ali ✓

@waterloo_intern · San Francisco · joined 06 Oct 2024

ml research, kernels, and the occasional peer-reviewed shitpost inference @baseten || eng @uwaterloo

35 544Followers

114Following

689Posts total

3.3MViews on collected posts

Posts recentes

ali ✓@waterloo_intern6 Sep

beautiful intro to spec dec need the prompt that made the visuals asappp 26.1K views · 138 likes · 4 reposts · 6 replies Open on X →

ali ✓@waterloo_intern6 Sep

Introducing 𝐒𝐩𝐞𝐜𝐮𝐥𝐚𝐭𝐢𝐯𝐞 𝐃𝐞𝐜𝐨𝐝𝐢𝐧𝐠: 𝐇𝐨𝐰 𝐈𝐭 𝐄𝐯𝐨𝐥𝐯𝐞𝐝, 𝐖𝐡𝐞𝐧 𝐈𝐭 𝐒𝐭𝐚𝐲𝐬 𝐋𝐨𝐬𝐬𝐥𝐞𝐬𝐬, 𝐚𝐧𝐝 𝐖𝐡𝐚𝐭'𝐬 𝐍𝐞𝐱𝐭. An interactive tutorial @Madisonkanna and I built for the NeurIPS Education Track. Every LLM you use generates one token at a 107K views · 783 likes · 102 reposts · 33 replies Open on X →

ali ✓@waterloo_intern15 Aug

“rumor-mills we’re following have been mentioning how the data industry is taking off in China — very much driven by American data companies selling to Chinese model labs. This could look like Chinese labs buying many of the same RL environments that are used by American frontier 15.7K views · 69 likes · 5 reposts · 7 replies Open on X →

ali ✓@waterloo_intern14 Aug

for my final post as @waterloo_intern, i'd like to ‘outroduce’ myself. it takes exactly 4 years and 8 months to make a waterloo intern. today is the last day of mine. the full life cycle, in four stages, is as follows: 1- interview hazing 2- cali or bust 3- inflection point h

51.6K views · 754 likes · 20 reposts · 47 replies Open on X →

ali ✓@waterloo_intern13 Aug

kimi paper readers in SHAMBLES after reading the deepseek paper (me, it’s me, and at least one more (henry, below)) as in, if you can get just as good (actually better of) a model with swa, how much of k3’s success can be attributed to its use of kda vs the remaining tricks, and 53.8K views · 481 likes · 16 reposts · 18 replies Open on X →

ali ✓@waterloo_intern13 Aug

I (very embarrasingly) only realize sliding window attention also makes kv cache bounded (i.e. indep of seq len), similar to KDA sure maybe it uses more kv cache than KDA but its not a magnitude more 62K views · 105 likes · 1 reposts · 2 replies Open on X →

ali ✓@waterloo_intern27 Jun

@waterloo_intern @IKorovinsky Very soon this will be your average waterloo first year project 🫡 833 views · 6 likes · 0 reposts · 1 replies Open on X →

ali ✓@waterloo_intern26 Jun

@waterloo_intern absolutely insane work. This speed unlocks a whole category of products in AI Video Generation! 1.1K views · 11 likes · 0 reposts · 1 replies Open on X →

ali ✓@waterloo_intern26 Jun

@waterloo_intern bro said notes and dropped an entire textbook 1.9K views · 17 likes · 0 reposts · 1 replies Open on X →

ali ✓@waterloo_intern26 Jun

https://t.co/qe2HpEQZPd 3M views · 852 likes · 141 reposts · 35 replies Open on X →

Em comparação com contas do mesmo porte

6 posts dos últimos 90 dias, ao lado da faixa de 10K–100K seguidores. aparece para muita gente, mas poucos desses espectadores reagem.

Mediana de visualizações52 696esta conta924mediana para 10K–100K

Alcance, %148.26%esta conta3.62%mediana para 10K–100K

Engajamento, %0.72%esta conta1.52%mediana para 10K–100K

Métrica	Esta conta	Mediana para 10K–100K	Proporção
Mediana de visualizações por post	52 696	924	57.0×
Alcance (visualizações ÷ seguidores)	148.26%	3.62%	41.0×
Taxa de engajamento	0.72%	1.52%	0.47×

Outras contas desta faixa → Comparar com outra conta → Como estas referências são construídas →

Growth & engagement

How the posts we collected actually performed: views and reaction rate post by post, what the audience did with them, and where the follower count goes.

Views per post

3M26 Jun

1.9K

1.1K

83327 Jun

62K13 Aug

53.8K

51.6K14 Aug

15.7K15 Aug

107K6 Sep

26.1K

Last 10 collected posts, oldest on the left. The scale is logarithmic: one post can outrun the rest a hundred times over.

Engagement rate per post

0.04%26 Jun

0.94%

1.13%

0.84%27 Jun

0.18%13 Aug

0.96%

1.60%14 Aug

0.52%15 Aug

0.87%6 Sep

0.57%

Reactions — likes, reposts, replies and quotes — divided by views. Median for 10K–100K accounts is 1.52%.

What the audience does

Likes47.7%3 216 in total

Reposts4.3%289 in total

Replies2.2%151 in total

Quotes0.7%48 in total

Bookmarks45.1%3 041 in total

Share of every reaction we collected for this account. Replies mean argument, reposts mean endorsement, bookmarks mean the post was worth keeping.

The follower curve appears once this account has two daily snapshots — we take one a day, and this one is on its first.

Posts recentes

Em comparação com contas do mesmo porte

Growth & engagement

Views per post

Engagement rate per post

What the audience does

Contas semelhantes