Nick Noble

@NotionHQ the merge of nocode and yescode is almost complete

Now in beta: Notion as code. Define an entire workspace in TypeScript: teamspaces, databases, custom agents, all of it… then deploy it through the API. Build workspaces with coding agents, version-control your setup in git, and reproduce the same setup anywhere you need it.

.@optemization @temnco and I have been talking about this almost as long as we’ve known each other, and even built multiple approaches over the years. Nice to see a first party implementation finally!! Congrats on the launch!

None of the work trackers (Jira, Linear..) have a concept of underwriting. Take any ticket and try to answer: What budget / capacity is this coming out of? Who authorized spending time on this instead of something else? This is a hugely first-class piece of info, ontology-wise.

Unresolved thought I want one of you to write more deeply about: I think creating internal memes is an important company activity. They have a positive relational effect and can be useful shorthand, amongst many other benefits.

PMs? you mean backward deployed engineers?

I often hear from early startups that they need a freelancer or founding designer to help define themselves. I’d love to help make those connections. If you’re a freelancer, small studio, or open to an interesting founding design role, DM me and I’ll share roles as they come up!

Has claude gotten sharply worse in the past day for anyone else? Feels like opus is now sonnet and fable is now opus, but like not even as good.

@pallavi_benawri Have you tried @Horse_Browser ?

Link hoarder that I am, I have tons of background tabs open about tech, design, decor and cool products I find. Organizing them all on a mind map in hopes of keeping track 🔎

The vibe I bring to the function

THAT is great animation holy moly

Every programmer should write their own agent. It's fun, only takes 50 lines of code, and will surprise you. But to get the most from the experience, do these two things. First, hand-code it from scratch. Start with a blank text file and type out every line of code yourself; don't use any AI, not even autocomplete. Second, rely only on your language's standard library docs and the docs for Anthropic's API (or whatever model you're using). You can easily prompt Claude to do this for you. But the value of building your own agent by hand is that it helps you build a strong mental model of how they work, not just in broad strokes ("they're just an LLM in a loop with tool calls") but in the nitty gritty details. By doing everything manually you can make sure you don't accidentally gloss over important bits you don't understand yet, and you can experience directly how quickly new behavior emerges. For instance, my first agent had a single tool for adding two numbers. But that was enough for it to do multiplication by repeatedly invoking the tool. Once you get something working, there are dozens of fun things to try: add a second tool (perhaps `bash`? Make sure to do this in a sandbox), swap out the model (what's the worst model you can use and still get good results?), or make a simple memory system.

@nicholasbs @just_be_dev !!!

@just_be_dev New site + video about RC!

Excited for tomorrow.

@pketh 🎉 !

A little “in the hospital waiting for my wife to give birth” kind of feature

I’ve tasted this a few times and it’s great but there’s actually another level: a few awesome long term clients that let you work WHENEVER your brain gets “the juice” and give you really clear feedback (and HYPE) about what they want to do next.

Almost every single time I released something in my career, I see people saying: you are clueless. You don't understand the space. You don't know what I am doing. In the early days of the Turso Cloud, there was this guy here that would every now and they remark that "Turso keeps building the wrong thing", always followed by an explanation of what SQLite *IS*, what is good at, what is not good at, how people use it, etc. Turso now has almost one signup every 5 minutes, and 700,000 databases were created in our cloud this week. On the rewrite of SQLite itself, the common accusation was that we didn't understand that people use SQLite because of its reliability, and any rewrite would fail because it had no access to their test suite. We took Turso out of beta last week and power many production users already. Before that, it was Scylla, a rewrite of Cassandra. We were roasted by many, who said that we were morons who didn't understand that Cassandra was I/O bound, so any improvements in the CPU architecture were pointless. Scylla was 10x faster than Cassandra in real life. My first experience of that was when at Red Hat we patched QEMU to be the virtualization layer for the device abstraction for the KVM Hypervisor. I was 19 at the time, and being part of the team I submitted a talk to a local conference, who rejected me saying that QEMU was an emulator, and I didn't even seen to understand the different between virtualization and emulation if I was conflating the two. The common thread in all of those is always the same: people getting dead set in their ways, always looking at the world as it is, completely unable to understand that if you just tweak things, most things can be very adaptable. Things can reach new heights. They can be used in different ways.

@nickgeracehacks One for humans, one for monsters 🦞?

They call me Geralt of Slopia the way I travel with two laptops

@benbarry @johnpalmer @areatechnology_ Well put!

@nickisnoble @johnpalmer @areatechnology_ If that is true, then that means they couldn't sell it, which means that they failed at the hardest part of the job IMO. We all have killed work we love, that doesn't mean you should share it publicly. Save it for the right application.

@benbarry @johnpalmer @areatechnology_ has done work in the past for OpenAI, it's possible this *is* client work for a "real" entity — client just went in a different direction. area.tech/openai

@johnpalmer Experiments are totally fine, but don't think they should be presented as work for a real entity. Let them be their own thing. Students and very recent graduates get a pass, but otherwise I think this is amateur behavior.

IMO, designers posting speculative work are just broadcasting that they are bad at their jobs. The hardest part of the job is not making work that looks cool, it's convincing the client that your vision is the correct one.

@DanHollick @suhailrazzak Not a bug, fair enough! I'll stick to reader mode.

@nickisnoble @suhailrazzak I won't fix that.

Have you ever wanted to make your own font? Well I've written something that will hopefully dissuade you from that idea. makingsoftware.com/chapters/how-t… It's free to read for the next 48hrs. Enjoy.