LESSWRONG
LW

ZankerH
56001670
Message
Dialogue
Subscribe

Posts

Sorted by New

Wikitag Contributions

Comments

Sorted by
Newest
No wikitag contributions to display.
We Don't Just Let People Die—So What Next?
ZankerH1y-2-1

From what I was allowed to read, I think you're deliberately obfuscating and misrepresenting the active and passive choices. If that was unintentional, you need to work on good faith argumentation.

Reply
We Don't Just Let People Die—So What Next?
ZankerH1y-3-2

Stopped reading when the author proposed I do so, thank you for the notice.

Reply
Templarrr's Shortform
ZankerH1y1-3

Modern datacenter GPUs are basically the optimal compromise between this and still retaining enough general capacity to work with different architectures, training procedures, etc. The benefits of locking in a specific model at the hardware level would be extremely marginal compared to the downsides.

Reply
D&D.Sci(-fi): Colonizing the SuperHyperSphere
ZankerH2y20

My inferences, in descending order of confidence:

(source: it was revealed to me by a neural net)

84559, 79685, 87081, 99819, 37309, 44746, 88815, 58152, 55500, 50377, 69067, 53130.

Reply
Improving the safety of AI evals
ZankerH2y20

ofcourse you have to define what deceptions means in it's programming.

That's categorically impossible with the class of models that are currently being worked on, as they have no inherent representation of "X is true". Therefore, they never engage in deliberate deception.

Reply
Some thought experiments on digital consciousness
ZankerH2y10

>in order to mistreat 2, 3, or 4, you would have to first mistreat 1

What about deleting all evidence of 1 ever having happened, after it was recorded? 1 hasn't been mistreated, but depending on your assumptions re:consciousness, 2, 3 and 4 may have.

Reply
All AGI Safety questions welcome (especially basic ones) [~monthly thread]
ZankerH2y10

That’s Security Through Obscurity. Also, even if we decided we’re suddenly ok with that, it obviously doesn’t scale well to superhuman agents.

Reply
The Prospect of an AI Winter
ZankerH2y52

>Some day soon "self-driving" will refer to "driving by yourself", as opposed to "autonomous driving".

Interestingly enough, that's what it was used to mean the first time the term appeared in popular culture, in the film Demolition Man (1993).

Reply
All AGI Safety questions welcome (especially basic ones) [~monthly thread]
ZankerH2y46

We have no idea how to make a useful, agent-like general AI that wouldn't want to disable its off switch or otherwise prevent people from using it.

Reply
Load More
No posts to display.