David Mosher 🇨🇦

CSS, SQL, and everything in between.

[David Mosher 🇨🇦 @dmosher]

@mattpocockuk /medium-rare

[David Mosher 🇨🇦 @dmosher]

Use Pi + GPT, think hard before prompting, single-thread your work and focus on simplifying.

[Gergely Orosz @GergelyOrosz]

So, at your company, what are you doing about the spiking token prices?

Approaches I hear:

1. Inference routing - route more basic workloads to a LOT cheaper APIs or providers

2. Use cheaper open models for inference (eg Fireworks, Baseten etc)

3. Default model: cheap one

[David Mosher 🇨🇦 @dmosher]

@garybernhardt Still rocking the EDM personally, it works whether I'm coding or the agent is 😎

[David Mosher 🇨🇦 @dmosher]

Going on 2 months now. Pi and a Codex subscription is fantastic.

[Uncle Bob Martin @unclebobmartin]

I just cancelled my Claude account. I've been using codex, and haven't used Claude in several weeks.

[David Mosher 🇨🇦 @dmosher]

Getting back into the habit of uploading. Here's a weird little house track on the Syntakt.

https://t.co/bv1Py3Vcof

[David Mosher 🇨🇦 @dmosher]

Another way to stand out is to go in the opposite direction: Maximum UI, brutalist designs, high-friction surfaces, bespoke UI for everything.

Interfaces that feel like architecture instead of a series of templates.

[David Mosher 🇨🇦 @dmosher]

Perhaps the commodification of UI design will be the thing that leads to it being made obsolete.

If everything that is designed begins to look the same with agents trending towards the mean, then it stands to reason that one way to stand out is to have the opposite: no UI.

[Matt Pocock @mattpocockuk]

The more I replace plans with prototypes, the better the outputs

Who'd have thought that low fidelity prototypes were better than walls of spec

Oh yeah, the entire industry for 20 years

Stop going against decades of knowledge because someone in SF shipped it as a 'mode'

[Mitchell Hashimoto @mitchellh]

AI slop is good, actually. Slop is what enables fast parallel experimentation. The etiquette and skill is understanding the boundaries of where slop exists and the extent to which it should be cleaned up and how.

A few examples:

I’m working on the internals of some system right now. The API and GUI of this thing is fully zero shame slop. It’s horrible. But it lets me focus on the core quality while shipping a usable piece of alpha quality software to testers (transparent about the slop frontend).

Similarly, this system has plugins. We sent agents in Ralph loops overnight to generate dozens of plugins. The plugins are slop. The quality is bad. The plugin API/SDK is absolutely not done.

But we can test a full GUI with a full plugin ecosystem. When we change the API, we can regenerate them all. The cost of change is just tokens, the velocity is incomparable to before.

I built Terraform. We tested and shipped TF 0.1 with about 3 very weak providers. Because we ran out of time. Building was slow. And when we changed our SDK the cost was immense. Totally different today, 10 years later. Today, I would’ve slop generated 100 providers (again, with transparency and cleanup later, but just to prove it out).

As an anti example, I would not PR this (without prior warning) to another project. I would not throw this onto customers without full review or transparency (as I’m already doing). I would not accept first pass slop. It’s almost never right.

Slop is a tool. And like anything else it’s not blanket bad or good. The context is everything.

[David Mosher 🇨🇦 @dmosher]

@mitsuhiko @badlogicgames @nonsens3 @mikker ah that makes sense, I was tagging in some screenshots on macOS which can get large (i think these were in the ~8mb range)

[David Mosher 🇨🇦 @dmosher]

@badlogicgames @nonsens3 @mikker @mitsuhiko had to manually swap back to sse today with pi + codex, I was getting 'Error: WebSocket closed 1009' repeatedly

[Test Double @testdouble]

AI changed the cost structure of software. Outputs may be cheap, but outcomes are still valuable. @dmosher says leverage has moved to the harness: lint rules, types, tests, ADRs, feedback loops. https://t.co/KabOBjRpfG

[David Mosher 🇨🇦 @dmosher]

📜 "The Story of Mel" — a 1983 Usenet post resurfaces via @garybernhardt (worth a follow). Somehow more relevant than ever → https://t.co/t2AunnPRaj

[David Mosher 🇨🇦 @dmosher]

A few links that made it onto my reading list this weekend 👇

🔧 LazyPi — opinionated `pi` setup with themes, subagents, memory, ralph loop, and more → https://t.co/opBhr6rRV2

[David Mosher 🇨🇦 @dmosher]

🔑 "Some Secret Management Belongs in Your HTTP Proxy" — from https://t.co/450KLHkOL6 (VMs + sandboxes for agents). Useful framing if you're thinking about secrets in agentic stacks → https://t.co/86ZXyD1feS

[David Mosher 🇨🇦 @dmosher]

📄 "How We Made Our Docs Test Themselves" — LangChain's take on evergreen docs in agentic codebases. Tactical and practical → https://t.co/ceIuvMVPgP

[David Mosher 🇨🇦 @dmosher]

💻 WTerm — web terminal emulator built in Zig, compiled to WASM; gaining traction for quick e2e testing of TUI features → https://t.co/VEUIMvOjjL

[Simon Willison @simonw]

Is there still a widespread belief that LLMs and coding agents are good for greenfield development but don't help for maintaining large existing codebases?

I don't think that idea holds up any more

[David Mosher 🇨🇦 @dmosher]

I'm still in the honeymoon phase and haven't yet used it in anger, but so far, @Railway is really good.

If they can sort out their platform stability woes as they scale, this feels like the new Heroku in terms of DX.

Just discovered the "simple dashboard" APM button and it's👌🏻

[Matt Pocock @mattpocockuk]

I don't want to go too deep on AI + DDD. My current thinking:

GOOD: Ubiquitous Language / Bounded Contexts / ADR's
BAD: Entities / Value Objects / Aggregates / Domain Events

Essentially, use DDD to document the app but don't prescribe the shape of the app