ghost of john gode

@ghostofjohngode

manager at ska walgreens

532 Following330 Followers2,234 Posts

Bluesky

Is this your profile?Claim it and ghostofjohngode.dirty.social is yours.Claim profile

ghost of john gode@ghostofjohngode· 6d

on top the free advertising by (probably!) accident, I love that it's making it actively harder to find old posts, too

ghost of john gode@ghostofjohngode· 7d

ghost of john gode@ghostofjohngode· Jul 9

no it doesn't lol

ghost of john gode@ghostofjohngode· Jun 28

empty-ass America 250 "celebration" concert with one stupid dork playing guitar under and Israeli flag to zero audience members. stupid.

ghost of john gode@ghostofjohngode· Jun 14

ghost of john gode@ghostofjohngode· Jun 11

thinking about this for no reason

ghost of john gode@ghostofjohngode· May 27

ghost of john gode@ghostofjohngode· May 21

worked at a place where the no-shit answer to this problem was to just have the LLM tools do the review/debugging/etc and it broke the shit out of everything lol (source: third-bit.com/2026/05/20/t...)

$Measuring Only the Easy Half LLMs make code generation faster, and that half is easy to measure. The other half is harder: time spent reviewing LLM-generated code for correctness, time lost debugging confidently wrong suggestions, security vulnerabilities introduced by plausible-looking but insecure code, and technical debt from suggestions that solved the immediate problem while ignoring the surrounding design. A study of GitHub Copilot’s code found that a substantial fraction of generated code contained security vulnerabilities, and that developers under time pressure accepted insecure suggestions at higher rates [Pearce2022]. A 2025 evaluation of five major LLMs found that none produced web application code meeting industry security standards [Dora2025]. A large-scale analysis of over 300,000 AI-authored commits found that more than 15% introduce at least one quality issue, and nearly a quarter of those issues persist in the codebase long-term [Liu2026]. Measuring only the inputs that go up while ignoring the costs that also rise is not measurement; it is marketing.$

ghost of john gode@ghostofjohngode· May 10

I don't think you actually understood the posts here, but I guess I'm not surprised

ghost of john gode@ghostofjohngode· Mar 30

what about vibe unaliving

headline: OpenAI Announces Browser-Based AI Agent for "Vibe Lifing"

by: Victor Tangermann

image: Sam Altman and 3 other dumb dipshits sitting around a laptop, looking like they're on ketamine

ghost of john gode@ghostofjohngode· Mar 30

walking out of Plato's cave, having a quick look around, and then deciding actually I'd rather go back in

hacker news comment:
It's free so why not just publish it on github then so that people could read the code and compile it themselves.
Right now it's closed source binary with a big fat "DOWNLOAD FOR FREE" button and instructions casually telling you to disable the last barrier between your system and persistent malware. Nobody should recommend this to anybody

direct reply from a dumbass:
Well, depends what the author's plans are for the future. Maybe it's not always going to be free as in beer, either.

ghost of john gode@ghostofjohngode· Mar 18

ghost of john gode@ghostofjohngode· Feb 12

shouldn't have left this guy at home, Guerin

ghost of john gode@ghostofjohngode· Feb 9

these guys just can't help themselves but to crib from the 14 words jfc

ghost of john gode@ghostofjohngode· Feb 8

this kind of thing should rightfully get you fired from being the dog catcher let alone managing the kind of wealth this guy deals with

ghost of john gode@ghostofjohngode· Feb 7

@yeoldebuttpirate.bsky.social dawg I'm dying at this

ghost of john gode@ghostofjohngode· Feb 1

of all the guys to be throwing around "creepy loser" accusations

elon musk on X claiming he could have been better at sex trafficking than his friend Jeffrey Epstein who he now claims he never liked

ghost of john gode@ghostofjohngode· Jan 31

here are the CEO and COO of my apartment

two tuxedo cats; black one in a sideways box and grey one standing beside her, both regarding the photographer with suspicion

ghost of john gode@ghostofjohngode· Dec 28

not the silliest but the most recent at least

ghost of john gode@ghostofjohngode· Dec 28

this industry, man, we're so cooked lol

csar 12 hours ago | prev | next [–]

Getting feedback on a plan or implementation is valuable because you get a fresh set of eyes. Using multiple models may help though it always feels a bit silly to me (if nothing else you’re increasing non-determinism because you know have to understand 2 LLM’s quirks).
But the “playing house” approach of experts is somewhere between pointless and actively harmful. It was all the rage in June and I thought people abandoned that later in the summer.

If you want the model to eg review code instead of fixing things, or document code without suggesting improvements (for writing docs), that’s useful. But there’s. I need for all these personas.

reply

bahaAbunojaim 9 hours ago | parent | next [–]

The way it works is that each agent think independently, discuss the solution and each agent opinion then one will synthesize a solution.
reply

ghost of john gode@ghostofjohngode· Dec 27

ghost of john gode@ghostofjohngode· Dec 19

ghost of john gode@ghostofjohngode· Dec 18

ez way to tell this stuff is snake oil is that it gets presented with unqualified characterizations... trying to sell me on how innovative the AI functionality is in a settings interface is bozo shit

settings interface in Google's chrome browser with the AI item inexplicably labeled "AI innovations" instead of AI tools or options or something useful

ghost of john gode@ghostofjohngode· Dec 17

lol

ghost of john gode@ghostofjohngode· Dec 5

ghost of john gode@ghostofjohngode· Nov 29

guess the ant got bored with autofellating?