Hidden Product Criticism - Harness engineering: Leveraging Codex in an agent-first world

Frustration that the article describes impressive metrics without revealing what product was built, making claims impossible to evaluate

Commenters express deep skepticism toward the article’s impressive metrics, arguing that claims of "agent-first" success are impossible to verify when the actual product remains hidden. Many view this secrecy as a hallmark of "AI hype," where technical opacity and a lack of sample repositories prevent peers from evaluating specific implementations or validating promised productivity gains. This frustration signals a broader demand for tangible proof, as critics note that if AI truly enables 10x engineering speeds, the industry should be seeing substantial, machine-created software rather than just more theoretical promises. Ultimately, the community remains wary of success stories that offer no links, code, or visible output to bridge the gap between internal prototypes and real-world results.

View on HN · Topics

They never specified what exactly the product was, without which it's impossible to judge the post.

For some reason most of the uses of "agents" are to build yet other AI products, it's turtles all the way down. Maybe that says more about the field of harnesses than it does about the power of "agents".

View on HN · Topics

I'm not an AI skeptic but I'm skeptical of the intent of this article. It makes great claims about agent-first engineering and tries to make a real case based on a real product, with real users, and a real team that's been growing — all without even saying what was built or showing it, just like every other AI hype article.

View on HN · Topics

At the time we wrote the article we hadn’t released the product and weren’t ready to talk about it. It was an internal prototype that looked very much like the current Codex app.

View on HN · Topics

And this thread too is filled with users that "I also have done this or that" but bar one user, nobody followed up with any link to anything.

View on HN · Topics

I agree. I followed this article for a repo I'm working on, and I had a very hard time inferring how, specifically, they implemented "providers" and enforced import layers. A sample repo would've been nice.

View on HN · Topics

This would be much more convincing if the repos, issue trackers, etc. were accessible.

View on HN · Topics

Given that we can code at 10x speed for at least half a year, one would expect to see at least some pieces of machine-created software with 5 years' worth of equivalent human engineering work.

Anyone know some?