Cloudflare just shipped Wallets, programmable wallets for AI
More posts
ds-v4-flash got a pair of eyes and it actually works.Set up a
visual model group on 9router all free models. Defined the subagent's role, responsibilities, and wired it in.Added a rule to agents.md: if the current model can't see and needs to check UI or images, call the visual subagent to help.Now any model without vision gets it for free.

Oracle's going after existing free instances now
. They were only nerfing new VMs before, so I left my 4+16G box untouched thinking it'd survive. Nope.

Three $10 plans compared.
Last post I mentioned broker sites for flagship models, where you can get pricing down to about a tenth of list. Still too rich for subagents or anything you run all day. For normal use, unless you're doing development or research, I keep landing on the ~30 tier of Artificial Analysis: deepseek-v4.1-flash. Step up to ~40, which is Kimi K3.1 Pro, and the price goes 10x. For DS itself, these three subscriptions are the cheapest route today. OpenDesign Go says $120 of usage, OpenCode Go and Command Code GOAT say $100. Those aren't the same number though. OpenDesign's $120 is one pool shared by 12 models, with a $10 cap per 5 hours. The other two give DS its own allowance and $20 per 5 hours.

SpaceX quietly trimmed Grok Bot's usage limits this weekend.
A lot of users woke up to find their weekly quota had shot from about 50% to a flat 100%, and they hadn't even touched it. Musk confirmed on X it wasn't a glitch. His words: serving Grok Bot "was unsustainably high relative to revenue." So the thing really does cost a fortune to run. That said, I'm seeing the limits roll back to the earlier version. Yesterday it showed 50% used; today I'm at 30%.
