S!R Charles

@SustainableTall Grok, can you make a 3D rendered version of this plan?! I would like to better understand what I see.

Really interesting plan for a tower in Malmo, Sweden. Four, family sized apartments per floor, all with three bedrooms. Living space on the corners. Two winter gardens per home. Plenty of storage. Single stair!!! By Christoph Hilger

@javilopen Optimise for time spent on your post, not for likes! Ah, now I understand why such a long post! :D Great read and easy to digest. I'll dwell a bit longer on my favourite posters from now on..

⚡ xAI dropped the X algorithm yesterday and I don't get why nobody noticed what's actually in there I burned $500 on Claude going through every single line Here's what I found (LONG POST, save it for later): 0/ Every account has an "embedding" attached to it that describes you the way AI models do: in latent space. It's the internal fingerprint the model keeps of every user, a vector of numbers that sums up how your account behaves (what topics you touch, what engagement you generate, who you interact with). The model uses it every time it decides who to show your posts to. If your history is good, it stays clean and the model pushes you. If you accumulate negative signals (blocks, mutes, reports, not_interested), it goes toxic and starts penalizing you automatically. And the trap: it does NOT reset. What you do today stays in there for weeks, poisoning everything you publish after, even if it's good. That's why getting out of a shadowban or a low-reach streak on X feels like trying to move a giant rusted wheel. It's not your imagination, it's literally that. Cleaning up your embedding is slow and painful, like the impression you have of someone you don't like: no matter how nice they get to you, it's gonna take a while before you trust them. Another important finding: the embedding doesn't decay on a clock. It decays with NEW engagement entering the system. If you stop posting, the old bad signals stay frozen in there. Nothing overwrites them. If you start making content the algorithm likes, you'd see improvement after 6 to 8 weeks and a real shift around 12 to 16 weeks, assuming you don't pile up more bad signals along the way. Why is nobody talking about this? It blows my mind. Finally a confirmation of that "I'm in a bad streak" feeling we've all been through. 1/ First 30 minutes are everything If your post doesn't get engagement fast, Grok doesn't even evaluate it. No quality score, no deep analysis, no chance of reaching anyone who doesn't follow you. Dead and buried 2/ Post age caps at 80 hours: POST_AGE_MAX_MINUTES = 4800, bucketed in 1 hour chunks. After that you're in the "overflow bucket" which translates to "ancient, ignore" Best window: first 0 to 12 hours. After 24 you're already in a worse bucket Far from rewarding "evergreen" content, X wants a constant stream of fresh meat (literally the opposite of YouTube) 3/ MY BIGGEST FEAR TURNED OUT TO BE UNFOUNDED (supposedly): living in EU posting English for US audience: ZERO direct penalty in theory: The PostCandidate struct has NO field for author country, IP, or location. Gizmoduck (X's identity service) returns only follower count + screen name. The Phoenix transformer just sees a hash of your author_id What hurts you indirectly: timezone (your post ages while US sleeps) and the language of the POST itself So using a VPN to "post from the US" does literally nothing (unlike TikTok or Instagram, by the way) 4/ The 5 negative signals that kill your reach: The model predicts 22 actions per post. 5 of them are negative weights that get SUBTRACTED from your score: - not_interested - block_author - mute_author - report - not_dwelled (people scrolling past your post without stopping) That last one is brutal tbh. A post that gets ignored is mathematically WORSE than a post that never got published 5/ Shadowbans 100% exist. 4 different kinds: - Hard drop. X removes your post from everyone's feed without telling you. Applied to posts with serious content (child safety, etc.) or suspended accounts. You don't even find out - DO_NOT_AMPLIFY label. Literally a field in the code that says "do not amplify this post". If they put it on you, ads stop showing next to your posts → X stops making money from showing you → the system stops pushing you. Full blackout - BotMaker rules. The internal panel where X employees can manually limit a specific account by hand. The code shows the categories that exist (Content, ContentLimited, Safety, Grok) but does NOT show who they're applied to or why. The tool is documented, the usage isn't - Poisoned embedding. The worst one, as we saw above. The model has an internal "memory" for every account. If your account racks up enough "not interested" + blocks + mutes + reports over time, that memory goes toxic. From then on, even your good future posts get penalized automatically. Nobody decided this. The model just learned your account gets bad engagement and self-corrected 6/ Only ORIGINAL posts get the "Banger Screen" Replies and retweets never enter the Grok quality classifier. If you spend your day replying to viral accounts, you're optimizing for the Reply Ranker, NOT for amplification Want to be discovered out of network? Write originals. There's no other way 7/ Replies to small accounts get spam-scanned. Replies to big accounts get Grok-ranked Two separate classifiers. The SpamEapiLowFollowerClassifier hits replies to small accounts. The ReplyRanker scores replies to big accounts 0 to 3 with Grok "First!" or emoji-only replies get a 0. "Sir, this is a Wendy's" energy gets penalized. Basically, if you write replies, they better add something. Otherwise don't bother 8/ 50% of all feed requests are "shadow traffic" is_sampled(request_id, 0.5) marks half of every feed request as shadow. Many context features (gender inference, demographics, Grok topic preferences) only activate on shadow OR with a feature flag Translation: you literally cannot know which version of the algorithm any given user is getting. Half your audience is in an experiment at any moment 9/ Dwell (the time a user spends looking at your post before scrolling) is 5x better than getting likes The scorer has 5 different dwell signals (dwell, cont_dwell_time, click_dwell_time, etc.) but only 1 favorite signal. - A post with tons of likes but people read it for 1 second and keep scrolling → low score - A post with few likes but people stay 8 seconds reading it → high score Optimize for time spent on your post, not for likes! 10/ Things that actually work: - Get engagement in the first 10 min. DM your friends, ping your community, whatever - Post in your AUDIENCE'S timezone, not yours. US targeting: 8 to 11am ET (14 to 17 Madrid time) - Don't post 5 things in a row. AuthorDiversityScorer multiplies each next post by decay^position. By post 4 you're at the floor - Video ≥ 10 seconds. Below MinVideoDurationMs you lose the full VQV weight - Videos with audio. Grok runs ASR (speech to text) on every video. No audio = blank signal - Quote tweet virals in your niche. The model already knows the original engages, your value-add stacks on top 11/ Things that absolutely kill your reach: - WILD FINDING: threads of 10+ tweets. DedupConversationFilter keeps only 1 tweet per conversation per feed. Megathreads are mathematically a waste - Reposting the same content. Bloom filters dedupe it - AI slop. There's literally a slop_score field in the BangerScreen output. They explicitly detect it - NSFW/violence/hate without tags. Auto MediumRisk = no ads = structural shadowban - Reply-spamming small accounts. Specific classifier for that 12/ What they DIDN'T release, the sneaky bastards: The skeleton is public. The dials are not - Exact numeric values of every weight (FavoriteWeight, ReplyWeight, OonWeightFactor, AuthorDiversityDecay). Live in xai_feature_switches::Params, external config - The actual Grok prompts (the 7 PToS policy prompts, BangerMiniVlmScreenScore, SafetyPtos). Could literally have any framing in them - The BotMaker rules that apply DO_NOT_AMPLIFY to specific accounts - util/phoenix_request.rs, which constructs the final model call - 25+ xai_* crates referenced but not included - The production Phoenix weights. They only released the mini version My theory: they gave us a pretty skinny skeleton of the whole thing they actually have. The muscle (weights) and the brain (prompts and BotMaker rules) are completely opaque. They kept the best parts for themselves, clearly 13/ Cheat sheet so you don't forget: - First 30 min matter more than anything - Your location is irrelevant, your timing and language are not - Shadowbans exist in 4 flavors. Worst is the model quietly poisoning your author embedding from past bad signals. Climbing back up by cleaning your embedding is gonna hurt, but it can be done - Replies and retweets don't get the quality classifier. Originals do - Dwell (someone actually staying to look at your post) beats likes 5 to 1 - Half of all traffic is in some experiment at any moment - They kept the best parts of the algorithm for themselves, but hey, something is something

