That’s such a silly take.

“Our approach is harness-first engineering: instead of reading every line of agent-generated code, invest in automated checks that can tell us with high confidence, in seconds, whether the code is correct. “

that’s literally what The whole industry has been doing for decades, and spoiler: you still need to review code! it just gives you confidence that you didn’t miss anything.

Also, without understanding the code, it’s difficult to see its failure modes, and how it should be tested accordingly.

▲

menaerus 3 hours ago | parent [-]

So you read the three-part series of blogs that are packed in details in 3 minutes after I shared the link and put yourself into a position of entitled opinion and calling my position a silly take? Sure thing.

▲

stingraycharles an hour ago | parent | next [-]

Obviously not, I skimmed through the first two, and it’s not difficult to assess that it’s just fluff that sounds interesting but is actually not.

	▲	menaerus an hour ago \| parent [-]
		Implementing a Redis and Kafka rewrite (in Rust) but with workload-aware and self-balancing JIT-like engine deployed at Datadog-scale is no fluff. You obviously have no idea what you're talking about.

▲

grey-area 2 hours ago | parent | prev [-]

They probably used an AI to summarise those blog posts for them and it told them with high confidence, in seconds, whether they were correct.

	▲	menaerus 41 minutes ago \| parent [-]
		Their profile generally comes up here on HN very often with Dunning-Kruger effect like comments so it makes me believe it is no AI. AI would do a better analysis, for the better or worse.