Be sure to increment unofficial plugin versions when you make edits: codex's auto-update works reasonably well, claude not so much, but when asked, both can fix their own config.
And like others have said, imho the skills that are incanted as macros are much more reliably useful. I use my technical project plan skill suite in 90% of my sessions via direct reference, and the stage -> cross-model second-opinion review is how I land all my commits.
Codex and Claude Code support plugin symlinks for local development; if you don’t mind keeping a local clone of your skills repo they can just use it. Claude needs a shim, as it wants to cache plugins; it’ll run a shell command (!) locally to get the plugin path. Codex supports this natively.
The neurologists and neurotherapists for a family member who is a stroke survivor have been pretty consistent in saying that cardiovascular exercise and regular social engagement seem to be the most promising activities to stem cognitive decline.
Yes, I think both things can be true. And also, we haven't had decades of mental activity being mostly optional, so we're not yet seeing the consequences nor science of long-term impact.
In the 1950s, many doctors were convinced that exercise was actively harmful and running was dangerous.
I had two sessions this morning that prior fable and sol sessions were stuck on, where iterations just resulted in _different_ bugs. (One kind of tricky fe layout problem, the other was a backend refactoring that was complicated by trying to aggregate a couple prior sessions that crashed).
I summarized each into new fable 5.1 sessions, and both seem to have arrived at reasonable solutions that only need a few nits revised before they are commit worthy.
Why would we compare it to an 8-year-old design? For browsing, the current MBP smokes the MBN, by margins of roughly one-third. It is a significant and noticeable regression. For sustained workloads like software development or even running the MacOS updates, it is a huge and glaring regression. But it's still good kit.
Don’t forget reasoning effort. We get labels like “low,” “high,” and “max.” That doesn’t mean that the numbers associated with those don’t get remapped on the backend.
I suspect most CFOs/CTOs fear the risk of undertaking a rewrite of your payment processor or merchant of record layers (which can be tricky to fully test even with sandbox/test environments) more than the percentage discount and opportunity cost of not shipping more features.
Be sure to increment unofficial plugin versions when you make edits: codex's auto-update works reasonably well, claude not so much, but when asked, both can fix their own config.
And like others have said, imho the skills that are incanted as macros are much more reliably useful. I use my technical project plan skill suite in 90% of my sessions via direct reference, and the stage -> cross-model second-opinion review is how I land all my commits.
reply