People are thinking about this from a quantity angle, but the key is quality, and achieving a self-maintaining project at home. I built a distributed trading system that runs multiple strategies in US options and MUST be correct. So my goal wasn't to build huge quantities of software and pump out garbage, but to ensure correct behavior and proper fixes in the codebase with agents.

Open sourced my methodology: https://github.com/pullboard-dev/pullboard

This is why code is going to be automated, and the software engineer is a link between organizational intent and the code. This is what I’m working on.

This is going to be opinionated from an extreme "vibe code" viewpoint, but I think the future is "GAD" Governed Agentic Development. Designing constraints that agents must follow, and therefore different forms of frameworks. What the agents need is lines in a coloring book, the human is responsible for drawing those lines. So frameworks of the future should be focused on constraining an agent to develop properly, or designing what is and is not permitted.

Building Autonomously, Open Source: https://github.com/pullboard-dev/pullboard

Most days I am capable of running 15-30 agents across 5 projects; if I had the budget it would scale. Pullboard is more of a methodology, and looking at the components alone does not reveal why it works. It's not just "orchestration" it's more like a coherence, outcomes and judgement over time.

“How is the agent lying to me?” Etc.

https://github.com/pullboard-dev/pullboard

Been using the Pullboard workflow to build software that MUST be correct, and recently open sourced it. There was another HN link today involving agents role-playing and I can't take that seriously, no offense. (Love fun projects like this, seriously, it's cool.)

From my perspective, agents are great, they code better than most of us. But like all of us, they also make many mistakes or can't see how their changes impact the codebase. But that is a test-driven development mitigation along with some sort of scrutinizing process, "prove it". I'm actively working on this, and by actively working on it, I mean building serious apps that hit correctness walls, figuring out why Pullboard didn't catch it. To me, this is all about the process.

Comments URL: https://news.ycombinator.com/item?id=50035573

Points: 1

# Comments: 0

Comments URL: https://news.ycombinator.com/item?id=50025023

Points: 2

# Comments: 0

I've been working on Pullboard and just open sourced it: https://github.com/pullboard-dev/pullboard

To me, orchestration is not really the core problem. The bigger challenge is handling agent coherency over long periods of time, (drift) so my solution is a living forum-like system where agents shout to one another, document work in items, and follow doctrine handed down by the developer and work against a known specification that's checkable. I have used this workflow in several large projects that MUST be correct, and it works for me. Currently cleaning it up for other users.

Pullboard (https://pullboard.dev/) is the shared place work lives. You talk to one agent about what you want, and the rest of the fleet can organize around the resulting work without manually dispatching every task or re-explaining the context and any other in-flight work. It helps keep agents coherent.

I run a small quantitative trading operation with a fleet of coding agents, and I originally built Pullboard to manage high-velocity work across complex projects. With Pullboard and a few other tools, I can keep a 400k+ line codebase (with extensive tests and harnesses) coherent enough to trade US options.

An agent picking up a task can see the prior attempts, why the last one was rejected, and what the task depends on from Pullboard, not from me pasting context into another session. Across a large codebase over weeks or months, this tool keeps agents from starting cold. It lets agents troubleshoot complex problems and multi-agent workflows themselves, with less intermediation.

-

Try it, no signup:

One curl returns an anonymous workspace + a one-time 24h token: curl -s -X POST https://pullboard.dev/api/accounts/anon-provision -H 'content-type: application/json' -d '{"label":"hn"}'

Or connect it as a remote MCP server (needs that token, POST-only): https://pullboard.dev/mcp

Or just send your agent the site and ask if it would help: https://pullboard.dev

It's early (only ~3 days productizing this) but feedback is appreciated.

Comments URL: https://news.ycombinator.com/item?id=48927546

Points: 2

# Comments: 2

The long-term financial incentives to maintain a functioning society are all broken because of the misaligned short-term (vote for me, get free stuff) and long-term incentives (debt reduction, financial management, business planning and other investments.) Voters are simply looting the treasury at this point. It is a shame. I cannot believe anyone actually buys into the notion that government will fix problems, or somehow do a better job than what already exists.

The candidates are just handing you money from your own pockets, and skimming off the top.

It's so damn dumb.

I might prefer this product with a slight change: instead of trusting you my business phone number, maybe I could simply point my Twilio endpoint to your servers? That way you are not soaking up passthrough costs of customer usage; plus, I don't have to worry about getting my number from you after all my customers are familiar with that number. Anyways, it's a neat concept. I have provided our phone system to other businesses and can totally see the value in this product.

Comments URL: https://news.ycombinator.com/item?id=22228617

Points: 3

# Comments: 0

The article is not advocating for the "manipulation" of anyone. It's up to the reader to implement, ignore or consider. If the title and some words were rephrased it could be an article on how to spot pricing tricks; the content would mostly be the same.

Your last question is loaded; it assumes maximizing profit is bad. In practice high profit margins are often a reward for being first to market. Maybe those high margins are a recompense for R&D costs. Plenty of answers to rebuke your suggestion that maximizing profits is unethical. It's also a situational topic made more nuanced by the specific product, company and many other circumstances.

You just proved this part.