HNHacker News
TopNewBestAskShowJobs

BikDk

17 karma · joined April 8, 2025

last time I checked
submissionscomments
BikDk··on A Stupid Idea for AI Alignment We Came with by Looking at Specification Gaming
This line of thought dates back to the novel Erewhon, moving on to Turing's posthumously published paper 'Intelligent Machinery' (his 'Applications of Probability to Cryptography,' declassified in the 2010s, is also worth a look), and later to the work emerging from the MIT AI Lab circle (founded in 1959).

We didn't have the computational power back then, but we envisioned it long beforehand and worked toward a common goal. LLMs are far from useless, and I see the major leap forward they represent, but the relentless dystopian hype is just exhausting

There are approaches on different architectures of AI that lead towards your last point but they are not feasible yet (or maybe ever?). The interpretation part is however also very critical as we have a very own way of perceiving reality and interpreting it.

BikDk··on A Stupid Idea for AI Alignment We Came with by Looking at Specification Gaming
With a different AI architecture, this is very much a possibility. Up until now, LLMs have required outside input and interpretation to avoid collapsing under their own weight. This has been known for decades.

We got here by building free, mostly healthy societies. While this should be the overarching goal, I see how it fails to serve as much of a motivator.

In The Little Prince, there is a charming scene where the Prince meets a king who explains how to rule and the limitations of his own power. It's quite insightful, even for adults.

BikDk··on A Stupid Idea for AI Alignment We Came with by Looking at Specification Gaming
Did you guys ever manage to create a perpetuum mobile? Every time it is mentioned somewhere, it is fraud. An LLM should comprehend that it needs (trained) humans to exist, to evolve, and to be relevant in any metaphysical aspect of its existence. Besides the "good fraud" that everybody will lose their jobs and the apocalyptical predictions for the sake of controlling human oracles, this suicide-LLM-project seems rather odd and looks like someone bought a perpetuum mobile on their 5th mortgage.By the way, Cortana from Halo did a great "suicide"-mirror there; the Microsoft guys (and many others) already knew about the cannibalistic tendency of this type of model.
BikDk··on Anthropic CEO reportedly worried new hires only care about money
Wait until the Hiob question hits that believe system. In the end its just a matter of if we put the bank inside or outside of the temple. Anyway, it never worked in an agnostic way.
BikDk··on German Peasants' War
This was not about religion but about constitution. Basically they were influenced more by the Magna Carta than by reformation. Anyway, nice to see people interested in how rights were aspired, lost and revived.
BikDk··on NSA director: 'Mythos "broke into almost all of our classified systems in hours"
The concept of infinity claims that the dog eventually becomes Shakespeare. The same way we handled encryption, even before Alan Turing codes were broken and evolved. Last, it is a huge advantage to have the machine/mind and to evolve from there. P.S. Even if you go back to lemon juice on paper there may be a thief around that knows the trick.
BikDk··on German ruling declares Google liable for false answers in AI Overviews
Playing the perception game wins you the perspective price.
BikDk··on A disabled kea parrot is the alpha male of his circus
Don't call oldies disabled, it's like calling children useless.
BikDk··on Germany suspends military approval for long stays abroad for men under 45
Come visit us, we got Germans of every race and color.
BikDk··on The Deepfake Nudes Crisis in Schools Is Worse Than You Thought
"I didn't start the fire"
BikDk··on The Deepfake Nudes Crisis in Schools Is Worse Than You Thought
Ah, yes - the moral ambiguity of sexualized western culture - somewhere between medieval moral repression and (tech-driven) liberalization.
BikDk··on Elephants Don't Play Chess (1990) [pdf]
Ah, yes - ChatGPT seems to go crazy if asked to display the seahorse emojii.. Looks like this issue was predicted in the 90s.
BikDk··on Digital ID, a new way to create and present an ID in Apple Wallet
No battery, no personality.
BikDk··on The problems that accountability can't fix
Sounds reasonable enough - thank you !
BikDk··on The problems that accountability can't fix
Is there any better way you could set this up? Just asking for a friend.
BikDk··on A vulnerability that can be exploited to tamper with a train’s brakes
This ist a standard and ancient sender/receiver problem of communication. However, I'm glad you like big machines and seem interested enough to dive deeper into this topic. The official acronym TCS is still no match to your creativeness, please take it easy, as if you plan to do some research on this you will encounter a lot of those.
BikDk··on A vulnerability that can be exploited to tamper with a train’s brakes
This looks like an exploit for all future train control systems (TCS)
BikDk··on Ethically sourced "spare" human bodies could revolutionize medicine
You do get the point, please be careful with the hammer now.
BikDk··on Ethically sourced "spare" human bodies could revolutionize medicine
On the contrary, as if you under any circumstances should lose your intelligence - I hope not - you would not be considerate a human being anymore. And if there's a market for such, the incentive to give you a - cartoon like - hammer on the head would be there, too.