@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)
English
David Mosher 🇨🇦
17.7K posts
David Mosher 🇨🇦
@dmosher
CSS, SQL, and everything in between.
Ottawa, Canada Katılım Nisan 2007
893 Takip Edilen2.1K Takipçiler
@dmosher @badlogicgames @nonsens3 @mikker 1009 is especially annoying because that's just message too big. That implies we might have to fall back to SSE.
English
pi.dev's been supporting OpenAI's WebSockets mode since March. /settings > transport. the difference between SSE and WS for e.g. Spark is not that stark in terms of tokens/sec.
the real speed up actually comes from caching context OpenAI side, and only sending deltas as the context grows.
pi currently does not implement the latter. hmmmmmm
OpenAI Developers@OpenAIDevs
⚙️ We made agent loops faster with WebSockets in the Responses API As Codex got faster, the bottleneck moved from inference to inefficient API calls WebSockets keep response state warm across tool calls, helping workflows run up to 40% faster end to end openai.com/index/speeding…
English
@badlogicgames @nonsens3 @mikker @mitsuhiko had to manually swap back to sse today with pi + codex, I was getting 'Error: WebSocket closed 1009' repeatedly
English
@nonsens3 @mikker i've been on websockets since forever and not seen it once :/ @mitsuhiko said he wants to impl retries for websocket mode. we'll see if that fixes it.
English
David Mosher 🇨🇦 retweetledi
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. link.testdouble.com/ecfcc5
English
📜 "The Story of Mel" — a 1983 Usenet post resurfaces via @garybernhardt (worth a follow). Somehow more relevant than ever → catb.org/jargon/html/st…
English
A few links that made it onto my reading list this weekend 👇
🔧 LazyPi — opinionated `pi` setup with themes, subagents, memory, ralph loop, and more → lazypi.org
English
🔑 "Some Secret Management Belongs in Your HTTP Proxy" — from exe.dev (VMs + sandboxes for agents). Useful framing if you're thinking about secrets in agentic stacks → blog.exe.dev/http-proxy-sec…
English
📄 "How We Made Our Docs Test Themselves" — LangChain's take on evergreen docs in agentic codebases. Tactical and practical → langchain.com/blog/our-docs-…
English
💻 WTerm — web terminal emulator built in Zig, compiled to WASM; gaining traction for quick e2e testing of TUI features → github.com/vercel-labs/wt…
English
David Mosher 🇨🇦 retweetledi
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
English
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👌🏻
English
David Mosher 🇨🇦 retweetledi
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
Matt Pocock@mattpocockuk
I'm starting to think that DDD might be the answer to all of my problems - Model not doing what you want? Shared language - Can't navigate a massive codebase? Bounded contexts with global mapping - Don't know why a decision was made? ADR's It's just so freaking elegant
English
This tracks. I like to call it DDD: the good parts.
Matt Pocock@mattpocockuk
I'm starting to think that DDD might be the answer to all of my problems - Model not doing what you want? Shared language - Can't navigate a massive codebase? Bounded contexts with global mapping - Don't know why a decision was made? ADR's It's just so freaking elegant
English
David Mosher 🇨🇦 retweetledi
'Improve the way you prompt the agent'
I've started to consider this advice a bit of a red flag
'Commanding' the agent isn't the right approach. Instead, collaborate with it. Talk to it. Reach consensus together.
/grill-me is great for this.
English
David Mosher 🇨🇦 retweetledi
Here is a little experiment: an interactive pi tutorial. Make an empty folder, then run this:
pi -e git:github.com/earendil-works…
And give feedback! Reason: pi works best if you have an onboarding buddy. But if you don't have one, maybe pi can be one for you?
English
David Mosher 🇨🇦 retweetledi
After @aiDotEngineer, which was full of useful criticism, I remembered that the most confident takes on AI often came from the least exposure. Rejection is easy, trial and error is expensive. I wrote about it. lucumr.pocoo.org/2026/4/11/the-…
English
David Mosher 🇨🇦 retweetledi
recommended viewing. one more time, on it's own. this is probably yhe most practical talk on using coding agents i've watched to date. watch it. by @lucasmeijer
it's also a great demo of pi and captures exactly why i built it.
youtu.be/fdbXNWkpPMY?si…
YouTube
English
@jescalan I had similar challenges this weekend. Only 2 out of 20 planned tasks, but it was weird to have to prompt it a bit harder.
English
Transition to gpt in openclaw not going so great this far 😂
English
Don't let the bitterness of where we might end up rob you of the sweetness that comes from growing, learning, and shipping--especially things that don't scale.
English
There is a certain emotional nihilism in the Bitter Lesson if you take it at face value.
But if we stop pursuing excellence today on the off chance a machine might do it better tomorrow, we end up paying the price of obsolescence twice.
English
The last three weekends I have just built things. It's all I want to do. Software is so much more fun with AI. 🚀
English