HackerLangs
TopNewTrendsCommentsPastAskShowJobs

pelario

no profile record

Submissions

Hexagonal Architecture

en.wikipedia.org
3 points·by pelario·2 เดือนที่ผ่านมา·0 comments

Top downloaded skill in ClawHub contains malware

1password.com
334 points·by pelario·5 เดือนที่ผ่านมา·151 comments

comments

pelario
·20 วันที่ผ่านมา·discuss
The link does not seem to be working
pelario
·29 วันที่ผ่านมา·discuss
As I see many others like me, full of nostalgia: You can play it on the internet archive:

https://archive.org/details/msdos_Prince_of_Persia_1990

Once every couple of years I dive into it, I still cannot complete it without cheat codes, but I love the mouse animation, the "mirror" prince, and many other amazing details!
pelario
·2 เดือนที่ผ่านมา·discuss
This should be the first comment. I wrote some criticism, mostly because many internal contradictions in the article. Then, I notice the structure...

"The accountability gap" Here’s the question nobody’s asking: when it goes wrong, who carries the bag? (..)

"What to do instead"

"The craft still matters"
pelario
·2 เดือนที่ผ่านมา·discuss
> It hasn’t thought about the problem at all. It’s pattern-matching against its training data and producing the most plausible-sounding response.

The article kind of lost me here. Agents are way more than that, today. And the author knows it, as later it says stuff like

> Claude will never do this. It’s trained to be helpful.

But the first phrase just tell me author just have a deep dislike for agents and it's looking for rationalizations for that feeling.

Part of the criticism is on point, sure. But if it "being trained to be helpful" is a problem, it's fixable. It can "be trained to be more critical".

Later:

> But it wasn’t designed for your team. (..) It was designed for the median of everything Claude has seen. A generic best practice for a generic problem at a generic company. Which is to say, it was designed for nobody.

That's non-sense. Anybody who understand algorithms know that, sure, on a first instance you have a "good algorithm" that has a good performance on average, or in worst-case. But then, you can design algorithms that are adaptive to the input. Same applies here.
pelario
·5 เดือนที่ผ่านมา·discuss
Not only europe:

https://www.state.gov/releases/office-of-the-spokesperson/20...

https://apnews.com/article/chile-united-states-china-visa-sa...
pelario
·6 เดือนที่ผ่านมา·discuss
could you tell more details or links about that ?
pelario
·6 เดือนที่ผ่านมา·discuss
From the article:

"As temperature approaches zero from the negative side, the model output will again be deterministic — but this time, the least likely tokens will be output."

I understand this as, a negative number far from zero is also quite random (just with a distribution that will produce unlikely tokens).