클로드 코드 2월 업데이트 이후 복잡한 엔지니어링 작업 불가

anthropics / claude-code Public Notifications You must be signed in to change notification settings Fork 18.2k Star 110k [MODEL] Claude Code is unusable for complex engineering tasks with the Feb updates #42796 New issue Copy link New issue Copy link Open Open [MODEL] Claude Code is unusable for complex engineering tasks with the Feb updates #42796 Copy link Labels area:model bug Something isn&#x27;t working Something isn&#x27;t working model Description stellaraccident opened on Apr 2, 2026 Issue body actions Preflight Checklist I have searched existing issues for similar behavior reports This report does NOT contain sensitive information (API keys, passwords, etc.) Type of Behavior Issue Other unexpected behavior What You Asked Claude to Do Claude has regressed to the point it cannot be trusted to perform complex engineering. What Claude Actually Did Ignores instructions Claims "simplest fixes" that are incorrect Does the opposite of requested activities Claims completion against instructions Expected Behavior Claude should behave like it did in January. Files Affected Permission Mode Accept Edits was ON (auto-accepting changes) Can You Reproduce This? Yes, every time with the same prompt Steps to Reproduce No response Claude Model Opus Relevant Conversation Impact High - Significant unwanted changes Claude Code Version Various/all Platform Anthropic API Additional Context We have a very consistent, high complexity work environment and data mined months of logs to understand why -- essentially -- starting in February, Claude cannot be trusted to perform complex engineering tasks. Every senior engineer on my team has reported similar experiences/anecdotes, however, we have one engineer with a repeatable process that we have been using to experiment and data mine. Analysis is from his logs and all workarounds known publicly have been attempted. We have switched to another provider which is doing superior quality work, but Claude has been good to us, and we are leaving this in the hopes that Anthropic can fix their product. Extended Thinking Is Load-Bearing for Senior Engineering Workflows Produced by claude based on my extensive data - if there's any issues, it's because anthropic doesn't let claude think anymore ;) Unfortunately claude deleted my January logs containing a bulk of my work so only summary analysis is available - January was what I expect, Febuary started sliding, and March was a complete and utter loss. Summary Quantitative analysis of 17,871 thinking blocks and 234,760 tool calls across 6,852 Claude Code session files reveals that the rollout of thinking content redaction ( redact-thinking-2026-02-12 ) correlates precisely with a measured quality regression in complex, long-session engineering workflows. The data suggests that extended thinking tokens are not a "nice to have" but are structurally required for the model to perform multi-step research, convention adherence, and careful code modification. When thinking depth is reduced, the model's tool usage patterns shift measurably from research-first to edit-first behavior, producing the quality issues users have reported. This report provides data to help Anthropic understand which workflows are most affected and why, with the goal of informing decisions about thinking token allocation for power users. 1. Thinking Redaction Timeline Matches Quality Regression Analysis of thinking blocks in session JSONL files: Period Thinking Visible Thinking Redacted Jan 30 - Mar 4 100% 0% Mar 5 98.5% 1.5% Mar 7 75.3% 24.7% Mar 8 41.6% 58.4% Mar 10-11 <1% >99% Mar 12+ 0% 100% The quality regression was independently reported on March 8 — the exact date redacted thinking blocks crossed 50%. The rollout pattern (1.5% → 25% → 58% → 100% over one week) is consistent with a staged deployment. 2. Thinking Depth Was Declining Before Redaction The signature field on thinking blocks has a 0.971 Pearson correlation with thinking content length (measured from 7,146 paired samples where both are present). This allows estimation of thinking depth even after redaction. Period Est. Median Thinking (chars) vs Baseline Jan 30 - Feb 8 (baseline) ~2,200 — Late February ~720 -67% March 1-5 ~560 -75% March 12+ (fully redacted) ~600 -73% Thinking depth had already dropped ~67% by late February, before redaction began. The redaction rollout in early March made this invisible to users. 3. Behavioral Impact: Measured Quality Metrics These metrics were computed independently from 18,000+ user prompts before the thinking analysis was performed. Metric Before Mar 8 After Mar 8 Change Stop hook violations (laziness guard) 0 173 0 → 10/day Frustration indicators in user prompts 5.8% 9.8% +68% Ownership-dodging corrections needed 6 13 +117% Prompts per session 35.9 27.9 -22% Sessions with reasoning loops (5+) 0 7 0 → 7 A stop hook ( stop-phrase-guard.sh ) was built to programmatically catch ownership-dodging, premature stopping, and permission-seeking behavior. It fired 173 times in 17 days after March 8. It fired zero times before. 4. Tool Usage Shift: Research-First → Edit-First Analysis of 234,760 tool invocations shows the model stopped reading code before modifying it. Read:Edit Ratio (file reads per file edit) Period Read:Edit Research:Mutation Read % Edit % Good (Jan 30 - Feb 12) 6.6 8.7 46.5% 7.1% Transition (Feb 13 - Mar 7) 2.8 4.1 37.7% 13.2% Degraded (Mar 8 - Mar 23) 2.0 2.8 31.0% 15.4% The model went from 6.6 reads per edit to 2.0 reads per edit — a 70% reduction in research before making changes. In the good period, the model's workflow was: read the target file, read related files, grep for usages across the codebase, read headers and tests, then make a precise edit. In the degraded period, it reads the immediate file and edits, often without checking context. Weekly Trend Week Read:Edit Research:Mutation ────────────────────────────────────────── Jan 26 21.8 30.0 Feb 02 6.3 8.1 Feb 09 5.2 7.1 Feb 16 2.8 4.1 Feb 23 3.2 4.5 Mar 02 2.5 3.7 Mar 09 2.2 3.3 Mar 16 1.7 2.1 ← lowest Mar 23 2.0 3.0 Mar 30 1.6 2.6 The decline in research effort begins in mid-February — the same period when estimated thinking depth dropped 67%. Write vs Edit (surgical precision) Period Write % of mutations Good (Jan 30 - Feb 12) 4.9% Degraded (Mar 8 - Mar 23) 10.0% Late (Mar 24 - Apr 1) 11.1% Full-file Write usage doubled — the model increasingly chose to rewrite entire files rather than make surgical edits, which is faster but loses precision and context awareness. 5. Why Extended Thinking Matters for These Workflows The affected workflows involve: 50+ concurrent agent sessions doing systems programming (C, MLIR, GPU drivers) 30+ minute autonomous runs with complex multi-file changes Extensive project-specific conventions (5,000+ word CLAUDE.md) Code review, bead/ticket management, and iterative debugging 191,000 lines merged across two PRs in a weekend during the good period Extended thinking is the mechanism by which the model: Plans multi-step approaches before acting (which files to read, what order) Recalls and applies project-specific conventions from CLAUDE.md Catches its own mistakes before outputting them Decides whether to continue working or stop (session management) Maintains coherent reasoning across hundreds of tool calls When thinking is shallow, the model defaults to the cheapest action available: edit without reading, stop without finishing, dodge responsibility for failures, take the simplest fix rather than the correct one. These are exactly the symptoms observed. 6. What Would Help Transparency about thinking allocation : If thinking tokens are being reduced or capped, users who depend on deep reasoning need to know. The redact-thinking header makes it impossible to verify externally. A "max thinking" tier : Users running complex engineering workflows would pay significantly more for guaranteed deep thinking. The current subscription model doesn't distinguish between users who need 200 thinking tokens per response and