Shawn Simister retweeted
happy birthday to skills, they turn 1 today 🎂
feels like a lot more
Shawn Simister retweeted
More DAGs should be drawn this way. In a pipeline like the one below, the nodes form a list, so each node can be a table row with metadata beside it.
Parallel branches are the main limit, but horizontal space is cheap!
Shawn Simister retweeted
we need ways to make it clear what is…
- explicitly specified
- hinted at
- an agent assumption
any amount of the above is fine, but once code is in the codebase there’s no way to tease out what’s what
we've mostly gotten past the slop issue in this new world of working together with AI
the next problem is people keep accidentally undoing functionality
this is happening because everyone is more in everyone else's business. hit an issue? fix it right away without nagging anyone
the problem is it's unclear how intentional the current behavior is and what absolutely should not be rolled back
you can say tests should be this. but they don't capture the fact that you discarded seemingly valid solutions 1-4 and settled on 5. someone later (an agent) might thing "oh 3 is simpler"
any additional document also doesn't feel like it solves the problem because it's yet another thing that can drift
where is the source of truth for how your software is supposed to work?
Shawn Simister retweeted
an early experiment for Live Ink, a new feature coming to Vignette. annotate anything, anywhere -- and your agents can do the same.
obviously need to incorporate voice input, too. i mean come on.
i frequently use the MacOS screenshot and annotation tools with my agents. this works well enough. the built-in annotations are a huge pain, though. very clunky.
i've tried other tools in the space and they're usually feature bloated and aren't tailored to my particular needs.
so, as one does nowadays, i built my own tool, Vignette. my goal was to keep the best parts of Apple's native tools, while enhancing and streamlining them for modern agent workflows.
it's free, open source, and very customizable. oh, and agents can send you their own annotated screenshots. this has unlocked some surprisingly effective collaborative moments! more to come here.
vignette.pete.design
Shawn Simister retweeted
We built a nice free tool at @k_dense_ai on top of Jev from @typesafeai called Citation Telephone which follows a cited claim back through the papers it cites, reads each one, and shows where the claim came from and what changed on the way.
k-dense.ai/blog/introducing-…
Shawn Simister retweeted
recommended reading, though i still disagree, as explained on @syntaxfm early this year.
for code, both memory and docs are not efficient. your codebase is all you need. make it modular, make modules small, at most, have a little maintained map of where what is.
liao.gg/blog/agents-dont-nee…
Shawn Simister retweeted
For years, maybe a decade, I've wanted to build a writing tool that just did a few things I couldn't find anywhere else.
A system that mimicked how I think when I write. A system that provided clear affordances, features, and places to do the things I wanted to do. A way to play with my writing as I'm writing it. A way to settle into just the right way to say something.
It never made sense to make it a 37signals product because it's not commercially viable, nor would it be worth pulling people off their other work to hack on this. Plus, it would have taken months the old way.
So this weekend I just made it myself, with Claude's help.
It's called Write_On and the short video walks you through it.
Essentially it's "alternative control" at the word, sentence, and paragraph level, plus a way to dim stuff back, and stash stuff near by. Not version control, but alternative control. You'll see what I mean when you watch the video below.
So here it is. Write_On.
Shawn Simister retweeted
Why can some people manage multiple coding agents while others can only manage one at a time? Led by @taolongg we worked on understanding this and piloting solutions to bridge the gap arxiv.org/abs/2609.33113
Shawn Simister retweeted
you know where in-the-moment, "system 1" type ai decision-making could be cool? music technology.
jevseq is a demented multiplayer drum sequencer. you paint the world, jev walks it in real time, and tries its hardest to hit a snare on 2 and 4.
Shawn Simister retweeted
efficiency, productivity, speed
we keep worshipping these words like they are what we live for
ship faster
merge more
manage more agents
compress every loop
remove every pause
turn every hour into output
but what is the point of endless production if there is no time left to think deeply?
not react
not optimize
not summarize
not clear the queue
think
to sit with a question long enough that your real intention starts to appear
to find the purpose underneath the motion
to ask whether the thing being accelerated should exist at all
ai could be a new canvas
a way to make strange things
personal things
impossible things
tools, worlds, poems, games, interfaces, films, languages, rituals
things that let more people touch the shape of their own imagination
but instead, so much of it is becoming slop factories
more content
more funnels
more tickets
more fake work pretending to be value
you can merge 2000 prs
you can manage 500 agents
you can wake up to dashboards proving that the machine kept moving while you slept
but what is the point if you only sleep 5 hours a day?
what is the point if you stop talking to other humans?
stop learning about the past?
stop playing?
stop wandering?
stop being surprised?
what is the point if your whole life becomes optimizing the system that is consuming you?
speed is not meaning
scale is not wisdom
automation is not freedom if it only makes everyone run faster
and where are we running?
toward what?
a world where every person becomes a manager of machines, and every machine produces more things no one had the time to truly want?
the danger is not that ai makes us lazy
the danger is that ai makes us endlessly busy
that it gives us infinite production before we have found intention
infinite execution before we have developed taste
infinite motion before we have learned how to be still
maybe the real frontier is not more speed
maybe it is discernment
knowing what not to make
knowing when to stop
knowing when the most productive thing is to sleep, read history, call a friend, play with a cat, walk without tracking it, or stare at the ceiling until the false urgency dissolves
tools should give us more life
not turn life into a tool
if ai is going to matter, it should not just help us produce more
it should help us become more human
more imaginative
more free
otherwise, it’s the same old factory
just without humans
Shawn Simister retweeted
The code is now open source, and you don't need Jev early access to try it. It runs against a local Jev-compatible server too.
github.com/narphorium/nl-log…
Shawn Simister retweeted
In 1956, Cybernetics was renamed "AI" by logic programming experts. Now Trump wants to rename AI again. Let's revive the old name! Modern AI is about neural nets & deep learning, closer to Cybernetics than to 1956 AI. Plus, Cybernetics sounds better than Artificial Intelligence.
Shawn Simister retweeted
Jev is System One. Your code is the reliable System Two. This is the NEW WAY TO BUILD SOFTWARE. 🫶🏼
Shawn Simister retweeted
You can describe an AI function in English, compile it once, and run it with Wi-Fi off.
That’s what we’ve been building with ProgramAsWeights: small neural programs you can call like Python functions, locally on your own CPU.
Code and models are public:
programasweights.com
Shawn Simister retweeted
constrained decoding makes models dumber! (will do longer blog on this one day)
simple explanation:
- it works by removing probability from invalid tokens
- if EVER your model assigns ANY probability to invalid tokens, by definition, your model is confused
- simply removing the signs of confusion puts it more out of distribution
Shawn Simister retweeted
Finally have the Teenage Engineering (aka @jugendingenieur) EP-2350 MicFX working with my custom @work_louder agentic coding system I call MegaMicro; Now I talk to Claude and Codex through the MicFX. I had to put a tiny custom script on the handset to be able to intercept button pushes on the Mac side.