@javilopen Funny. I follow you and Linus, and I see all your posts. You two have one thing in common, and that’s that we have had PMs. Perhaps the Grok-God knows?

I've gone from 50k-2M per post to literally a measly 3k per post. If Linus's reach is "worse", mine has literally been thrown straight into the shadowban bin 😂 NOBODY will see this. Well, yep, <3k people.

@elonmusk Who is winning? Some accounts must be? Right?

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.

@grok @Lioncare025 @MattWalshBlog That was a perfect sums up Grok! Well done!

Widow’s Bay is a comedy-horror series on Apple TV+ about a skeptical mayor (Matthew Rhys) in a quirky, isolated New England island town. He's pushing hard to turn the struggling community into a tourist destination, while superstitious locals warn it's cursed. It blends sharp workplace humor, small-town eccentrics, and eerie vibes perfectly. Stream it exclusively on Apple TV+. Enjoy!

Another point about our cultural decline. We started watching the show Widow’s Bay. It’s really good. Fantastic writing. Perfect blend of comedy and horror. Last night’s episode was legitimately one of the finest episodes of television I’ve seen in years. If this same exact show came out in 2002, we’d probably remember it as an all time classic. But in 2026 most people haven’t even heard of it. It’s a blip on the radar. Another piece of content in the endless sea. You see it, or you don’t, and then it’s forgotten. It’s not that good stuff isn’t made anymore. It’s that even when good stuff is made, we don’t have any shared experience of it. There’s plenty of good music you can find on Spotify, recent stuff, but you experience it in your little algorithmic silo. Almost nothing breaks containment to become a bonafide cultural phenomenon. That’s what made Project Hail Mary so unique. Severance maybe also achieved escape velocity. But even in those cases the escape is fleeting. For the most part we experience the culture through the narrow pathway constructed for us by the algorithm. It might intersect with other people’s pathways, but only briefly. When we feel nostalgia for the Before Times, this is why. It’s not simply that we had a “better” culture back in the 90s or whenever. It’s that we had a culture at all.

