII · x · 2026-10-07
- The author claims new state-of-the-art models have been quietly nerfed/quantized about 15 times since 2025, and the pace is accelerating.
- His workaround: hold both Codex and Claude subscriptions ($100 each) and have them send prompts back and forth in the terminal, so you can always lean on whichever model isn't currently degraded.
- Caveat: this requires working entirely in the terminal.
More from coding & agent
- Running 2-3 parallel AI coding sessions beats 5-6, founder finds — IgorCarron · 2026-10-07
- Apple paper: a single well-prompted agent with shell beats multi-agent ML harnesses, 62.5% vs 47.1% Kaggle medal rate — rohanpaul_ai · 2026-10-07
- Caveman Renders AI Agent Skills as Images, Cutting Token Cost by 61% — bigaiguy · 2026-10-07
- Kev: an open-source reimplementation of Jev built on Qwen3.5 that runs 100% locally — Arindam_1729 · 2026-10-07
- Google Releases SAM, a P2P Network Letting AI Agents Discover and Call Each Other's Tools — thisguyknowsai · 2026-10-07
- Open-Source PhoneUse Agent Runs Real Android Tasks With Observe-Act-Verify Loop — 381654729fuck · 2026-10-07