Maggie Appleton
@Mappletons
Staff Research Engineer at @GitHubNext. But actually a designer. Writes about design, dev, & anthropology.
Also on Bluesky 🦋 @maggieappleton.com
1.6K Following 44.1K Followers
GitHub Universe day one done!
If you’re here, come by tomorrow to chat to all the @GitHubNext folks at the Speakeasy section. We’re in white lab coats.
Also demoing some stuff in the final keynote.
Show more
New talk! About the divided human & agent worlds, boundary objects, and building thicker interfaces
I've been exploring how to improve "planning", aka. deciding what agents should build, how you want it built, & making the whole team part of that process
Show more
Jigs very good for tweaking design system values with live previews of how those colours work in the context of specific components and WCAG contrast calculators on screen.
So easy to say "show me every component that uses grey 400 and put it in the lab file" → tweak → commit
Show more
people arguing that AI won't get access to wet labs
Anthropic:
For people new to design jigs, this is a good example of using them in the wild.
I first saw them used by @doctorbaytas in this beautiful talk at @meetgranola:
added a little bit of spice to the bookmark animation, opus 5.5 btw
The current state of agent design skills
Had a wonderful chat with @GergelyOrosz - always nice to go deep on ideas in a proper long chat. Got to show off some notebook sketches and design jigs with agents too.
BREAKING
It has been 30 entire minutes since a frontier model dropped.
Experts confirm progress has officially stalled.
Tomorrow on the podcast - with one of the best design engineers I know!
@Mappletons current jev can be called a decision model, but I don't think the shape should be called that
it would be like calling InstructGPT a copywriting model
HINT HINT HINT
the only alternatives to system one I like:
- machine-native model
- large programmatic model
Show more
Can we agree to call Jev a "Decision Model"?
I feel like they buried this in the explainations and docs.
Language models output language. Decision models output decisions.
Messing around with @typesafeai Jev for real-time styling
🔤 🔜 🎨
If you can define a bounded, semantically meaningful property space, you can project a natural language expression into that space in one generation step
Show more
Jev is the future
After co-inventing ChatGPT, I kept asking myself: why have superhuman chat models not led to AGI?
I’ve spent the last 2 years in stealth building a new way to train models (RLCD), and a new type of frontier AI model that we are releasing today: Jev
• 20-200x faster
• 40-400x cheaper (w/ output tokens free)
• Frontier composable intelligence optimized for decisions
AFAICT the shortest path to AI-based economic revolution
Show more
Mondrian windows
