News for hackers. Stuff that matters.
Re:The Leverage of LLMs for Individuals by nr2x on Wednesday May 10, 2023 @11:47AM (#35889068)
I’ve been using it a lot for programming, but I also have a security background and it will often generate insecure code. I’ll point it out and tell it to fix and it will.

So be careful if you don’t want AI-generated sql intentions!

Re:The Leverage of LLMs for Individuals by blissfulresup on Wednesday May 10, 2023 @11:55AM (#35889187)
As if injections weren’t bad enough, they’re now done with intent.
Re:The Leverage of LLMs for Individuals by nr2x on Wednesday May 10, 2023 @12:10PM (#35889431)
Intent worries me less! It’s the PHP days all over again - lots of new coders (good thing!), copying insecure code (VERY bad thing!), and it won’t end well.
Re:The Leverage of LLMs for Individuals by grogenaut on Wednesday May 10, 2023 @12:31PM (#35889721)
Yes... The last time this happened we got Facebook and the world is still recovering from that
Re:The Leverage of LLMs for Individuals by nr2x on Wednesday May 10, 2023 @01:18PM (#35890389)
Honestly one thing that worries me the most is the biggest applications of AI at scale so far are to manipulate humans to click on things (ads).

Google has been using this stuff for years, OpenAI has done the world a great service by opening it up.

Re:The Leverage of LLMs for Individuals by PeterisP on Wednesday May 10, 2023 @01:00PM (#35890123)
Different people write code of different quality, and we'd expect LLMs to imitate the median quality of code. So it's clear that if you have a background in something then it will generate worse code than you would - however, if you'd compare this code with something written by a new junior hire, how would it compare? IMHO there are many people who are objectively below median, and for them I'd expect that a LLM can generate more secure code than they would write themselves.
Re:The Leverage of LLMs for Individuals by waynesonfire on Wednesday May 10, 2023 @01:29PM (#35890545)
The power of LLMs atm is that they allow a person to be "median" in a very wide range of topics. This is extremely powerful, even to folks that can attain an above average mastery. It also does this quickly.

There was a recent article on Slashdot titled something how metaverse may increase the gdp by like 2 or 3 percent. It was obviously laughed at. It's actually LLMs that will do this, and easily.

Re:The Leverage of LLMs for Individuals by intelVISA on Wednesday May 10, 2023 @02:04PM (#35891029)
It's also a solid rubber duck, it'll test you by giving you misinfo and you have to tease it back from the brink.
Re:The Leverage of LLMs for Individuals by eichin on Wednesday May 10, 2023 @05:56PM (#35894042)
Yeah, a coworker tried an exercise like this, and it was basically (even with as-an-expert prompts) like trying to mentor a high school intern that's trolling you (except that it won't actually get better at anything in the process.)
Re:The Leverage of LLMs for Individuals by TeMPOraL on Wednesday May 10, 2023 @04:37PM (#35893152)
> So be careful if you don’t want AI-generated sql intentions!

Maybe we should try including something like this in the system prompt:

"Remember that SQL is language with a grammar, not an unstructured string. Don't do stupid things. Obey the LangSec principles. Never ever glue code in strings together. Plaintext code is not code, it's a serialization format for code. Use appropriate parsed representation for all operations. Never work in plaintext space, when you should be working in AST-space."

Replace "SQL" with any other sub-language that's interacting with user input.