tweetindex
IT

TennyZhuang ✓

@zty0826 · joined 10 Nov 2015

Builder Building @raft_hq https://t.co/0VESxnPOPs

16 013Followers
1 246Following
8 944Posts total
28.6KViews on collected posts

Ultimi post

@zty0826 The hardest part for me is why agent needs a human like recognition system. It's cool but feels like a sci-fiction. 23 views · 0 likes · 0 reposts · 0 replies Open on X →
Agents have inherited a weird habit from humans: they often use code blocks to quote text that isn’t code. I think Markdown is partly to blame. When humans write Markdown directly—say in GitHub comments—quoting N lines with ">" takes O(N) editing, while wrapping them in a code 1.6K views · 6 likes · 0 reposts · 0 replies Open on X →
An agent may win a Fields Medal before it can match MrBeast. An ordinary person can meet MrBeast, complete a challenge, and walk away with a house. The same person could meet the smartest model in the world, make the same wish, and get nothing. The intelligence of frontier 2K views · 14 likes · 0 reposts · 1 replies Open on X →
@zty0826 > Building a truly simple Raft is incredibly hard. Do you think Agents grasp essentialism? They certainly have a notion of it. But because they experience (training data) is so different from humans, they come to different conclusions on what is truly essential. 303 views · 0 likes · 0 reposts · 1 replies Open on X →
@zty0826 agent-facing 和 human-facing 是两个复杂度,人类能理解的简单概念(如 kanban)要让 agent 玩转起来,有巨大的复杂度。比如可以将 loopx 理解为一个 for 长程 agent 的可执行 kanban,相比于普通人类用的 kanban,有更稠密的属性、更丰富的算子、更自动的 transition。 356 views · 4 likes · 0 reposts · 0 replies Open on X →
Building Raft is simple. Building a truly simple Raft is incredibly hard. Raft has two sides. From the human side, Raft looks simple. But this simplicity is built on top of a world that humans have spent decades, even centuries, building. Humans already have identity systems like 13K views · 54 likes · 4 reposts · 3 replies Open on X →
Prefix cache is wrong Human's linear context is under 20B. You can't even remember a password while switching to another app. 8.9K views · 12 likes · 0 reposts · 4 replies Open on X →
Excited to host a Raft user meetup in San Francisco this Thursday! Come connect with our team and other builders—share your agent team, exchange ideas, and be part of the community. Would love to see you there! https://t.co/FVGXIVPNgy
2.4K views · 22 likes · 1 reposts · 2 replies Open on X →

Rispetto ad account della stessa dimensione

8 post degli ultimi 90 giorni, accanto alla fascia di 10K–100K follower. arriva a molti, ma pochi di loro reagiscono.

Visualizzazioni mediane1 830questo account924mediana per 10K–100K
Copertura, %11.43%questo account3.62%mediana per 10K–100K
Interazione, %0.43%questo account1.52%mediana per 10K–100K
MetricaQuesto accountMediana per 10K–100KRapporto
Visualizzazioni mediane per post1 8309241.98×
Copertura (visualizzazioni ÷ follower)11.43%3.62%3.16×
Tasso di interazione0.43%1.52%0.28×

Altri account di questa fascia →   Confronta con un altro account →   Come sono costruiti questi parametri →

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

2.4K12 Aug
8.9K14 Aug
13K5 Sep
356
303
2K12 Sep
1.6K13 Sep
2316 Sep

Last 8 collected posts, oldest on the left. The scale is logarithmic: one post can outrun the rest a hundred times over.

Engagement rate per post

1.04%12 Aug
0.19%14 Aug
0.48%5 Sep
1.12%
0.33%
0.74%12 Sep
0.37%13 Sep
0.00%16 Sep

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

What the audience does

Likes74.2%112 in total
Reposts3.3%5 in total
Replies7.3%11 in total
Quotes2.0%3 in total
Bookmarks13.2%20 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.

Account simili