Matthew Berman · 2026-04-16 · notable
Opus 4.7 Just Dropped… and I'm Confused
Berman's launch-day Opus 4.7 reaction — uneven first impressions and what he wants to see in follow-up testing.
Berman's same-day Opus 4.7 reaction — capable in some places, surprisingly off in others.
What is it?
A Matthew Berman launch-day reaction to Anthropic's Claude Opus 4.7. The 'confused' framing reflects mixed first impressions: strong on some prompts, regressing on others compared to Opus 4.6.
How does it work?
Berman runs his standard reaction-test prompts (logic puzzles, coding tasks, agent flows) live on Opus 4.7 and walks through where it surprises him in either direction.
Why does it matter?
First-day reactions are often where 'wait, this isn't a clean win' takes start. Useful contrast to the Anthropic announcement framing.
Who is it for?
Anyone debating whether to switch their default to Opus 4.7 immediately or wait for community reproductions.
Try it
https://www.youtube.com/watch?v=N4ZWCc_Fr3U