Agents are perfectly capable of learning. Why would the model need to learn? The harness and tooling are all that matter.

They aren't, it's just populating context window until "memory" is pushed out.

This is my experience. Though ice been writing LLM harnesses, agents, tooling, etc for 5 years now and believe it requires several hundred hours of experience before understanding how to consistently outperform at scale.

These types of comments help demonstrate first-hand how human reasoning stacks up against what an LLM would say in this situation.

A lot of us have been doing this for over a year now.

What would you even need to see? I struggle to find things that I cant do at scale with AI, and it’s dumbfounding to read posts about people that are unconvinced.

Tech products improving, for one. If everyone is a 10x engineer now (and has been for years) why isn't everything better? Instead, we're seeing github outages increasing in frequency, consumer products degrading left and right (google, iOS, etc etc). What is taking so long? Where are the results?

Where is the impact on the real world? Where are the process improvements? Where are the efficiency gains? Why are prices going up, not down? If y'all are actually super-engineers now why aren't you actually making anything better? Hurry up and fix some shit already.

I'll tell you why: it's all bullshit. You aren't actually any more effective with AI than you were without it. You may feel that way, but it's delusional. I'd love to be proven wrong, you can do it by living up to the hype.

I'm confident that won't happen, though. The industry will continue to produce the same mediocre, enshittified slop it always has. It'll do it at approximately the same rate, achieving the same output per engineer, even if they make you do it via a chatbot middleman. AI has had this property for a long, long time before LLMs, before Deep Learning, while neural nets were in their infancy--before backprop even. It can do really impressive things, in the right context, but it is not a substitute for thought and work. You have to put in the effort--whether it's tuning an objective function or iteratively crafting and refining a prompt. All that was old is new again.

The difference now is that it's taken on some bizarre religious significance. These goddamn fucking acolytes running around praising the computer jesus because it speaks words and stuff!. Revolting.

If you really want to convince me, show me something better than that.

Because markdown can totally do all the stuff that this article is about. Did you even read it?

This is the correct response.

This day is probably not long off. My prediction is before the end of 2028.

What particular point do you find false?

I dont know wtf you want, but I know what I want. The rest of us are generating all the apps we’ve ever needed, customized to our exact taste.