Hacker News new | past | comments | ask | show | jobs | submit | jonator's comments login

I've done the same, but with AI generating a lot of the boilerplate, and helping generate automated tests, has accelerated this process considerably.

Like for a dev server? Are you using a file watcher? I also find a test watcher helpful to increase confidence in the agents changes.

Recently, the cursor agent panel supports multiple tabs and sometimes I use that to kick off multiple non conflicting agents. You may prefer a separate window. Further, to avoid file conflicts completely, you could use a git work tree.


Yes a dev server. I can use a file watcher and on the JS side do the automatic page refresh there too, but was curious about local options. I haven't tried Cursor.

I'm assuming you're using FLAME?

How do you protect the host Elixir app from the agent shell, runtime, etc


Not using FLAME in this case. The agent runs entirely separately from your apps/IDE/compute. It communicates with and drives your runtime over phoenix channels

Oh interesting. So how do messages come from the container? Is there a host elixir app that is running the agent env? How does that work?

Yes, elixir app deployed across the planet as a single elixir cluster. We spawn the agents (GenServer's), globally register them, and then the end-user LiveView chat communicates with the agent with regular elixir messages, and the IDE is a phoenix channels client that communicates with and is driven by the agent.

Exactly. And as more software is written, the demand and possible set of softwares increase.

It's really a matter of positive sum/growth mindset vs scarcity/status quo mindset.


Maybe, but it's zero sum to the people with money. We saw wage growth in the lowest end during the Biden admin and it drove the bosses insane.

You can think of it as just automating the boring tedious stuff so us humans can focus on the harder problems like strategy, direction, design, GTM, etc.

The days are numbered where humans are sitting typing out code themselves.

It's akin to the numbered days of type writer secretaries of the 20th century.


I know what stories workers in the industry are using to cope with working with capitalists that have explicit goals of eliminating workers.

I'm sure your poor understanding of the history of improved tooling, like "type writer secretaries", will be a soft comfort in the future.


And you don't think capitalism is the reason we have these computer jobs to automate away in the first place?

No, because I’ve read a history book.

I believe it will raise the standard of what is valuable. Now that LLMs can now handle what we consider "mundane" parts of building a project (boilerplate), humans can dedicate focused efforts to the higher impact areas of innovation and problem solving. As LLMs get better, this bar simply continues to rise.


We can slightly squeeze more juice out of them with larger projects by providing better context, docs, examples of what we want, background knowledge, etc.

Like people, LLMs don't know what they don't know (about your project).


I think will will increasingly be orchestrators. Like at a symphony. Previously, most humans were required to be on the floor playing the individual instruments, but now, with AI, everyone can be their own composer.


Does it have an MCP server?


definitely want to get there soon, right now the most requested related features are apple shortcuts. Hopefully with the growing MCP ecosystem it will be a sweet MCP setup as we don't need a server or a node process.


Consider applying for YC's Fall 2025 batch! Applications are open till Aug 4

Guidelines | FAQ | Lists | API | Security | Legal | Apply to YC | Contact

Search: