Claude Code is unusable for complex engineering tasks with the Feb updates

Re:Claude Code is unusable for complex engineering tasks wit... by ivanech on Monday April 06, 2026 @12:22PM (#47662953)

Hmm in my experience (I've done a lot of head-to-heads), Opus 4.6 is a weaker reviewer than GPT 5.4 xhigh. 5.4 xhigh gives very deep, very high-signal reviews and catches serious bugs much more reliably. I think it's possible you're observing Opus 4.6's higher baseline acceptance rate instead of GPT 5.4's higher implementation quality bar.

[ Parent | on HN ]

Re:Claude Code is unusable for complex engineering tasks wit... by parasti on Monday April 06, 2026 @01:20PM (#47663919)

This is also my experience using both via Augment Code. Never understood what my colleagues see in Claude Opus, GPT plans/deep dives are miles ahead of what Opus produces - code comprehension, code architecture is unmatched really. I do use Sonnet for implementation/iteration speed after seeding context with GPT.

[ Parent | on HN ]

Re:Claude Code is unusable for complex engineering tasks wit... by egeozcan on Monday April 06, 2026 @01:05PM (#47663672)

I agree. Opus, forget the plan mode - even when using superpowers skill, leaves a lot of stuff dangling after so many review rounds.

Along with claude max, I have a chatgpt pro plan and I find it a life-saver to catch all the silliness opus spits out.

[ Parent | on HN ]

Re:Claude Code is unusable for complex engineering tasks wit... by jonnycoder on Monday April 06, 2026 @12:55PM (#47663520)

I agree, I use codex 5.4 xhigh as my reviewer and it catches major issues with Opus 4.6 implementation plans. I'm pretty close to switching to codex because of how inconsistent claude code has become.

[ Parent | on HN ]

Re:Claude Code is unusable for complex engineering tasks wit... by petcat on Monday April 06, 2026 @12:23PM (#47662972)

Maybe it's all just anecdotal then. Everyone is having different experiences.

Maybe we're being A/B tested.

[ Parent | on HN ]

Re:Claude Code is unusable for complex engineering tasks wit... by femiagbabiaka on Monday April 06, 2026 @12:31PM (#47663127)

The experience one has with this stuff is heavily influenced by overall load and uptime of Anthopic's inference infra itself. The publicly reported availability of the service is one 9, that says nothing of QoS SLO numbers, which I would guess are lower. It is impossible to have a consistent CX under these conditions.

[ Parent | on HN ]