> ...but the human reviewing, directing, and course-correcting feels worse, not better.
Has this person ever been a design or tech-lead for a team? I'm still tired and I've moved on from that role over 5 years ago. Gathering requirements, designing a solution, implementing as tickets, handing off to developers, staying involved in the feedback loop, then reviewing the code and iterating on PRs is absolutely exhausting. The only thing greater than the naive take that HITM is tiring is the privilege to not understand how asinine it is.
I'm mind blown people are complaining about token consumption and not communicating what thinking level they're using - if cost is a concern and you're paying any attention, you'd be starting with medium and seeing if you can get better results with less tokens. Every person complaining about token usage seem to have no methodology - probably using max and completely oblivious.
It's unsurprising when this is the first day that tokens have been crazy like this.
All of us doing crazy agentic stuff were fine on max before this. Now with Opus 4.7, we're no longer fine, and troubleshooting, and working through options.
Ya...you may be who I'm talking about though (if you're speaking from experience). If your methodology is "I used 4.6 max, so I'm going to try 4.7 max" this is fully on you - 4.7 max is not equivalent to 4.6 max, you want 4.7 xhigh.
From their docs:
max: Max effort can deliver performance gains in some use cases, but may show diminishing returns from increased token usage. This setting can also sometimes be prone to overthinking. We recommend testing max effort for intelligence-demanding tasks.
xhigh (new): Extra high effort is the best setting for most coding and agentic use cases.
Ah - xhigh is probably what you want. Their docs suggest xhigh for agentic coding, though judging by their blog high should be better than 4.6 max (ymmv)
I've always used high, so maybe I should be using xhigh
Am I dumb, or are they not explaining what level thinking they're using? We all read the Anthropic blog post yesterday - 4.7 max consumes/produces an incredible number of tokens and it's not equivalent to 4.6 max; xhigh is the new "max".
I tried creating a whatsapp "bot" which would just send notifications for my Jellyfin server. It was a bureaucratic nightmare - creating dev accounts, creating some sort of "project", then it was requiring I register it as a business as though the only valid use case for creating an app for WhatsApp is a business, then it required me to verify my identify and upload documents.
