linuxdeveloper

Joined 6 years ago

Karma
82
Submissions
44
Member since
Jun 15
I write a blog at https://blog.linuxdeveloper.io

It is a technical web log with tutorials, tips and tricks focused on Arch and Debian GNU/Linux. Alt topics include programming, nature, music, electronics and art.

My personal website is https://linuxdeveloper.io

You can email me at [email protected]

View on Hacker News

Recent submissions

Comment · 1 year ago
Ciao, help plz.

Nate Houk

Comment · 3 years ago
Comment · 3 years ago
"This way, Chrome gives you a personalized, predictable browsing experience."

Right... "predictable."

Comment · 3 years ago
Also, when did backups go from $2/month to $5/month per linode? What a joke.
Comment · 3 years ago
Sad but expected price increase on short notice. RIP Linode (2003-2023)
Comment · 3 years ago
This is fascinating and impactful for AGI as likely the action-plan for the robot will be generated token by token similar to an LLM.

Assume you have a robot instructed to protect humans.

How do you verify the action-plan passes moderation (i.e. doesn't harm a human) when the individual actions each do pass moderation, but the plan as a whole is dangerous (will harm a human).

Waiting to verify the entire chain of actions before starting actions in motion means your reaction time is slower.

If the robot is standing at a crosswalk, and sees a girl about to get hit by a car, he has to decide if he will push the girl out of the way, or if that action will cause greater harm.

The individual actions (activate arm, move arm towards girl, orient hand, shove girl out of path of car, etc) might each look beneficial to the human but as a whole actually are harmful.

However, the reaction time for the robot to save the girl might require near-immediate response.

Do you start processing the pipeline immediately or do you wait to verify the entire thing passes moderation?

Comment · 3 years ago

Live from the official Hacker News API

A modern reader for Hacker News · SvelteKit + Skeleton