First bit of negative feedback I've heard about it.

i know breh. they retain with the best of 'em

openai retaining like a eunuch during no-nut-november

I create my fair share of regressions so I want/need tests. But I also want/need to keep max fear so I'm forced to compress and make sense of the code constantly.

I find myself wanting automated tests now that I'm not writing as much of the code. Tests can create a false sense of security (not unlike vibe coding) is my main gripe with them, but I should be able to get over that.

edit: what i mean - tests are certainly better to have than not all being equal. but that all being equal part is where things can break down ime.

I hadn't heard of a galactic second, but I'd guess you start at a galactic year, which is 225 million years. Then, 1 galactic second = 225 million years per galactic year / 31,536,000 seconds per year ~= 7.1 years.

Good rec. In this case the change is small by line count but delicate. Best use of an LLM in that case (I've found) is asking for a review matrix so I have a little more working memory.

routing around a broken API by earning sats from a bounty and spending them on the next tool

explain

From the same newsletter, open weights are keeping up and growing their market share:

I find it difficult to do code review after vibing for a couple days. Not good. And ime vibe reviewing misses ~20% of bugs when code is sufficiently hairy.

ah, for link posts we default to nostr's kind-1 (twitter-like) events and most nostr clients do not render markdown in those notes

the problem with making this a feature, as is, is that the comment counts won't represent the removed comments and cause confusion. why that is is kind of technical, but i could probably come up with a solution to it

those suckers

yep, borg

The Virgin AI HITL Purist. hbu?