Issue: Claude Code is unusable for complex engineering tasks with Feb updates

Post by michaelashley29 » Tue, Apr 07, 2026, 1:29 PM UTC

freeqaz wrote: post #603

bcherny wrote: post #209

Hey all, Boris from the Claude Code team here. I just responded on the issue, and cross-posting here for input. --- Hi, thanks for the detailed analysis. Before I keep going, I wanted to say I appreciate the depth of thinking & care that went into this. There's a lot here, I will try to break it down a bit. These are the two core things happening: > `redact-thinking-2026-02-12` This beta header hides thinking from th…

I have been wondering if 1 Million token context contributes here also. Compaction is much rarer now. How does that influence model performance? For some tasks I do, I feel like performance is worst now after this. Also Plan mode doesn't seem to wipe context anymore?

Post by pcjones1 » Tue, Apr 07, 2026, 1:40 PM UTC

alexchen_dev wrote: post #510

bcherny wrote: post #461

Earlier quoted context omitted.

Thanks for the feedback IDs — read all 5 transcripts. On the model behavior: your sessions were sending effort=high on every request (confirmed in telemetry), so this isn't the effort default. The data points at adaptive thinking under-allocating reasoning on certain turns — the specific turns where it fabricated (stripe API version, git SHA suffix, apt package list) had zero reasoning emitted, while the turns with d…

[flagged]

Post by grim_io » Tue, Apr 07, 2026, 1:46 PM UTC

gib444 wrote: post #602

thatxliner wrote: post #567

Earlier quoted context omitted.

> is consumer-hostile thinking I've been saying this with many of my friends but, I feel like it's also probably illegal: you paid for a subscription where you expect X out of, and if they changed the terms of your subscription (e.g. serving worse models) after you paid for it, was that not false advertising? Could we not ask for a refund, or even sue?

Depends on the terms and conditions

Post by robeym » Tue, Apr 07, 2026, 1:56 PM UTC

bcherny wrote: post #209

Hey all, Boris from the Claude Code team here. I just responded on the issue, and cross-posting here for input. --- Hi, thanks for the detailed analysis. Before I keep going, I wanted to say I appreciate the depth of thinking & care that went into this. There's a lot here, I will try to break it down a bit. These are the two core things happening: > `redact-thinking-2026-02-12` This beta header hides thinking from th…

  {
    "env": {
      "CLAUDE_CODE_EFFORT_LEVEL": "max",
      "CLAUDE_CODE_DISABLE_BACKGROUND_TASKS": "1",
      "CLAUDE_CODE_DISABLE_ADAPTIVE_THINKING": "1"
    }
  }

Post by JamesSwift » Tue, Apr 07, 2026, 2:06 PM UTC

viktorianer wrote: post #702

dev_l1x_be wrote: post #372

Earlier quoted context omitted.

It hallucinated a GUID for me instead of using the one in the RFC for webscokets. Fun part was that the beginning was the same. Then it hardcoded the unit tests to be green with the wrong GUID.

[flagged]