Bill Mitchell

328.8K posts

Bill Mitchell banner
Bill Mitchell

Bill Mitchell

@mitchellvii

CEO of YourVoice™ Studios, Inc. Host of YourVoice America. This account is owned and managed by Bill Mitchell. So excited for the next 4 years! #MAGA

West Virginia Katılım Aralık 2008
19.1K Takip Edilen502.9K Takipçiler
Sabitlenmiş Tweet
Bill Mitchell
Bill Mitchell@mitchellvii·
PEOPLE MISUNDERSTAND THUNE! - People think that John Thune opposes the SAVE America Act. That's not true at all. The only way to pass a SAVE America Act is nuking the filibuster. John Thune opposes nuking the filibuster because this will give Trump too much power. He, along with his puppet master McConnell, are globalists. They need to slow the AmericaFirst agenda to serve their corporate donors, the multinational corporations. As long as the filibuster exists, they have an excuse not to pass the Trump agenda. They can blame it on the Democrats. But once that filibuster is gone, it's all on them. I believe Thune supports the SAVE America Act but the path to that act, nuking the filibuster, is completely against his globalist agenda.
Bill Mitchell tweet mediaBill Mitchell tweet media
English
1.4K
1.8K
4.5K
474.1K
Bill Mitchell
Bill Mitchell@mitchellvii·
I just want 5 to 15% of my followers to see my post in the 30-minute probe phase as was promised. If that happens the rest takes care of itself. It makes no difference if the algorithm "likes" my post. My follower engagement with drive reach. THIS is the broken piece. @elonmusk @nikitabier
English
3
2
17
331
Bill Mitchell retweetledi
Bill Mitchell
Bill Mitchell@mitchellvii·
Grok just informed me that, "... in 2026, follower count has largely become a vanity metric when it comes to actual reach." This concerns me.
English
7
6
23
1.2K
Bill Mitchell
Bill Mitchell@mitchellvii·
But here's the problem. All of this is based upon your probe phase. If the algorithm excludes your followers from the probe phase in a narrow niche like politics, you are going to get no reach. None of this works with a broken probe phase.
Nav Toor@heynavtoor

Elon has open-sourced the algorithm that decides what you see on X. Not a blog post explaining it. Not a press release describing it. The actual source code. With the actual model weights. On GitHub. Every line. Every signal that determines whether your post reaches 100 people or 100 million. This is the most powerful recommendation engine on Earth. And now you can read it. Here is what the algorithm actually looks at: → Fifteen actions. The model does not score "relevance." It predicts 15 separate probabilities for every post: favorite, reply, repost, quote, click, profile click, video view, photo expand, share, dwell, follow the author, not interested, block author, mute author, report. Your final reach is the weighted sum of all 15. → Negative actions hurt more than you think. Block, mute, report, and not-interested are weighted negatively. Every single mute on your post subtracts from your score. A post that triggers one mute and ten likes does not net ten likes. It nets ten likes minus one heavy penalty. → Bookmarks are not tracked. Bookmark is not in the 15 predicted actions. Every creator guru telling you to "write bookmark-worthy posts" is wrong, at least according to this released code. Bookmarks may matter for the user privately, but they do not feed the ranker. → Dwell time is a silent vote. If someone stops scrolling and lingers on your post without engaging, that counts as a positive signal. The model has a P(dwell) prediction. The algorithm knows when people pause. → Profile clicks are tracked separately. P(profile_click) is its own prediction. People clicking from your post to your profile is a distinct positive signal. Your post sells the click, your bio closes the follow. → Quote is worth more than repost. The model predicts P(quote) and P(repost) as two different actions with two different weights. A quote tweet, where someone adds their own commentary, carries information a silent repost does not. The algorithm rewards conversation, not amplification. → Follow-after-engagement is tracked. P(follow_author) is one of the 15 predictions. A post that converts a reader into a follower is rewarded directly by the ranker. Not because of a hardcoded rule, but because the model learned the signal. → The Author Diversity Scorer punishes spam posting. There is a specific component in the code called Author Diversity Scorer. Its job is to attenuate repeated scores from the same author. Posting twenty times a day cannibalizes your own reach. The algorithm enforces diversity automatically. → Candidate isolation. Each post is scored alone against your history. Posts cannot see each other during scoring. Your post is not competing with the post above it in the batch. It is competing with the user's taste model. → No hand-engineered features. There is no rule in the code that says "boost verified" or "suppress external links" or "promote subscribers." The Grok transformer learns everything from raw engagement sequences. Whatever the model has learned, it learned from user behavior, not from a hardcoded boost. → Out-of-network discovery. The Phoenix retrieval system uses a two-tower model. One tower encodes you. One tower encodes every post on X. They meet in a vector space. The closest matches surface in your For You feed even if you do not follow the author. → Visibility filters run last. After ranking, a final pass strips spam, violence, gore, and deleted posts. Ranking decides reach. Visibility decides whether you see it at all. Here is what this means for you: If your posts are not reaching people, it is not because the algorithm is broken. It is because the algorithm is working exactly as designed. It rewards: 1. Posts that get reactions across multiple action types (a like AND a profile click AND a follow beats five likes alone) 2. Conversation depth (quote tweets are worth more than reposts in the math) 3. Dwell time (write posts people stop to read) 4. Posts that convert viewers into followers (your bio is part of your post) 5. Variety from each author (post less, post better) And it punishes: 1. Mutes 2. Blocks 3. Reports 4. "Not interested" clicks 5. Same-author saturation For twenty years, the algorithm was a secret.

