Comments URL: https://news.ycombinator.com/item?id=49248765

Points: 2

# Comments: 0

I think workflow builders are mostly the wrong mental model for AI. A graph of predefined nodes and edges is useful when you already know the exact sequence of work.... but the point of an AI agent is that it can decide what to do next from the current context.

IMHO reusable building blocks still matter enormously. You should not have to recreate an integration, a capability, or a piece of reliable deterministic logic every time. It is wasteful and you cannot oneshot it. Even with coding agents which we use all the time system to system connectivity is more complex than writing the code. But those should be available to the agent as tools, mechanics, and features that are not wired together as a visual workflow of sorts.

A product can look graph-like at a glance though, while avoiding making a workflow builder. I think this still matters in order to put a mental model around it. But the mechanism should not be graph / workflow like in practice.

I wonder what will happen. I think it might get flooded by automated AI submissions.

Comments URL: https://news.ycombinator.com/item?id=49175717

Points: 65

# Comments: 54

On one hand, our core product is just simply not fit for them at its scale. We've tried but the project is large enough to require human input for every change. But we have AI automations for light code refactoring, writing tests, UI changes etc. and they work.

On the other hand, I started a number of small experiments to see how far software factories can be pushed and while the code produced so far is nothing spectacular I could easily imagine how this can be extended in the near future. Perhaps if you start from the ground up with the idea that the code will be written that way then you can come up with strategies and architectures that accommodate it. At least this is my thinking right now.

Anyway, it is all open source and documented here https://relentless.works/ I am not sure for long I will keep this running. I provide zero direction to where this is going. I have no idea what it will happen next. It is a fun experiment.

I have another such experiment with a trading agent. I thought it will loose all of the money in short time. For a while it was stuck with no open positions after it lost a bit. I decided not to intervene and just observe the behaviour. Recently it opened new positions which was an interesting development. It is still loosing money (~ -3%) but it has not lost all of them and given the current market circumstances I would say this ain't bad at all. It just shows that perhaps we might be a bit impatient when it comes to AI.

So I think it is probably possible to build software factories but we need new concepts and a bit of change of mindset.

I hope this helps.

If a tool is authenticated as personal then it can be only accessed under personal context - i.e. privately. Now if the author of the agent wants to add tools authenticated with shared secrets that is something should be considered in the threat model.

In other words:

- reading my personal emails in a public setting - not ok - reading the agents shared inbox in a public setting - probably ok depending on the threat model