At this point, I trust LLMs to come up with something more secure than the cheapest engineering firm for hire.

nozzlegear 5 hours ago | parent | next [-]

"Anyone else out there vibe circuit-building?"

https://xcancel.com/beneater/status/2012988790709928305

	▲	alexjplant 35 minutes ago \| parent [-]
		People make these mistakes too. Several times in my high school shop class kids shorted out 9V batteries trying to build circuits because they didn't understand how electronics work. At no point did our teacher stop them from doing so - on at least one occasion I unplugged one from a breadboard before it got too toasty to handle (and I was/am an electronics nublet). Similarly there was also a lot of hand-wringing about the Gemini pizza glue in a world where people do wacky stuff like cook fish in a dishwasher or put cooked meat on the same plate it was on when it was raw just a few minutes prior. LLMs are just surfacing the fact that assessing and managing risk is an acquired, difficult-to-learn skill. Most people don't know what they don't know and fail to think about what might happen if they do something (correctly or otherwise) before they do it, let alone what they'd do if something goes wrong.

▲

Aurornis 6 hours ago | parent | prev | next [-]

The cheapest engineering firms you hire are also using LLMs.

The operator is still a factor.

▲

jama211 6 hours ago | parent [-]

Yeah, but they’ll add another layer of complexity over doing it yourself

▲

Aurornis 5 hours ago | parent [-]

The people doing these kickstarters are outsourcing the work because they can’t do it themselves. If they use an LLM, they don’t know what to look for or even ask for, which is how they get these problems where the production backend uses shared credentials and has no access control.

The LLM got it to “working” state, but the people operating it didn’t understand what it was doing. They just prompt until it looks like it works and then ship it.

▲

caminante 5 hours ago | parent [-]

You're still not following.

The parents are saying they'd rather vibe code themselves than trust an unproven engineering firm that does(n't) vibe code.

	▲	TeMPOraL 2 hours ago \| parent [-]
		> they'd rather vibe code themselves than trust an unproven engineering firm You could cut the statement short here, and it would still be a reasonable position to take these days. LLMs are still complex, sharp tools - despite their simple appearance and proteststions of both biggest fans and haters alike, the dominating factor for effectiveness of an LLM tool on a problem is still whether or not you're holding it wrong.

▲

Kiro 4 hours ago | parent | prev | next [-]

LLMs definitely write more robust code than most. They don't take shortcuts or resort to ugly hacks. They have no problem writing tedious guards against edge cases that humans brush off. They also keep comments up to date and obsess over tests.

▲

BoorishBears 2 hours ago | parent | next [-]

I had 5.3-Codex take two tries to satisfy a linter on Typescript type definitions.

It gave up, removed the code it had written directly accessing the correct property, and replaced it with a new function that did a BFS to walk through every single field in the API response object while applying a regex "looksLikeHttpsUrl" and hoping the first valid URL that had https:// would be the correct key to use.

On the contrary, the shift from pretraining driving most gains to RL driving most gains is pressuring these models resort to new hacks and shortcuts that are increasingly novel and disturbing!

▲

devmor 4 hours ago | parent | prev [-]

Interesting and completely wrong statement, what gave you this impression?

▲

Kiro 3 hours ago | parent | next [-]

The discourse around LLMs has created this notion that humans are not lazy and write perfect code. They get compared to an ideal programmer instead of real devs.

	▲	joe_mamba 2 hours ago \| parent \| next [-]
		This. The hacks, shortcuts and bugs I saw in our product code after i got hired, were stuff every LLM would tell you not to do.
	▲	gxs 2 hours ago \| parent \| prev \| next [-]
		Amen. On top of that, especially now, with good prompting you can get closer to that better than you think.
	▲	salawat 3 hours ago \| parent \| prev [-]
		LLM's at best asymptotically approach a human doing the same task. They are trained on the best and the worst. Nothing they output deserves faith other than what can be proven beyond a shadow of a doubt with your own eyes and tooling. I'll say the same thing to anyone vibe coding that I'd say to programmatically illiterate. Trust this only insofar as you can prove it works, and you can stay ahead of the machine. Dabble if you want, but to use something safely enough to rely on, you need to be 10% smarter than it is.

▲

dylanowen 3 hours ago | parent | prev | next [-]

I know right. I kept waiting for a sarcasm tag at the end

▲

majorchord 3 hours ago | parent | prev [-]

right and wrong don't exist when evaluating subjective quantifiers

▲

lukan 6 hours ago | parent | prev | next [-]

And the cheapest engineering firm won't use LLMs as well, wherever possible?

	▲	fc417fc802 4 hours ago \| parent \| next [-]
		The cheapest engineering firm will turn out to be headed up by an openclaw instance.
	▲	TheRealPomax 6 hours ago \| parent \| prev [-]
		fun fact, LLMs come in cheapest and useless and expensive but actually does what's being asked, too. So, will they? Probably. Can you trust the kind of LLM that you would use to do a better job than the cheapest firm? Absolutely.

▲

minimalthinker 6 hours ago | parent | prev [-]

this.