tweetindex
TR

Chip Huyen

@chipro · San Francisco, CA · joined 30 Jun 2008

@aisysbooks @goodailist AI Engineering: https://t.co/94dv4uTU1H Designing MLSys: https://t.co/G81hL2dWmr Reading @chipslib

146 641Followers
720Following
586Posts total
661.9KViews on collected posts

Son gönderiler

i'm researching best practices for skills. what's the most number of skills you've had installed for your agents? 16.3K views · 42 likes · 2 reposts · 40 replies Open on X →
real question: why does gpt 5.6 over engineer so much? 138.1K views · 1K likes · 27 reposts · 235 replies Open on X →
what's a good model tiering system? i'm sick of telling my agent orchestrator things like: "for Claude, use model X, for OpenAI, use model Y, etc." i want to be able to tell my orchestrator: "use models tier ..." for this kind of task 32.1K views · 184 likes · 9 reposts · 49 replies Open on X →
that's the problem he should've sent them in all caps https://t.co/zqNe1FPI7I
19.3K views · 99 likes · 11 reposts · 4 replies Open on X →
@chipro great overview. looking at the current state of agents a planner is the centerpiece of a multi agent strategy cauz the stuff doesn’t work well enough in a multi turn fashion.and like you said that is as easy as prompting it. we don’t really need abstractions for agents. 842 views · 2 likes · 0 reposts · 1 replies Open on X →
@chipro thanks huyen for writing this. time to grab coffee and dig into this cool guide. solid work 😌 896 views · 2 likes · 0 reposts · 0 replies Open on X →
@chipro I found the high level definition of agent of @swyx quite concise "agent = llm + memory + planning + tools + while loop" (some objective would be implied here) https://t.co/KJBP9rDj52 for a lightweight agent library I liked the approaches of OpenAI (Swarm 8.6K views · 38 likes · 2 reposts · 1 replies Open on X →
My 8000-word note on agents: https://t.co/x5IzSUwO5b Covering: 1. An overview of agents 2. How the capability of an AI-powered agent is determined by the set of tools it has access to and its capability for planning 3. How to select the best set of tools for your agent 4. 417.7K views · 2.9K likes · 459 reposts · 69 replies Open on X →
@simonw agent = llm + memory + planning + tools + while loop https://t.co/qEd8jixioW 27.9K views · 285 likes · 11 reposts · 13 replies Open on X →

Aynı büyüklükteki hesaplara karşı

Son 90 güne ait 4 gönderi, 100K–1M takipçi aralığıyla yan yana. geniş kitleye gösteriliyor, ama izleyenlerin azı tepki veriyor.

Medyan görüntülenme25 728bu hesap5 912100K–1M için medyan
Erişim, %17.55%bu hesap1.58%100K–1M için medyan
Etkileşim, %0.67%bu hesap1.04%100K–1M için medyan
ÖlçütBu hesap100K–1M için medyanOran
Gönderi başına medyan görüntülenme25 7285 9124.35×
Erişim (görüntülenme ÷ takipçi)17.55%1.58%11.1×
Etkileşim oranı0.67%1.04%0.65×

Bu aralıktaki diğer hesaplar →   Başka bir hesapla karşılaştır →   Bu kıyas değerleri nasıl kuruluyor →

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

27.9K7 Oct
417.7K7 Jan
8.6K
896
842
19.3K10 Aug
32.1K17 Aug
138.1K25 Aug
16.3K

Last 9 collected posts, oldest on the left. The scale is logarithmic: one post can outrun the rest a hundred times over.

Engagement rate per post

1.11%7 Oct
0.82%7 Jan
0.48%
0.22%
0.36%
0.59%10 Aug
0.75%17 Aug
0.92%25 Aug
0.51%

Reactions — likes, reposts, replies and quotes — divided by views. Median for 100K–1M accounts is 1.04%.

What the audience does

Likes48.4%4 548 in total
Reposts5.5%521 in total
Replies4.4%412 in total
Bookmarks41.7%3 919 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.

Benzer hesaplar