the models love to add so much extra code for cases that will never happen
one example is in review it 'caught':
"changing a setting while being demoted from admin in the same request" which no user would ever hit
but then they miss the obvious things that grind down your codebase quality over time
Linus Torvalds says, rules prohibiting AI usage are “UTTERLY STUPID” and “idiotic”.
For the Linux kernel, Torvalds says, “we’re not going to make stupid rules that say ‘you can’t use tools for X’”.
My favorite fix in the latest @conductor_build release:
> Fixed Conductor keeping Bluetooth headphones connected to your Mac after adding a model in Settings → Models → Loadout.
So excited to welcome Soffia and Caco to Conductor!
We first discovered the Faces team in our Discord. They are ideal early users - they loved Conductor but weren't afraid to tell us what wasn't working ;)
@SPLehman noticed their messages, DM'd them, we all got lunch, and the rest is history. I can't imagine the team without them now. All aboard!
Meta Wonder Full is confusing me. It’s an excellent personal assistant model, significantly ahead of Opus or Astra. But when coding, I don’t vibe with it. It feels like the model gets stuck when iterating.
I wonder if it needs different prompting than Opus to become more effective.
Introducing Anatomy
Describe a machine in one line. Claude brings it to life.
- Interactive isometric wireframes you can rotate, inspect and explore
- WebGL shaders for fire, water, plasma and more
- Real 3D motion, with individual parts that rotate and move
Install it as an agent skill. Fully open source.
I think the most important piece was to tell it to research the physics of those holo effects and generate shaders that emulate the different layers of real holo cards.
Other than that lots of visual references, both video and images, as well as my feedback on how it should look and feel.
Ever since I saw @jmtrivedi's holo shader, I've had this private benchmark task to have a model build a realistic holo effect for Yu-Gi-Oh! cards. Until now all models were absolutely crap at it. Opus 5.5 was the first model to produce something I was genuinely impressed by instead of a cheap rainbow shader. This isn't one-shot but it's built without any prior knowledge of how holo effects on cards work.
(And yes, Opus also produced the showcase video)
Rust no longer the defacto best language for agents
Compile times are too long, I'm always finding myself bottlenecked by time not intelligence
And the agents have gotten really at doing manual memory management now
convergence to the mean
when everyone looks at everyone else to decide what to make, we eventually stop making anything of our own.
we copy what works. borrow the language, the aesthetic, the features. we call it learning from the market, following best practices, staying competitive. together, everything starts to feel familiar. polished, interchangeable. nothing wrong. nothing alive.
the mean isn’t necessarily bad. it’s where everything lands when we remove the reasons for it to be different.
numbers are easier to compare than feelings, so we make things that produce numbers. we study what gets attention, then shape ourselves around it. eventually the feedback stops informing the work and starts authoring it. we’re no longer asking what we want to say. we’re asking what will be rewarded for saying.
ai makes this loop frictionless. it can draw from more references than we could see in a lifetime. but access to every perspective isn’t the same as having one. it hasn’t lived a particular life that makes one detail unbearable and another beautiful. when we ask it to choose for us without bringing any intention of our own, we get something plausible, easy to approve.
then we ship it, measure it, copy it, and feed it back into the next round. a tidal wave of mid.
this changes not just the work, but the people making it.
we describe ourselves in categories platforms can distribute and markets understand. designer. founder. creator. pick a niche. build a brand. be consistent. the parts that don’t fit become inconvenient, even when those contradictions might produce our most interesting work. we become easier to classify and harder to tell apart.
i think we need to approach making things more like artists.
an artist develops a perspective through the work. making, noticing, choosing, failing, returning. learning what matters even when nobody else cares. craft gives that perspective a form precise enough for someone else to experience.
the life outside the work matters too. the places you’ve lived, the people you’ve loved, the things you’re embarrassed to care about. these aren’t distractions from having something to say. they’re how you come to have something to say.
we understand this with music, paintings, photographs, movies. we expect a person to be present in the choices. we want to experience something we wouldn’t have encountered without them.
software can do this too.
a piece of software expresses beliefs about how life should feel. what deserves your attention. what you should be free to change. whether a task should feel like paperwork or play. even a small interaction can carry someone’s care, humor, or curiosity.
but we rarely talk about software as a medium. we talk about it as an industry. markets to capture, workflows to optimize, competitors to catch up with. we add a feature because someone else has it, without asking whether it belongs. products accumulate the same parts and lose what made them worth choosing.
underneath the branding, it’s all the same thing.
artists learn from others too. the question is whether you’re absorbing those influences into a point of view, or using them to avoid developing one.
what are you trying to let someone feel, understand, or do? why this particular shape? what have you noticed that the existing tools don’t seem to notice?
those questions don’t have answers you can borrow from a competitor’s roadmap.
if we can make almost anything, deciding what deserves to exist becomes more important, not less. speed gives us more chances to exercise judgment. it doesn’t remove the responsibility.
i don’t want a world where every person becomes a more efficient distributor of the same ideas. i want people to use these tools to go further into what they actually care about. to make things specific enough that we can feel someone behind them.
what is the point of everyone being able to make something, if we all end up making the same thing?
@kareemoncall No worries. The TestFlight app should be treated more like a beta which can include bugs. The AppStore version should be much more stable.
If you encounter any issues or have feedback please reach out though. We are always looking to improve things!