Stay curious. Fan of science and design.

Joined May 2007
164 Photos and videos
Yikes. I need to rethink this: "The generated chain has 61 model workers plus the collector, still under the 64 dynamic jobs allowed from this source job. I’m submitting it now and will poll until the collector completes."
6
Ok, it's Friday. Musssssst... put... thisssss ... down....ahhh. Happy weekend!
1
21
tool tip: I am very satisfied having switched to keep.md for having e-mail newsletters, GitHub ⭐️'s, Twitter bookmarks, RSS feeds, and read-later bookmarks from mobile&browser all in one inbox for followup or wiring into automation (MCP, API, CLI). keep.md
2
73
Using AI models to surface potential improvements for *your particular code and product* along the dimensions that are important to you is a fun way to find things you might otherwise miss. 🧵
1
1
30
Below, a rough visual ranking from an experiment I ran requesting 6 different models to look through a code base and brainstorm along dimensions I wanted to focus on. Aside: even Opus 4.8 agreed with me that gpt-5.5 did the best job LOL. 🤣
1
41
What do you see when you look at these latest model rankings from artificialanalysis.ai ?
19
WWDC2026 keynote: Hey developers, we're not going to say [wink] why we're so focused on your mobile apps being resizable [wink], but check out this origami (literally folding paper) example app [wink]. A folding phone coming soon? waaaaaaaat? Where would you get that idea?
24
Playing around with small LLM's that run entirely local, in a user's web browser, seeded with context of my site.
1
33
Come on... please!
19
WWDC keynote day! Prepare for an onslaught of new API's that LLM's have no training or clue how to code for . . . lol. Might have to write some code yourself -- gasp 😮 Nah, they'll probably ship LLM consumable skills/examples (?)
33
A fun thing you can leverage AI for is learning about and tuning your own harness and habits with long running experiments using data or derivable data that _only you have_. 🧵
1
24
I'll definitely be adjusting my default when working on this particular codebase.
1
8
Of course what works for you will depend on your codebase, your models, and your context/tools tuning, so YOU SHOULD RUN YOUR OWN experiments like this!
7
Playing around with some 'personal software'... a rust based TUI built on top of the keep.md API, for reading and sorting through everything I have it collecting . . . thanks for providing the API @iannuttall !
1
173
Open sourcing this (MIT) here: github.com/mattorb/sift
6