I don't see any meaningful performance improvements in those paid models anymore.

They all roughly produce junior developer-level code, continue to have mental breakdowns in their “thinking” stage, occasionally hallucinate things, delete pieces of code/docs they don’t understand or don’t like, use 1.5 times the necessary words to explain things when generating docs and so on.

I'm now testing "avoid sycophancy, keep details short and focus on the facts" in my AGENTS.md files.

▲

podnami 4 hours ago | parent | next [-]

This is snark. Since when has a junior level dev managed to debug and deploy say a cloudformation stack and follow up with notes under 3 minutes?

▲

gjsman-1000 4 hours ago | parent [-]

Heard this analogy elsewhere, but worth repeating:

AI is like having the greatest developer who ever lived, but she is always on 4 beers.

▲

nathan-hello 4 hours ago | parent [-]

personifying ai is incredibly cringe no matter how weird your comparison is

	▲	gjsman-1000 4 hours ago \| parent [-]
		Imagine a drunk developer. Sparks of brilliance while missing obvious trees.

▲

nimchimpsky 4 hours ago | parent | prev [-]

[dead]