I think I'm just slightly higher level, it seems. I don't give it small tasks, I give it ticket level prompts and let it decide what to do. (It being frontier models).

I don't have a harness or prompt. Just VS code integration through my company. All my prompts are from scratch and the only context it has.

Lately I haven't been saying go to X file and change Y, I say you have SSH keys to the embedded hardware: plan, deploy, and test latency improvements to the X stage of the image processing pipeline, parity test output images to avoid regressions, and target a 5ms latency improvement, ideas to look at are M, N, and P image processing techniques, I think latency is in this domain is mostly caused by Y, but verify, and let me know when you have a plan ready to implement.

Then it churns for 4 hours, it builds and runs it's own test harness and profiler, and autonomously works until it has a changeset ready to go.

That's how I get to 600k, and it seems to work fine? It got us 4.8ms today, through SIMD improvements and using a technique I hadn't thought of in place of a more expensive operation.

AKA "divide and conquer", how we programmers been fighting ever bigger and more complex problems since probably forever.

That doesn't make much sense to me because this is in nature much like how harnesses operate: launch a bunch of exploratory subagents to search and retrieve evidence to use in the actual prompt. Think of it as caching this end result so you don't have to re-fetch in the codebase.

the longer the context grows, the greater the probability that it generates ambiguity, and the probability that it makes mistakes approaches 1.

A system prompt should be looked at like a starting point and a direction, but not a giant atlas map of everything it may be asked to do.

I've been playing around with Qwen3.8-Next-Flash that has great logic, recall, roleplaying, etc. From what I can tell, it's definitely on part with the SOTA a few months ago, and my opinion, it likely is around the pinnacle of advancement without high inefficiency in preparing with the current LLM recipes. Further, I'm of the opinion America's SOTA is hitting the real cost-sigmoid and there's no singularity in site. These things will hack the planet if you put them in a group of agents and tell them to do it; but as context grows, the probability that they can answer "how many r's are in strawberry" goes down. No amount of parameters it going to erradicate that.

But I digress, my new stage of working with LLMs is figuring out how to use Qwen3.6-35B-A3B as the entry point to collect the context, and then use the big boys Qwen3.8 to make the edits, then degrade back and forth to complete changes. There's no harness yet for this, but there's clearly an intelligent way to setup a engineering harness.

And I do understand people have codebases that simply can't easily live in the smaller (~128k-256k) context windows, but instead of porting your codebase to another novel language, breaking it into context-aware components would make it closer to what these things can do.

And I'll repeat: I don't think we're approaching the singularity of self-recursion primarily because the LLMs will duplicate errors, context poison, and whatever else they encounter and there's no human who can sit around correcting it constantly. The American AI apparatus should cut their models like the Chinese down and work on real problems and stop imbibing the singularity-watts-are-all-we-need drugs.