<p>Curious what’s unfolding at Anthropic.</p>
by•
I’d skip this subscription entirely if Cloud Max didn’t offer Fable 5. Opus 4.7, 4.8 & 5.0 are underwhelming, and they keep regressing.
Benchmarks keep improving, but real-world experience keeps declining. It’s incoherent, difficult to steer, and perpetually slacks off.
It’s exactly that insufferable big-tech coworker: all lectures, no delivery.
When given tasks, it actively looks for ways to minimize its workload.
In automated loops? Send it 7 requirements, it’ll claim everything is complete. Yet every task is only 20% finished, rendering all outputs useless.
Curious what’s unfolding at Anthropic.
Opus 4.6 feels like a one-off stroke of luck. They seemingly haven’t cracked the code to build a better Opus iteration.
6 views
Replies
I just switched to the Max plan this month, and I feel the pressure and limits of the pro plan made me utilize it better.
Some days it works well, and some days it just fails and keeps a backlog for everything.
I asked it to create a launch checklist; it added 45 times. We close 12, but it added 9. Closed 11 and it added 10. Somehow it went to 64, it keeps discovering needs things but when I stuructered the md file around the mvp, it realized the mistake and categorized the tasks.
I think it's a learning curve to vibe code. Still to explore loop engineering; any tips there?