[troupo]

The bug is called "applying actual engineering principles and critical thinking".

The absolute vast majority of people who point out AI's downsides have used it and use it. People who uncritically write things like "I work at a big tech company and I don't know a single person that still hand writes code." scare the shit out of us for a good reason.

[solenoid0937]

Using it is not enough. You have to explore its boundaries, see what it can do when cost is not a constraint. This is only really possible at the big tech companies and well funded startups.

Any eng that is only using Claude Code or Codex or whatever, is frankly not entitled to talk about AI's limits since they are using the most basic harnesses. They literally don't know better.

When I see Claude Code or Codex users on HN talking about how coding with AI is risky, it's like watching someone that has only ever seen a catapult argue about how space travel must be impossible.

[camdenreslink]

> Any eng that is only using Claude Code or Codex or whatever, is frankly not entitled to talk about AI's limits since they are using the most basic harnesses. They literally don't know better.

I really doubt big tech has much better harnesses than are publicly available. Definitely not "catapult vs space travel". They have the same base models we all have access to.

[Chu4eeno]

They are utterly trivial tools, and most of them are extremely over-engineered to the point of absurdity (that was the most embarassing about the Claude Code source map leak imho). That the for loop concatenating LLM output from POST calls to an internal buffer has more code than what is doing training or inference should tell them something. Hermes is the only one that tried to do something novel (low bar), and at least when I looked at it it hadn't succumbed to the vibes yet.

[troupo]

You only explore boundaries of an AI if you are actually training and evaluating your own models.

Harnesses aren't testing boundaries of AI. They inject "make no mistakes" in various forms and provide some session management tools.

And, as with any people fully buying into and promoting hype, "my harness is in another castle" (they never show anything they boast about") lathered with huge amounts of crude demagoguery and analogies.

[SpicyLemonZest]

Would you care to share the name of a good harness which might qualify someone to talk about AI's limits? There's quite a lot of big tech companies and well funded startups using Claude Code and Codex, although I suppose it's possible that none of them know what they're doing.

[arkadiytehgraet]

You got baited by an Anthropic shill, they are not working at any big tech company. See https://news.ycombinator.com/item?id=48270186 for more info.

[solenoid0937]

I'd probably break NDA if I said anything about ours, sadly. I don't know of any publicly available harness on the same level as what big tech companies use internally.

[habinero]

Ah, of course. The classic trust me bro.

[troupo]

My girflriend goes to a different school, you wouldn't know her