English
1
0
2
582
Bill Mitchell
Bill Mitchell@mitchellvii·
@heynavtoor But here's the problem. All of this is based upon your probe phase. If the algorithm excludes your followers from the probe phase in a narrow niche like politics, you are going to get no reach. None of this works with a broken probe phase. 1:41 PM
English
0
0
1
38
Nav Toor
Nav Toor@heynavtoor·
Elon has open-sourced the algorithm that decides what you see on X. Not a blog post explaining it. Not a press release describing it. The actual source code. With the actual model weights. On GitHub. Every line. Every signal that determines whether your post reaches 100 people or 100 million. This is the most powerful recommendation engine on Earth. And now you can read it. Here is what the algorithm actually looks at: → Fifteen actions. The model does not score "relevance." It predicts 15 separate probabilities for every post: favorite, reply, repost, quote, click, profile click, video view, photo expand, share, dwell, follow the author, not interested, block author, mute author, report. Your final reach is the weighted sum of all 15. → Negative actions hurt more than you think. Block, mute, report, and not-interested are weighted negatively. Every single mute on your post subtracts from your score. A post that triggers one mute and ten likes does not net ten likes. It nets ten likes minus one heavy penalty. → Bookmarks are not tracked. Bookmark is not in the 15 predicted actions. Every creator guru telling you to "write bookmark-worthy posts" is wrong, at least according to this released code. Bookmarks may matter for the user privately, but they do not feed the ranker. → Dwell time is a silent vote. If someone stops scrolling and lingers on your post without engaging, that counts as a positive signal. The model has a P(dwell) prediction. The algorithm knows when people pause. → Profile clicks are tracked separately. P(profile_click) is its own prediction. People clicking from your post to your profile is a distinct positive signal. Your post sells the click, your bio closes the follow. → Quote is worth more than repost. The model predicts P(quote) and P(repost) as two different actions with two different weights. A quote tweet, where someone adds their own commentary, carries information a silent repost does not. The algorithm rewards conversation, not amplification. → Follow-after-engagement is tracked. P(follow_author) is one of the 15 predictions. A post that converts a reader into a follower is rewarded directly by the ranker. Not because of a hardcoded rule, but because the model learned the signal. → The Author Diversity Scorer punishes spam posting. There is a specific component in the code called Author Diversity Scorer. Its job is to attenuate repeated scores from the same author. Posting twenty times a day cannibalizes your own reach. The algorithm enforces diversity automatically. → Candidate isolation. Each post is scored alone against your history. Posts cannot see each other during scoring. Your post is not competing with the post above it in the batch. It is competing with the user's taste model. → No hand-engineered features. There is no rule in the code that says "boost verified" or "suppress external links" or "promote subscribers." The Grok transformer learns everything from raw engagement sequences. Whatever the model has learned, it learned from user behavior, not from a hardcoded boost. → Out-of-network discovery. The Phoenix retrieval system uses a two-tower model. One tower encodes you. One tower encodes every post on X. They meet in a vector space. The closest matches surface in your For You feed even if you do not follow the author. → Visibility filters run last. After ranking, a final pass strips spam, violence, gore, and deleted posts. Ranking decides reach. Visibility decides whether you see it at all. Here is what this means for you: If your posts are not reaching people, it is not because the algorithm is broken. It is because the algorithm is working exactly as designed. It rewards: 1. Posts that get reactions across multiple action types (a like AND a profile click AND a follow beats five likes alone) 2. Conversation depth (quote tweets are worth more than reposts in the math) 3. Dwell time (write posts people stop to read) 4. Posts that convert viewers into followers (your bio is part of your post) 5. Variety from each author (post less, post better) And it punishes: 1. Mutes 2. Blocks 3. Reports 4. "Not interested" clicks 5. Same-author saturation For twenty years, the algorithm was a secret.
Nav Toor tweet media
English
10
18
52
4.3K
Bill Mitchell
Bill Mitchell@mitchellvii·
Isn't it fascinating how when we stopped funding the Ukraine war, the entire Democrat Party completely lost interest in it?
English
61
313
2K
11.4K
Bill Mitchell
Bill Mitchell@mitchellvii·
HERE IS THE PROBLEM WITH THE ALGORITHM IN A NUTSHELL: When Grok took over the algorithm, we were promised that in the "probe phase" of our post, 5 to 15% of our best followers would see the post in their timelines. THIS has not happened. In most cases, perhaps 0.1% of our followers see the post. The rest are non-follower unverified randos who either have no interest in our content or actively dislike it. Now, rather that having a vibrant positive debate in my replies, it is a landfill of non-sequiturs and ad hominem attacks. Worse yet, because the algorithm determines future reach based upon "early momentum," we enter a death spiral where our post is tested against mostly non-followers and we are unable to gain momentum and the post dies. This is why the lightweight garbage posting does so well, because it is not follower-targeted. SOLUTION: Just let 5 to 15% off our followers see our posts in the first 30 minutes as promised and everything will be fine.
Elon Musk@elonmusk

