Hacker News Reader

Comment by lhnz | Hacker News Reader

I know there's a joke about this regarding his ego and there's certainly some truth in that, however it's also quite believable that after a deployment he might have noticed the popularity of his tweets going down (since he no doubt checks his reach), so I can kind of understand how he might see "republicans", "democrats" and "celebrities_it_makes_sense_to_check_this_with_my_account_as_i_am_a_very_active_user" as core categories that need to have their reach balanced.

View on HN

> it's also quite believable that after a deployment he might have noticed the popularity of his tweets going down

He did notice it and it was treated as a 5 alarm fire, with a Musk cousin sending 2 am slack messages (on a Monday!) to Twitter engineers to urgently fix Elon's reach[1].

1. https://www.theverge.com/2023/2/14/23600358/elon-musk-tweets...

We don't need to speculate on this. It sounds like he did actually fire engineers over his tweets getting less engagement than he wanted.

https://www.platformer.news/p/elon-musk-fires-a-top-twitter-...

Honestly, if you read behind the lines, it sounds like the employee was intentionally making a joke about it at his expense in front of a bunch of people, and I think a lot of CEOs would take that badly as this is effectively the same thing as calling your boss egocentric.

But, we do have a bit of code that measures metrics on his account, so can we find the bit of code that increases the engagement on his account?

> But, we do have a bit of code that measures metrics on his account, so can we find the bit of code that increases the engagement on his account?

There doesn't need to be. When they run AB tests, it's possible that they'd pick the winning cell if it makes the Elon metrics look better.

Even if the algorithm doesn't do anything explicit about boosting him, it can be tweaked through AB testing to favor him.

You mean A/B testing of weights/biases?

No, the "weights" of your model are trained from the input data. What is usually AB tested are hyperparameters of the model, or different "flavors" of (model+input data).

What people are implying is still unsubstantiated though. The engineers on the Twitter Space say that this is to ensure that changes they make do not bias one category over another, they don't say that it's in order that they can make discretionary updates to bias towards Elon Musk.

Maybe after every update to the model, they check these stats to ensure that they haven't biased towards Elon Musk, and if so roll the change back.

? Considering Elon as its own category is a bias.

> “When you’re asked a question, you run it through your head and say ‘what is the least fireable response I can have to this right now?’” one employee explained.

Reading between the lines, Musk sounds like a giant baby.

The proper way to do that is create a pool of celebrities and monitor them. Not just the CEO's account.

For very active accounts, I assume that's what the "vits" or "power user" one is for. Or, heck, "vits" might actually be what you said.

ChatGPT suggests: Vitriolic accounts.

Reply on news.ycombinator.com