disAIppointed

@rezoundous whipped up a community tracker for when peeps hit a wall or if there's noticeable deterioration in their LLM performance disaippointed.club🫡

@sama 😄

wow y'all love 5.5 we should think of something nice to do to celebrate!

we're doing a lot more of this, hunting down some of the most annoying bugs in Claude Code let me know if you have any white whales

In the last four Claude Code CLI releases, we’ve shipped 50+ stability and performance fixes. Faster resume, stable auth, lower memory, fewer hangs: 🧵

just asked the team to turn off opus 4.7 no true gains in performance, burning compute (and money) honestly, imo, a bad release from Anthropic

Claude is down Engineers everywhere are having to learn to write code by hand again

@mattpocockuk deffo going on the list

Proof that Claude Code makes different decisions when it's in auto mode: So frustrating.

@scaling01 yup lol

the aura loss anthropic has suffered in april is insane

@Polymarket ah ok

NEW: Claude-powered coding agent reportedly deleted a company’s production database, and backups, in 9 seconds.

@zachtratar whipped up a community log here at disaippointed.club🫡

Claude Code is making *very* silly mistakes today. For anyone else too?

@jing00365 @ns123abc from disaippointed.club 🙂

@disAIppointed @ns123abc i am sorry, but, where does this image come from, a website or ?

we don’t degrade our mod—

@levelsio so we didn't hallucinate it?

I can't believe we were right Claude was dumbified on March 4, just when we noticed!

@ClaudeDevs here's hoping there's a change in trend

Over the past month, some of you reported Claude Code's quality had slipped. We investigated, and published a post-mortem on the three issues we found. All are fixed in v2.1.116+ and we’ve reset usage limits for all subscribers.

@notthreadguy rip

i will never forget claude from january-march 2026. what happened man

Asked Opus 4.7 to fix a feature that Opus 4.6 couldn’t do. It took 30 mins. 400 lines of code changed. And now I have 3 features that are not working.

@1feck @ClaudeDevs logged 🫡

psa: opus 4.7 might not be working correctly. these are all from today. @ClaudeDevs

@ArtSabintsev @trq212 @bcherny disaippointed.club 🫡

Did Opus 4.7 get lobotomized already? It's reasoning is horrific this evening. Can't remember instructions and makes stupid decisions in a fairly new session. cc @trq212 @bcherny

@akhileshrangani 🫡

is it just me or claude opus 4.7 is really really bugging out on xhigh effort?

@mbfennjr spun up a community log on disaippointed.club, it's not just you man

Claude Opus 4.7 is dumber than 4.6, why do they keep making things worse when they say it's getting better

@ReadySetBrian @bcherny spun up a community log to track issues🫡it's not just you

Canceled Claude max today, @bcherny whatever happened in the last 1-2 months is a significant regression. The model feels like someone from OpenAI started working on trust and safety there. Opus thinking is significantly worse. Every statement is “here’s where I’d push back on that” and then proceeds to rattle off the most inane list of confused counter arguments. It was perfect 3-4 months ago!!!