lol 5000 tests. Agentic code tools have a significant bias to add versus remove/condense. This leads to a lot of bloat and orphaned code. Definitely something that still needs to be solved for by agentic tools.

▲

nosianu 2 days ago | parent | next [-]

> Agentic code tools have a significant bias to add versus remove/condense.

Your point stands uncontested by me, but I just wanted to mention that humans have that bias too.

Random link (has the Nature study link): https://blog.benchsci.com/this-newly-proven-human-bias-cause...

https://en.wikipedia.org/wiki/Additive_bias

	▲	maddmann 2 days ago \| parent [-]
		Great point, interesting how agents somehow pick up the same bias.

▲

oofbey 2 days ago | parent | prev [-]

Oh I’ve had agents remove tests plenty of times. Or cripple the tests so they pass but are useless - more common and harder to prompt against.

▲

maddmann 2 days ago | parent [-]

Ah true, that also can happen — in aggregate I think models will tend to expand codebases versus contract. Though, this is anecdotal and probably is something ai labs and coding agent companies are looking at now.

	▲	oofbey 2 days ago \| parent [-]
		It’s the same bias for action which makes them code up a change when you genuinely are just asking a question about something. They really want to write code.