We have a customer using it with Swamp and it's actually pretty nice!

Mick, I've always believed you are a wise person. With that statement, you proved it!

Wonderful city!!

Irish people burn when we put on the big light in the living room!

I tried to point out before to a bunch of people that teams who got really good at continuous delivery are the teams who are most effective in this space

oh the latest action is working fine - I want the new verson as you can't use Opus 5.5 on an older install of claude and the new action release unlocks that release :D

Hey @AnthropicAI we still waiting on you to fix that broken GitHub Action build so people can use Opus 5.5 in CI github.com/anthropics/claude…

Opus 5.5 is great, on the other hand!

@AnthropicAI it seems your CI build for the GitHub Action has failed and no one can take advantage of Claude Opus 5.5 in CI

IT JUST GOT INTERESTING!!! As a person who didn't find a model I liked past Opus 4.6 (except GPT Terra...) Now I have my choice :D

what a response...

As if by magic, the normal message of "this new model is great and it has been my daily driver for the last few weeks" - that means the day they shipped Fable 5.2 they changed away from using that model and used this instead.... curious

Because not everything is tracked in VCS?

Had a really fun time talking at @kc_dc today - had so many fantastic questions and enjoyed hearing people’s views on building with AI I will post the slides on this page this evening: swamp-club.com/kcdc

@housecor I didn’t realise you moonlight??

I've stuck with Opus 4.6 as my driver for everything. I use Fable for deep security reviews but it just eats up the weekly limits for that type of thing. I am not 100% sure what I am going to do when Opus 4.6 gets reprecated. I know it's coming... 2/

I wish I could quantify it and present the evidence but I am pretty disappointed by the trend in the frontier models. They peaked for me at Opus 4.6 - each model after introduces token bloat, incredible cost increases, more verbose output and less good outcomes for me 1/

Added support to Swamp today for @AmpCode @pidotdev and Google AntiGravity. The list of native agent integrations is growing :)

I have blogged extensively about how we build the tool we build - stack72.dev - I am giving that talk at KCDC with the details of it I haven't blogged aout the agent tests I do though but it's on my list to write up

We will talk about this next week at KCDC if you are there, my talk is focused a lot on this :D