Hacker News
DeepSeek Ultrafast
platinumrad
|next
[-]
booi
|root
|parent
[-]
epolanski
|root
|parent
|next
[-]
AI is okay at best at mundane task or good at task you don't care for the output quality or maintanability.
It tends to write much more code than needed, handles countless made up edge cases and is so reinforced to find the "shortest" or "simplest" way (by god knows which training criteria), that it can't stop leak responsibilities left and right, so you have modules/systems A-B-C and all of those are tightly coupled and know each other.
And no, subagents, agents.md, and whatever crap does not help much.
I myself use AI daily, but you folks have to stop with those loser narratives pushing people being mindless meat proxies. AI is okay at micro level and glueing messes of micro level code, but it's still really not there when it comes to software design and taste.
tancop
|root
|parent
|next
|previous
[-]
And even if you solved that problem it still wouldn't be creative enough. Claude never actively sets up clever TypeScript constructions to enforce that all keys of a map are accounted for, or looks for a library instead of writing complex UI code from scratch, or makes any framework choices other than the safe default ones.
It can do these things but you need to explicitly prompt it every time after reading the code to identify problems. That's the opposite of an end to end approach.
NortySpock
|root
|parent
[-]
While that's running, I can, in a second window, collaborate with an LLM on the next plan...
Edited to add: architecture-wise I have only done this on smaller scripts, and I encourage and sometimes enforce "pure functions, that act on data, with no internal state", and then if I need state it would go in a specific typed structure, not a object that mixes state with functions.
robbles
|next
|previous
[-]
jahala
|next
|previous
[-]
anigbrowl
|root
|parent
|next
[-]
If you want to play with this but don't have mega-resources, you can rent a B300 cluster for about $100/hour. Not what I'd call cheap, but if you have a clear application in mind you could use it to jump-start a small business, academic project, or resume booster in a weekend at low financial risk.
xlayn
|root
|parent
|previous
[-]
rvz
|previous
[-]
What could possibly go wrong?
xlayn
|root
|parent
|next
[-]
Thanks god you are not a wacko suggesting Qwen4B-abliterated will hacK someone
rvz
|root
|parent
[-]
It takes the attackers to successfully breach their target once vs the defenders having to stop all attempts.
SR2Z
|root
|parent
[-]
ShinyLeftPad
|root
|parent
[-]
it's not gonna save you here because it's very asymmetric and not in your favor, if you're a defender.
xyzzy123
|root
|parent
|next
[-]
I think there are a lot of unanswered questions like "is software security possible", in the sense of, will there be a long tail of bugs left for second tier models after frontier models have picked over everything?
Most predictions also sort of assume that the IT landscape looks similar to the way it does today. But there are a lot of possible futures, e.g. a more feudal model where smaller orgs without strong security capability shelter in the big clouds, "protected" by amazon, google, microsoft level resources etc.
anigbrowl
|root
|parent
|previous
[-]
Correspondingly, the proliferation of high-speed digital offensive capability will probably be met with counter-hacking designed to identify and retaliate against such intrusions even faster or wider-spectrum attacks - a Gibsonesque cision of asymmetric cyber conflict. If 'black ice' doesn't take down an destroy intruders on its own, drone munitions probably will.