jbdamask
Joined 11 months ago
Karma
152
Submissions
106
Member since
Nov 28
Learner / Builder.
Went back to building after years as an exec.
View on Hacker NewsRecent submissions
Comment · 12 days ago
I'm running an experiment with a team of Claude agents to build a decision support app for biotech investors. Regardless of the results, the agents simply do too much for me to monitor what's going on. Standard updates to Slack are ok but that format lends itself to short-and-sweet posts.
Podcasts turn out to be a pretty good way to keep track of progress. At the end of a unit of work, the agent writes a script from the agent chat history (including my interjections) and generates the audio with voices from Eleven Labs.
A funny example came from an episode where I learned about the team's plan to run a large test suite. Instead of going through my Claude plan the team thought it was a good idea to use API calls. Estimated cost: $730.
I didn't get banned but you can imagine my mature, productive response when I hopped into the chat to stop the test.
Comment · 1 month ago
Really fun model! Thanks for opening up access as quickly as you are.
Comment · 1 month ago
Appreciate you trying it and commenting. And I'm sorry that you hit this bug on first contact. My goal is to have a dead-simple UX, not waste your time trying to get it working. Heck, the whole point of Rocky Surf is convenience.
I've filed this as a bug.
Per your comment about the documentation - I agree that the docs aren't great for humans. In fact, they're meant to be read by agents, not humans. But I don't make this clear anywhere.
During this build, my development agents were instructed to be verbose with documentation. I find that this improves code quality and architectural consistency across multiple agent sessions - Rocky Surf was built over hundreds of agent sessions. The trade-off is that there's too much for humans to read.
As I got closer to release, I read, edited, and pruned a considerable amount of verbiage, but stopped short of making concise docs a release requirement. But the fact that you noticed that a particular doc was 40 pages tells me that I didn't value your time as much as I should have. Duly noted.
Development and new releases will continue since I use Rocky Surf all the time. In fact, I recently found that it pairs nicely with Herdr https://x.com/jbdamask/status/2099110104037494963?s=20
Thanks again for trying it and commenting. You didn't have to give me feedback but you did, and that's really nice.
Comment · 2 months ago
An associated plugin, https://github.com/jbdamask/modern-software-engineering-in-a..., is available to audit codebases against the principles.
I find the perspective is a useful complement to standard code reviews.
Comment · 2 months ago
pfft...I'm way past understanding
Comment · 2 months ago
Not sure why this is surprising. Language is a communication protocol
Comment · 2 months ago
Enterprises need a solution like Lovable or Replit if only for the one-touch deployments. Unfortunately, neither tool is there.
I don't know what's taking Anthropic, OpenAI, Google, Microsoft, even AWS to build deployments themselves. There are only a handful of reference architectures for vibe-coded apps.
Comment · 2 months ago
I use AI explainers a lot in my own projects and have skills that give outputs I like. I'll even pipe the output into NotebookLM to make a video sometimes. This is actually a decent way to grok complex subsystems (YMMV).
What I don't care for is the pretty-yet-verbose HTML outputs that I see from some teams. They can be way too long and it's often the case that the engineer who made it didn't read the whole thing.