Re:Anthropic silently downgraded cache TTL from 1h → 5M on M...
by jitl on Sunday April 12, 2026 @12:23PM
(#47741510)
I saw a big hit to Claude’s intelligence w/ the 1M context window model and the change to adaptive reasoning (github issue linked elsewhere in this thread).
I’m pretty much using 90% Codex now, although since Claude is consistently faster at answering quick questions, I still keep it open for that and for code-reviewing codex/human work before commit.
I’m pretty much using 90% Codex now, although since Claude is consistently faster at answering quick questions, I still keep it open for that and for code-reviewing codex/human work before commit.