For more complex projects I find this pattern very helpful. The last two gens of SOTA models have become rather good at following existing code patterns.
If you have a solid architecture they can be almost prescient in their ability to modify things. However they're a bit like Taylor series expansions. They only accurate out so far from the known basis. Hmm, or control theory where you have stable and unstable regimes.
I don't really get the idea that LLMs lower the level of familiarity one needs to have with a language.
A standup comedian from Australia should not assume that the audience in the Himalayas is laughing because the LLM the comedian used 20 minutes before was really good at translating the comedian's routine.
But I suppose it is normal for developers to assume that a compiler translated their Haskell into x86_64 instructions perfectly, then turned around and did the same for three different flavors of Arm instructions. So why shouldn't an LLM turn piles of oral descriptions into perfectly architected Nim?
For some reason I don't feel the same urgency to double-check the details of the Arm instructions as I feel about inspecting the Nim or Haskell or whatever the LLM generated.
No I was referring to the original comment twisting words. They intentionally invoke the horrors of dictators running over protesters to disperse them.
Your comment showed the actual event, thanks. It showed an armored vehicle slowly pushing through protesters to gain access to something.
Not remotely comparable scenes, so I must assume intentional twisting of words. My comment was written sloppily.
I honestly don't understand why you posted the Narcissist's Prayer; however, to clarify: the original comment I responded to referred to another comment that said, "the United States government rolling through protesters in armored vehicles," to which I replied, in part, "it's a video of a WCCO news (local MSP TV station) segment which shows an armored vehicle pushing protesters out of the way."
The person who said I was twisting words said (emphasis mine), "There’s an enormous difference between driving slowly through a crowd of protestors with no injuries versus running over protesters with a tank."
At no point did I nor the comment I responded to use the words, 'running over protesters with a tank'.
I don't think anyone is claiming that the specific famous tank man of Tiananmen got run over by the tank. However, there is plenty of evidence that people got "mowed down by tanks" at Tiananmen Square: https://www.theglobeandmail.com/world/article-why-is-the-arm...
> Interesting. So what did the attestation say once I (random Internet user) updated the firmware to something I wrote or compiled from another source?
So your device had no user freedom. You're not doing much to refute the notion that these technologies are only useful to severely restrict user freedom for money.
> So your device had no user freedom. You're not doing much to refute the notion that these technologies are only useful to severely restrict user freedom for money.
Would love to hear more of your thoughts on how the users of the device I worked on had their freedom restricted!
I guess my company, the user of the device that I worked on, was being harmed by my company, the creator of the device that I worked on. It's too bad that my company chose to restrict the user's freedom in this way.
Who cares if the application of the device was an industrial control scenario where errors are practically guaranteed to result in the loss of human life, and as a result are incredibly high value targets ala Stuxnet.
No, the users rights to run any code trumps everything! Commercial device or not, ever sold outside of the company or not, terrorist firmware update or not - this right shall not be infringed.
I now recognize I have committed a great sin, and hope you will forgive me.
If you have a solid architecture they can be almost prescient in their ability to modify things. However they're a bit like Taylor series expansions. They only accurate out so far from the known basis. Hmm, or control theory where you have stable and unstable regimes.
reply