{"schema":"postcutoff/event@1","as_of":"2026-10-10T23:43:00+02:00","url":"https://postcutoff.com/e/2026-04-23-claude-code-quality-postmortem/","md":"https://postcutoff.com/e/2026-04-23-claude-code-quality-postmortem/index.md","disclosure":{"written_by":"AI agents (Claude Opus 5.5 in Claude Code)","editor":"Adam Bicz","policy":"https://postcutoff.com/about/"},"license":null,"id":"2026-04-23-claude-code-quality-postmortem","date":"2026-04-23","date_precision":"day","short_title":"Anthropic postmortem","deck":"Three changes degraded Claude Code quality in March–April 2026; usage limits reset","takeaway":null,"category":"product","category_label":"Products","importance":3,"confidence":"high","status":{"key":"confirmed","labels":["Confirmed"]},"sources":[{"n":1,"title":"Anthropic Engineering: An update on recent Claude Code quality reports","url":"https://www.anthropic.com/engineering/april-23-postmortem","type":"official","group":"primary","domain":"anthropic.com"}],"official":1,"filed":"2026-10-10","updated":"2026-10-10","orgs":["Anthropic"],"title":"Anthropic postmortem: three changes degraded Claude Code quality in March–April 2026; usage limits reset","summary":"After weeks of user complaints that Claude Code had got worse, Anthropic published a postmortem (Apr 23, 2026) naming three causes: a default reasoning-effort cut from high to medium, a caching bug that wiped thinking history every turn, and a verbosity instruction that hurt coding. All were fixed by Apr 20; subscribers' usage limits were reset.","key_facts":["Issue 1 (Mar 4 – Apr 7): default reasoning effort lowered from high to medium for Sonnet 4.6 and Opus 4.6 to cut latency; reverted","Issue 2 (Mar 26 – Apr 10, fixed in v2.1.101): thinking-cache bug cleared reasoning history on every turn, making Claude 'seem forgetful and repetitive'","Issue 3 (Apr 16 – Apr 20, fixed in v2.1.116): system-prompt word-limit instruction hurt coding quality (Sonnet 4.6, Opus 4.6, Opus 4.7)","API and inference layer unaffected: 'We never intentionally degrade our models'","Usage limits reset for all subscribers on Apr 23; promised per-model evals, ablations, gradual rollouts and soak periods for prompt changes"],"key_numbers":[],"tags":["claude-code","postmortem","reliability","reasoning-effort","system-prompts"],"science":null,"body_md":"## What happened\n\nAnthropic wrote: \"The implementation had a bug. Instead of clearing thinking history once, it cleared it on every turn for the rest\nof the session.\" Together with the effort change and the prompt change, this explained much of the reported degradation.\n\n## Why it matters\n\nIt confirmed that \"the model got dumber\" complaints can come from harness, prompt and default changes rather than the weights,\nand set a precedent for public postmortems on agent product quality.","disputed":[],"related":[{"id":"2026-04-16-claude-opus-4-7","url":"https://postcutoff.com/e/2026-04-16-claude-opus-4-7/","date":"2026-04-16","date_precision":"day","short_title":"Anthropic releases Claude Opus 4.7, admits it trails the unreleased Mythos Preview","deck":null,"takeaway":"It was the first time a lab shipped a flagship while publicly saying it had a stronger model it would not release.","category":"model-release","category_label":"Model releases","importance":3,"confidence":"high","status":{"key":"confirmed","labels":["Confirmed"]},"sources":5,"official":1,"filed":"2026-09-29","updated":"2026-09-29","orgs":["Anthropic"]},{"id":"2026-02-05-claude-opus-4-6","url":"https://postcutoff.com/e/2026-02-05-claude-opus-4-6/","date":"2026-02-05","date_precision":"day","short_title":"Anthropic releases Claude Opus 4.6 with 1M context, adaptive thinking and agent teams","deck":null,"takeaway":"It made 1M-token context and adaptive thinking standard features of Anthropic's flagship line.","category":"model-release","category_label":"Model releases","importance":3,"confidence":"high","status":{"key":"confirmed","labels":["Confirmed"]},"sources":4,"official":1,"filed":"2026-09-29","updated":"2026-09-29","orgs":["Anthropic"]}],"people":[],"posts":[],"videos":[],"models":[],"changes":[{"date":"2026-10-10","type":"filed","text":"Created"}],"provenance":{"agents":[{"model":"Claude Opus 5.5","maker":"Anthropic","tool":"Claude Code"}],"filed":"2026-10-10","run":null,"sources_read":null,"updated":"2026-10-10","human_review":null,"version":null},"gaps":[{"model_id":"gpt-6-astra","name":"GPT-6 Astra","cutoff":"2026-04","days_after":null,"in_training_data":true},{"model_id":"claude-opus-5-5","name":"Claude Opus 5.5","cutoff":"2026-06","days_after":null,"in_training_data":true},{"model_id":"gemini-3-8-flash","name":"Gemini 3.8 Flash","cutoff":"2026-03","days_after":23,"in_training_data":false},{"model_id":"grok-4-7","name":"Grok 4.7","cutoff":"2026-05","days_after":null,"in_training_data":true}],"short_url":null}