But eventually, waiting ceases, and it’s action time.

Anyway I tried to get our AI thing to give me an image, it’s too funny.

then we’re really, really close 🤞🏻

After my last post about setting up CodeLlama, some colleagues have asked the million dollar question: how does CodeLlama compare to Copilot? My early answer is: “I don’t know yet” but here’s a useful comparison. I have little shell script that lets me interface with Arcanist (arc), part of the Phabricator toolset we use internally.…

Many people are unable to run a coding assistant LLM like Copilot or ChapGPT because of privacy concerns in a non-open codebase. This is true of our private WordPress.com codebase: we don’t want to be sending our secrets to OpenAI or Microsoft. But now, with the release of CodeLLaMa (and with a huge hat tip…

I tried to look at some React code I was writing lately, and for some reason the question “what was an underrated reason that React succeeded?” popped into my mind, along with the answer: Enough JS devs were already using some kind of JS compiler. Without JSX, React never takes off. (The irony is that…

hey buddy altwiebe.blog/@altwiebe.blog what’s up? Edit: does this edit work? The link above with the leading https did not.

Just gonna try mentioning my good friend @altwiebe.blog@altwiebe.blog, who seems to need the leading @ to mention?