Mridul S

26 posts

Mridul S

Mridul S

@singhai

Building.

San Francisco Katılım Eylül 2024
94 Takip Edilen1.2K Takipçiler
xjdr
xjdr@_xjdr·
many many years ago, i worked on recsys and personalization systems. i finally looked at the xai algorithm and i do not understand it at all. its the normal candidate generation, pruning, reranking but without the core parts like collaborative filtering / matrix factorization and any type of simclustering like functionality seems missing? i didnt spend that much time looking at it but the best i could tell grok does the feature engineering in a black box (which is where all the magic is) and they arent using any sort of persona graph anymore? its very possible (even likely) that i am just way behind the SOTA after all these years but from where im sitting this seems like a bad design (even if the implementation is perfect)
English
19
12
313
25K
Andrew
Andrew@Dastan_2·
@santiagomed hi! please could you pass this on to the relevant people in your team so that they can fix this bug
English
1
0
0
125
Santiago
Santiago@santiagomed·
We've started rolling out the brand-new Developer Console for the X API. We've designed it to 10x your developer experience and made it much easier to get started building. Please send any feedback my way!
Santiago tweet media
English
35
21
185
21.3K
Mridul S
Mridul S@singhai·
@natevanben @turbopuffer Thanks. Reranking helps, but recall loss in first-stage retrieval would still cap overall search quality; missing candidates cannot be recovered downstream.
English
1
0
0
100
Nathan VanBenschoten
Nathan VanBenschoten@natevanben·
@singhai @turbopuffer That said, we often see that larger top_k values are paired with the use of a reranking model to filter the large top_k set down further. As a result, a small recall loss for first pass retrieval is usually not a problem.
English
1
0
1
140
turbopuffer
turbopuffer@turbopuffer·
tpuf ANN v3, for when you need to index the entire web 100B+ vectors @ 50ms p50 / 200ms p99 latency blog: tpuf.link/ann-v3
English
4
13
119
22.8K
“paula”
“paula”@paularambles·
you: annoyed by the genre of post me: annoyed by the fact that i was led to believe there is good sichuan food in sf
English
13
0
213
10.2K
Danielle Fong 🔆
Danielle Fong 🔆@DanielleFong·
why is @X search broken? it no longer ranks literal string matches. it seems to have a semantic search instead that doesn't encode string literals high enough ? @nikitabier
English
4
2
18
1.1K
Wes
Wes@wmorrill3·
Have seen this a ton in my feed and it honestly gets tiring to see the same media 27 different times just because everyone is trying to squeeze their monetization juice from good content without adding anything of value. X should do automatic attribution on media to the original poster then quote posts that are adding value will still happen but those just reposting with no value add won't have any incentive to do it. Would help ensure original content creators get a fair payout while having a side benefit to declutter the feed. @nikitabier we need @grok on it
Wes tweet media
APOCTOZ@Apoctoz

@elonmusk @signulll @nikitabier Fix the relationship between content creators and content aggregators. Currently, content aggregators get 100% of the monetization and credit. Embedding someone else’s work with a slight rephrasing or superfluous comment currently demonetizes them and almost everyone is doing it.

English
60
25
750
47.8K
Cybertruck
Cybertruck@cybertruck·
Who called it Sentry Mode and not Cyber Security
English
126
246
4.3K
115.9K
Mridul S
Mridul S@singhai·
@rpoo I prefer taking the yellow cabs instead of navigating the maze at SFO.
English
0
0
1
170
Ross
Ross@rpoo·
airport ride share pickups seem to converge towards looking like refugee camps
English
12
6
160
14.3K
Mridul S
Mridul S@singhai·
@allegrajacchia How about discussing main characters for various topics on that popular microblogging platform?
English
0
0
3
142
Allegra Jacchia
Allegra Jacchia@allegrajacchia·
Thanksgiving dinner topics this year: – Epstein files – Mamdani – “So… why aren’t you married yet?” – “And kids? Timeline??” – The White House ballroom / Trump – Explaining AI to grandpa – DWTS finale (risky)
English
20
4
113
6.6K
jackson ⁖
jackson ⁖@zeroxjackson·
engineers & founders, please share your advice for getting fit and staying fit while spending 10-12hr/day working on the computer.
English
1.5K
105
3.7K
2.5M
Ari Hoffman
Ari Hoffman@thehoffather·
"Jewish" Voices for Peace is hiding its location using a VPN Why would a local Hamas supporting activist group with ties to terror hide its location?
Ari Hoffman tweet media
English
4
12
51
2K
Shlomi Atar
Shlomi Atar@shlomiatar·
@ZuckermanRoy חשבונות ממשלתיים (אפורים) לא מקבלים את הפיצ׳ר למיטב הבנתי
עברית
1
0
13
619
Roy Zuckerman
Roy Zuckerman@ZuckermanRoy·
למה אין למירי רגב נתוני מיקום?
Roy Zuckerman tweet media
עברית
22
0
48
4.2K
Mridul S
Mridul S@singhai·
@DHSgov The facts are true, the rumors are fake. (We built this)
Mridul S tweet media
English
51
4
120
125.3K
Homeland Security
Homeland Security@DHSgov·
I can’t believe we have to say this, but this account has only ever been run and operated from the United States. Screenshots are easy to forge, videos are easy to manipulate. Thank you for your attention to this matter.
Nikita Bier@nikitabier

@lporiginalg This is fake news. Location was not available on any gray check account at any point. Furthermore, the DHS has only shown IPs from the United States since account creation.

English
6K
2.2K
31.4K
31M
George
George@georgecurtiss·
twitter/x search fucking sucks @nikitabier please fix
English
13
0
31
5.2K
Nikita Bier
Nikita Bier@nikitabier·
You're only as good as your last feature
English
688
104
2.2K
197.8K
Tetsuya3850
Tetsuya3850@Tetsuya3850·
大戸屋と油そばと牛タンが食べたいですね
日本語
1
0
2
384