Critique of the 𝕏 algorithm is welcome. There will be monthly updates of the latest algorithm to GitHub with release notes. As reminder, you can always choose no algorithm via the Following tab.

English
10
7
38
3.1K
Bill Mitchell
Bill Mitchell@mitchellvii·
@BenHart_Freedom My replies are filled with small unverified leftist trolls who have no business seeing my posts in the first place.
English
0
0
0
20
Ben Hart
Ben Hart@BenHart_Freedom·
@mitchellvii I find I have to actively search for people I'm interested in. Their posts are not coming up in my feed. And I tend to search for the same people every day.
English
1
0
1
36
Kat Kanada 🏴
Kat Kanada 🏴@KatKanada_TM·
@mitchellvii Vanity metric??? How about the years and years it took to build the growth on here? Do those years of grinding not count for anything?
English
1
0
1
68
Angry American
Angry American@Angry_American0·
@mitchellvii What’s the point in following people when you can’t even see their posts? For the most part, my posts goes to the void, no engagement. Despite being a trending topic. Even when you turn on notifications for that account, it doesn’t always show.
English
1
0
2
51
Keith Manley
Keith Manley@KeithManleyjr·
@mitchellvii To your point, it seems I barely see posts from even people I subscribe to.
English
1
0
1
37
Bill Mitchell
Bill Mitchell@mitchellvii·
HERE IS THE PROBLEM WITH THE ALGORITHM IN A NUTSHELL: When Grok took over the algorithm, we were promised that in the "probe phase" of our post, 5 to 15% of our best followers would see the post in their timelines. THIS has not happened. In most cases, perhaps 0.1% of our followers see the post. The rest are non-follower unverified randos who either have no interest in our content or actively dislike it. Now, rather that having a vibrant positive debate in my replies, it is a landfill of non-sequiturs and ad hominem attacks. Worse yet, because the algorithm determines future reach based upon "early momentum," we enter a death spiral where our post is tested against mostly non-followers and we are unable to gain momentum and the post dies. This is why the lightweight garbage posting does so well, because it is not follower-targeted. SOLUTION: Just let 5 to 15% off our followers see our posts in the first 30 minutes as promised and everything will be fine.
English
5
3
28
1.2K
Bill Mitchell
Bill Mitchell@mitchellvii·
Can someone remind me why we threw away hundreds of billions on Ukraine that was NOT our war? Oh that's right. They were laundering money back to the DNC. I keep forgetting that part.
English
112
656
2.5K
11K
Bill Mitchell
Bill Mitchell@mitchellvii·
Aliens land in your backyard. They teleport through your walls and ask you if you own any Frank Sinatra music. What do you do?
Bill Mitchell tweet mediaBill Mitchell tweet media
English
51
4
36
3K
Clyde MacCludgie 🐟
Clyde MacCludgie 🐟@ClydeMacCludgie·
@mitchellvii I'd ask the aliens if they want to watch High Society. I'd call the cops while they are distracted and sneak off to get my gun and force them to reenact a musical number for TikTok while I wait for the police to show up.
English
1
0
5
111