best opportunity you get this year to suck less at ai
i'm dead serious, this isn't hyperbole. do it.
this is world-class signal straight from the field
(and it's free)
these people are all amazing at what they do
some of them have been invaluable in my leveling up.
can't be grateful enough for all the amazing work that they share
joined! 🤝 starts in 5 days
and maybe we can run nice demos directly in solveit! : )
Building AI products is hard. But it's getting increasingly popular!
I'm really excited to share that my friends and I are putting together (the best) lecture series on AI Product Engineering this summer!! We've got an awesome lineup of talks spanning data, evals, and UX. With more to come.
The lecture series is completely free! And ~2k people have signed up already even though we haven't posted on social media yet! I can't wait. Join us and sign up: https://t.co/5DWcm4va5m
We live in a weird time of overhyping slop that will be forgotten about in weeks. Linux and Python are both from 1991. LLVM started as research project in 2000.
We want to build the foundations of silicon life. Software that lives for 50 years. There's time to make it perfect.
@yacineMTB laziness to do the simplest things
"we could <use variables> but let's hardcode for now"
mf it's not harder for you to gen things correctly you're a synth
anthropomorphizing RL is wrong, slippery slop.
and now out of control
(ensures future bills to fix what it does wrong tho)
been saying it for decades:
everyone should have a home server to perform whatever their needs are
now it includes GPUs for AI
(+ 3D/video processing for gaming etc.)
it's a neat way to get great private performance while thinning clients footprint (heat/noise & total bill).
Today marks the beginning of our launch calendar and to celebrate i am making ncode and our flagship kimi k2.7 model free to use for the next week (or until the traffic knocks us out). all you need to do is:
1) sign up for a noumena account at https://t.co/bJmg9QPGUH
2) go to https://t.co/2wBMNAS3mL and clone and build noumena code (ncode)
3) login to the platform with `ncode auth login` (or /login once you are in the app)
4) enjoy blazing fast tokens on the noumena platform with ncode
so honestly not tomorrow because my plate is full
but equally honestly i'm deeply interested by the project because that's on my radar
i want my whole environment / ecosystem on full p2p able to do any:any node, cmd, whatever. that it feels like one PC, one namespace.
so will definitely check it out once i reach that part of the stack i'm building!
exactly, it exists, it's doable and can be done well
now imagine
you're on a web page, some cool thing, wanna share
Press ` to open term in this dir.
> share . x -m "should i?"
New post on X
with link to this page
and your message
Then another to your gh repo
> share --md . github•com/myuser/myrepo/filename.md
When you come back to page:
> status # stdout below
- 3 replies (x•com)
- 1 issue (myuser/myrepo)
- 2 PR (myuser/myrepo)
Your cart is empty.
> … # now check replies etc.
> buy # alternatively, "cart"
👉 Are you sure you want to buy {product} for $12.34? [y/N] y
✅ Payment complete!
Estimated delivery: tomorrow before 4 pm.
More info: status
> status --store-only > cat ~/track/{product}.md
I want that. And it would be so easy to then pipe and compose many services to create flows, cool UX. It just needs a plain text stdio!
> Those standards are different.
I'm also exploring new codebase structures and conventions for AI. I find it's a lot of little things.
For instance,
I often run a glossary-style "sig.md" file that shows all public signatures in simple structured md reproducing the fs (with docstrings, additional notes, maybe LOC#, etc). Helps with modularity, orientation, arch, structure, expectations/contracts ("this input gives you that output" is often all you need to know, any more is noise).
Yes, you can use tools like ast, tree, some doc lib, etc., but that's indirection and as many failure points.
A simple text file seems often better; ideally containing nothing else than some pre-computed + processed output of said tools, the point being to ensure *some determinism* by removing the 'agentic' step of choosing what to run. So whatever the agent "often does", I try to make more robust in some way.
This basic sig.md may save like 90-95% of additional context for most orientation. More importantly, it lets the AI (and me) reason about the code from the arch/design standpoint much more cleanly, less noise.
It's really just a tiny example to drive my point.
The more I use AI, the more I discover many such tiny "tricks", which have disproportionate effects for the very little effort they require.
And in the end it seems to paint not alien but certainly different repo structs, with new expectations. For instance, for many things that would have been libs/mods yesterday, now I may do APIs for easy and standard interop/consumption by AI and other pieces, while decoupling codebases more granularly; so interfaces are less often in-app, I shift modularity to the network/HTTP level.
Apps become smaller, more KISS (helps a lot with AI context). I often say I'm moving "from apps to caps", where the control plane (as in MVC) is more about composing capabilities than building some complete UX for each app. Feels more like a giant terminal and piping, very flexible/ad hoc. Agents love to leverage such envs I think.
New "shapes" emerging, as Codex loves to say. A much flatter and wider buffet of simpler modules, much less vertical/monolithic complexity.
I must admit this fits my taste, so perhaps I'm biased and others are doing great with completely opposite principles!
But the point stands: I'm building differently, with AI a first citizen from day 1, and humans able to leverage it to great UX. It's a long journey with many stops, but I think that space is where the core paradigm shift of making software will happen. Structure, expectations, how we think about interop and modularity, how not just an API but a whole environment/world usage & options can be self-documenting, plainly obvious just by observing it.
in my exp, once you set it up, the headscale server is silent infra.
to add a new node, it's relatively easy to script onboarding with a new temporary key, so that can become a one-liner essentially (useful for containers etc; if you network is relatively static, you forget headscale even exists).
i'll try netbird but headscale properly setup is a set-it-and-forget-it essentially already : )
exactly, it exists, it's doable and can be done well
now imagine
you're on a web page, some cool thing, wanna share
Press ` to open term in this dir.
> share . x -m "should i?"
New post on X
with link to this page
and your message
Then another to your gh repo
> share --md . github•com/myuser/myrepo/filename.md
When you come back to page:
> status # stdout below
- 3 replies (x•com)
- 1 issue (myuser/myrepo)
- 2 PR (myuser/myrepo)
Your cart is empty.
> … # now check replies etc.
> buy # alternatively, "cart"
👉 Are you sure you want to buy {product} for $12.34? [y/N] y
✅ Payment complete!
Estimated delivery: tomorrow before 4 pm.
More info: status
> status --store-only > cat ~/track/{product}.md
I want that. And it would be so easy to then pipe and compose many services to create flows, cool UX. It just needs a plain text stdio!
Artificial Analysis just added GLM 5.2 to their open vs closed frontier timeline, here's a flipped version which gives the lag time of OSS perf on their intelligence index
@luckeyfaraday@jonathan_wilke the best GUI app are fully controllable by keyboard, btw
there is no reason why we couldn't at least try to support great UX outside the terminal
we could even add a term-like interface to our web apps if we so chose
in GUI and even via ssh
it's so weird that's not like std
You're talking about consumers
Developers never left the terminal
For anyone who actually builds things, the terminal has always been the superior interface
Faster, more composable, ssh, no mouse
CLI coding tools aren't a regression, they're just giving power users the interface they wanted