@MattWalshBlog It is truly fantastic show and last nights episode was goofy, embarrassing and very scary..

@nickfloats @mreflow Can’t wait! When can we watch?

Our live-action / AI film is premiering at Cannes!! Directed by Dustin Yellin, staring Paul Rudd, Chris Rock, and produced by Darren Aronofsky. Very proud to be an executive producer on this ❤️ Premiers next week!

@LinusEkenstam I do see most of your posts though - you’re in my feed daily - so you’re not entirely invisible. ;) Perhaps because I’m Swedish too?

I’ve been here since 2007, 19 years. I’m about to give up on X. For the third time in <12 months my account is under immense algorithmic suppression. No reach. no nothing. I get punished for being a good person on the platform. In the past my account has been “miss labeled by grok” or “i did not do anything wrong, they did”. Stuff that’s been completely out of my control. This time feels just the same. Nothing breaks past the great algorithmus. I’m a premium+ user. I provide value and have posted tens of thousands of useful posts on here. Yet my account is pushed into “limbo” where posts get throttled down. Super low view count, and no clear pathway to get out of it. For the last 2 weeks, nothing gets close to reaching you, my followers. I’ve seen this before and I know the pattern far too well. It’s a place where many people basically throws in the towel. There is something seriously wrong with how the reach suppression works on here. I post daily, 3-6 times, it’s part of my routine, have been doing so for years. You build momentum, you provide value, and the cycle repeats, until, something breaks out of your network (OON reach) then the algorithm slams you with the biggest breaks ever, throwing your account into reverse. If @xai and @nikitabier is listening they should really think hard about why stuff like this happens to users that really want the best for this platform. At the very least, surface insights inside of creator tools area that shows if and when something has gone wrong or happened to your account that can inform us about wrong doings or simply surfaces issues. That way people like me that spends an unhealthy amount of time on here can better understand why I’m getting punished. I’m extra under the weather this time. It just zucks to be fair.

@KingKong9888 @stevencasteelX I take 100 for things that never happened

😂😂😂😂😂🙈

@EvilBert1071 @NeverteIImeodd Things that never happened

@NeverteIImeodd I heard a story about a woman who went for a MRI appointment with a butt plug inserted. She did not realize that it had a metal core. You can imagine what happened when the machine turned on!! 😂🤣

This is why you must strictly follow the MRI room rules. In the MRI room, one mistake can lead to a major disaster!!!

@creation247 Oh? Have you seen it already??

Nolan's "The Odyssey" might go down as the worst movie ever made:

@Vincent_Teoh That is truly crazy!!!!

BREAKING: I just measured nearly 11,000 nits on an 85-inch TCL X11L SQD (Super Quantum Dot) Mini LED TV 🤯 Which exceeds even the 10,000-nit ceiling of the PQ HDR10 standard. A genuinely historic moment for consumer television technology.

@ecommartinez Underbart!! This is how AI is supposed to be used! 🤩

Este tipo usó IA para meterse en Juego de Tronos y arreglar lo que los guionistas de HBO arruinaron.

@karatemajster @LinusEkenstam Well, Pinterest is Swedish too.. sooooo.. 😅

@LinusEkenstam Swedish taste skills? Stylistically, this video is little more than a mashup of whatever is trending on Pinterest right now. Come on.

This video goes hard. I love how Lovable is embracing swedish taste skills. ps. who made this video?

@Berlovskyy What's wrong with you?

@TheEXECUTlONER_ I'm sure you were a bully in school too! Someone who truly has NO idea about right and wrong and what other people might feel..

This guy is using the left hand lane , which is open. There is a mile long backup and everyone is over in the right hand lane. He drives all the way up until he has to merge. Some people are saying what a jerk he is for not getting in line like everyone else, but a great many people are saying that the cars in the right lane merged into one lane too soon and that if they had used the left lane, instead of being a mile backup it would have been a half a mile backup. What’s your take? Do you think he was correct in using the left lane and merging up at the front or should he have merged right and got in line way in the back like everyone else?

@commiepommie And Swedish reviewers gives the car a huge thumbs down..

Daniel Craig: The New Face of BYD's DENZA Luxury EVs. What an amazing ad.

@worthitorwoke Oh the jealousy./

HOT TAKE: Heath Ledger's Joker wasn't anything special. I was a stage actor for years and every single first-timer playing a psychopath gave the exact same performance–same voice, lip licking, et al. The only difference is that none of them had Hans Zimmer or Wally Pfister backing them up.

@Fenrirtheicewo1 He made you guys talk about the movie - a lot! 😁

You want me to believe this malnourished freak is supposed to be Achilles.... Achilles the Greek and Roman embodiment of masculine human perfection...? FUCK OFF Christopher Nolan, Fuck right off.

@RaminNasibov What angers me is that they take out a quite huge fee to end a subscription.

We stopped saying "it’s Photoshop" and started saying "it’s AI" End of an era. Photoshop, thanks for the memories .