aocallaghan17

The models are the moat. It's why you have generous subscription usage plans and increasingly limited third party access.

Reminds me of this article: https://www.theverge.com/podcast/917029/software-brain-ai-ba...

Software engineers are definitely in a bit of a bubble here. Are we just early adopters who see the value sooner, or does it uniquely benefit software engineering, or do we just like cool automation and we're deluding ourselves that this adds value beyond the cost?

Yeah I mean this is closer to my use of LLMs, where I'm intentionally slowing things down enough to follow and course correct myself. This whole build the loop not the prompt idea seems to be advocating the opposite... I don't feel comfortable to not be the driver of the loop for a production system.

I'm just struggling with this, surely you need inner depth knowledge to reason about the system and make some level of decision, at least around system design and architecture if not lower level implementation details? But it sounds like you're generating that knowledge each time through a system of agents? How do you have so much trust in a non-deterministic system, or are you deferring ALL decisions to these "loops"? What if you and a team member generate a dashboard and it gives different results because the agent(s) used a different methodology?

And surely cost plays a part here. This is giving you such productivity gains to boost revenue enough to outweigh what must be huge token costs?

Seems like it. Perhaps the use case is for non-engineering folks to share AI generated prototypes?

We're starting to get asked by product managers how they can share/deploy their prototypes they made with Claude/Cursor.

Agree with this completely. This push for more autonomy I think is the complete wrong direction for how to use LLMs.

I want less code to maintain not more that I don't even fully understand.

I think research and very supervised coding with lots of guardrails is the way to actually gain productivity from these tools.

I just don't see any way you can work like this and maintain comprehension of the system being built?

Perhaps for toy projects or research, but for a production system you're accountable for understanding, maintaining and continuing to develop?

Agreed, and if automating the creation just creates more of these issues, faster than we can solve them, is it actually making us more productive?

The huge investment into LLMs at a loss is about having control of these tools and technology. Now we're seeing a state try to take some control.

But who do you trust more to make these decisions? A democratically elected government or a private company?