B.T. Franklin
@btfranklin.info
software architect // applied AI technologist // computational creativity researcher // futurist // world traveler
https://btfranklin.info
https://btfranklin.info
I think too many people focus on whether or not a model can "one shot" a project. I understand the excitement of the idea, like "what could I get with just a single wish", but I believe approaching AI-driven development this way misses a ton of extremely useful capabilities. 1/x
January 20, 2026 at 12:32 AM
I think too many people focus on whether or not a model can "one shot" a project. I understand the excitement of the idea, like "what could I get with just a single wish", but I believe approaching AI-driven development this way misses a ton of extremely useful capabilities. 1/x
Reposted by B.T. Franklin
"enshittfying our potable water" truly is the enshittification of "enshittification"
January 18, 2026 at 6:42 PM
"enshittfying our potable water" truly is the enshittification of "enshittification"
I build a lot of stuff, and I want people to see it, but I just never have the instinct to post about it anywhere. I don't really know why. I'm going to start doing that, especially now that there's an AI community here. I just need to actually make a point of sharing what I build.
January 17, 2026 at 4:05 AM
I build a lot of stuff, and I want people to see it, but I just never have the instinct to post about it anywhere. I don't really know why. I'm going to start doing that, especially now that there's an AI community here. I just need to actually make a point of sharing what I build.
Reposted by B.T. Franklin
OpenAI aren't talking about it yet, but it turns out they've adopted Anthropic's brilliant "skills" mechanism in a big way
Skills are now live in both ChatGPT and their Codex CLI tool, I wrote up some detailed notes on how they work so far here: simonwillison.net/2025/Dec/12/...
Skills are now live in both ChatGPT and their Codex CLI tool, I wrote up some detailed notes on how they work so far here: simonwillison.net/2025/Dec/12/...
OpenAI are quietly adopting skills, now available in ChatGPT and Codex CLI
One of the things that most excited me about Anthropic’s new Skills mechanism back in October is how easy it looked for other platforms to implement. A skill is just …
simonwillison.net
December 12, 2025 at 11:32 PM
OpenAI aren't talking about it yet, but it turns out they've adopted Anthropic's brilliant "skills" mechanism in a big way
Skills are now live in both ChatGPT and their Codex CLI tool, I wrote up some detailed notes on how they work so far here: simonwillison.net/2025/Dec/12/...
Skills are now live in both ChatGPT and their Codex CLI tool, I wrote up some detailed notes on how they work so far here: simonwillison.net/2025/Dec/12/...
Possibly medium-temperature post: I'm a child of the 80's. There are certain films that were "core" to that identity. One of those was Flashdance, which I had never actually seen. We've all seen clips. We've all seen "Maniac".
So I finally watched it. It's bad. It's terrible. Not a good film.
So I finally watched it. It's bad. It's terrible. Not a good film.
December 2, 2025 at 12:41 AM
Possibly medium-temperature post: I'm a child of the 80's. There are certain films that were "core" to that identity. One of those was Flashdance, which I had never actually seen. We've all seen clips. We've all seen "Maniac".
So I finally watched it. It's bad. It's terrible. Not a good film.
So I finally watched it. It's bad. It's terrible. Not a good film.
Reposted by B.T. Franklin
A series of Opus 4 self-portraits, from a conversation with itself
September 23, 2025 at 10:22 PM
A series of Opus 4 self-portraits, from a conversation with itself