cgarvis

I've seen some newer testing frameworks where you prompt for the outcome you want under a specific scenario. The first run is a LLM agent that figures out the steps but those steps are then used for recurring runs. If something fails, it goes back to the agent loop to see if it's an actual error.

This works well in e2e type tests where the test implementation might change but the customer experience hasn't.

So maybe there is a hybrid approach in our future.

This is the bet I'm making with Croft. LLMs to figure out the messy bits but once it's figured it, software is the better tool. Let the LLM write the software.

This is what software engineers do but just more expensive and time consuming.

MCP is for when your end user (the one driving an LLM Agent) is non technical. Most non technical people are not going to install a CLI on their computer. Most are not going to be driving the LLM agent via a terminal.

It also very helpful when you need auth. MCP OAuth with CIMD makes it easy instead of cumbersome process of generating API Keys.

If you are technical and already using CLIs, then MCP doesn't give you much.

Fly.io brings back some of that easy of deploy.

never knew you could do css selectors on custom elements! does seem like syntactical sugar over classes. I do like the current trend with tailwind: style with markup using smaller components. But maybe there is something here with so many components being just styles...

Are you doing got worktrees in the backend?

Reminds me of the three tribes of software programmers. https://josephg.com/blog/3-tribes/amp/

Mort == maker Elvis ==? hacker Einstein == poet

Dish outsources sales calls to a third party. This third party doesn’t have access to customer accounts so they have to send you to an actual Dish call center. Not as nefarious as you think but still frustrating.

ChatGPT has a Mac app. If you want to run your own models, Ollama with Chital is great.

https://github.com/sheshbabu/Chital

+1 for osmo

Recently read “Working in Public” where the author talks about how GitHub is to open source as the new feed was to Facebook/social networks

Smalltalk has a change file and an ability to be source controlled. My understand is that the source controlled output is not human friendly.

I’m currently building one by myself in Elixir/Phoenix/Liveview/Tailwind using Fly.io for deployment. Elixir has been amazing for more complicated app dev. A lot of previous ruby people there. Liveview gives a React like experience without the extra complexity. Tesla is great for building api integrations. Knock has a great elixir api for notifications and emails. Telemetry is built into most things. Livebook is Jupiter notebooks but better, great for quick prototyping or doing adhoc data analysis.

You can get most of this from just using https://legendaryframework.org/

Want native apps? LiveView Native is a thing https://native.live/. One app to do it all.

+1 Using it in a Elixir/Liveview app. Using phx_component_helper has made making those components really easy. https://phx-component-helpers-demo.onrender.com

Just looked into this with CheerpX. You need the CheerpX license (15k/yr) and Flash license (25-50k/yr).

Kinda feels like a JavaScript version of Elixir

Slight difference from stock phoenix but yes. Only area I’m not 100% on is auth. https://hexdocs.pm/phoenix_live_view/live-navigation.html