Hamel Husain ✓

@HamelHusain · Looking at the data · joined 15 Sep 2012

Evals Evals Evals - https://t.co/Zrmp6LRd9c About Me: https://t.co/P6WyeKkyTa

56 467Followers

2 662Following

17 466Posts total

673.6KViews on collected posts

โพสต์ล่าสุด

Hamel Husain ✓@HamelHusain16 ชม.

I recommend grabbing these skills that @sh_reya and I created and at the very least doing an /eval-audit of your existing pipeline. We've found that people often find low hanging fruits! https://t.co/AkSq3NqtiJ 17.6K views · 168 likes · 19 reposts · 8 replies Open on X →

Hamel Husain ✓@HamelHusain17 ชม.

Is Slop Dead? (Testing Writing With 5.5 Opus) https://t.co/4H7xOhhsHi 2.4K views · 15 likes · 1 reposts · 3 replies Open on X →

Hamel Husain ✓@HamelHusain21 ชม.

Pro tip: Install this new evals skill from @HamelHusain and @sh_reya, it'll save you many hours and a lot of mistakes https://t.co/RpWeLaxgQm https://t.co/uYo3fLsRIB

146.2K views · 1K likes · 65 reposts · 19 replies Open on X →

Hamel Husain ✓@HamelHusain23 ชม.

Q: What should you do when your "gold" eval dataset becomes stale? A: Use regular error analysis to find new problems. Keep updating your evals as your product and users change. https://t.co/L1AI4XrR4f https://t.co/6LfvxgiSEq

2.9K views · 62 likes · 6 reposts · 17 replies Open on X →

Hamel Husain ✓@HamelHusain23 ชม.

This post was a labor of love! We’ve distilled thousands of hours of work on AI Evals into a 30 min read + skills you can use to quickly uncover errors in your product. https://t.co/RuxMypR2Gd BTW in addition to high quality content, Lenny effectively **pays you** in AI 40.6K views · 364 likes · 42 reposts · 13 replies Open on X →

Hamel Husain ✓@HamelHusain22 Sep

Evals have been coming up more and more in my conversations with podcast guests and PM friends. Nearly half of the 25 awesome PM job openings I shared last week ask for experience writing evals. And leading companies keep sharing what investing in evals bought them: — @tryramp h

265.2K views · 546 likes · 42 reposts · 46 replies Open on X →

Hamel Husain ✓@HamelHusain11 Sep

It's cool that there is more interest in eval tools! Some opportunities for improvement: 1. Right now, this workflow tries to quiz you up front about your recollection of your experience with a plugin. It would be better if it was more "in-situ", meaning you could give 19.6K views · 183 likes · 16 reposts · 37 replies Open on X →

Hamel Husain ✓@HamelHusain4 Sep

. @isaac_flath and I are going to see if the slop prompt is good and do some evals. (also first time trying to stream haha). https://t.co/boPHM4nRR5 https://t.co/UpRoIJ7vxo

4.4K views · 14 likes · 0 reposts · 13 replies Open on X →

Hamel Husain ✓@HamelHusain4 Sep

I love how Teresa is merging product discovery with evals. I think its a powerful combination! I started learning about product discovery b/c of Teresa and I think its a great skill for any engineer as it helps you focus on what to build. Highly recommend checking out her 47.4K views · 184 likes · 10 reposts · 14 replies Open on X →

Hamel Husain ✓@HamelHusain3 Sep

AI evals have been the "it" skill for product teams for over a year. I've even called evals a new discovery habit. But I still meet product teams who only have a vague idea of what evals are. And it's not their fault. Most of the writing on this topic is intended for engineers 62.7K views · 286 likes · 24 reposts · 18 replies Open on X →

Hamel Husain ✓@HamelHusain3 Sep

Amazing advertising 4.2K views · 8 likes · 0 reposts · 3 replies Open on X →

Hamel Husain ✓@HamelHusain12 Aug

Over the summer, @sh_reya and I hosted 13 sessions on AI Engineering topics like retrieval, post-training, inference, and evals. I've summarized all the sessions, organized by theme, with links to the source materials. Warning: I've tried to pull the most important ideas from

60.3K views · 769 likes · 92 reposts · 29 replies Open on X →

เทียบกับบัญชีขนาดเดียวกัน

12 โพสต์จาก 90 วันที่ผ่านมา เทียบกับช่วง 10K–100K ผู้ติดตาม แสดงในวงกว้าง แต่มีผู้ชมตอบสนองน้อย.

ยอดดูมัธยฐาน30 103บัญชีนี้997ค่ามัธยฐานของ 10K–100K

การเข้าถึง, %53.31%บัญชีนี้3.84%ค่ามัธยฐานของ 10K–100K

การมีส่วนร่วม, %0.77%บัญชีนี้1.52%ค่ามัธยฐานของ 10K–100K

ตัวชี้วัด	บัญชีนี้	ค่ามัธยฐานของ 10K–100K	อัตราส่วน
ยอดดูมัธยฐานต่อโพสต์	30 103	997	30.2×
การเข้าถึง (ยอดดู ÷ ผู้ติดตาม)	53.31%	3.84%	13.9×
อัตราการมีส่วนร่วม	0.77%	1.52%	0.51×

บัญชีอื่นในช่วงนี้ → เปรียบเทียบกับบัญชีอื่น → ค่าอ้างอิงเหล่านี้คำนวณอย่างไร →

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

60.3K12 Aug

4.2K3 Sep

62.7K

47.4K4 Sep

4.4K

19.6K11 Sep

265.2K22 Sep

40.6K

2.9K

146.2K

2.4K

17.6K

Last 12 collected posts, oldest on the left. The scale is logarithmic: one post can outrun the rest a hundred times over.

Engagement rate per post

1.48%12 Aug

0.26%3 Sep

0.53%

0.44%4 Sep

0.61%

1.20%11 Sep

0.25%22 Sep

1.03%

2.90%

0.76%

0.78%

1.12%

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

What the audience does

Likes32.6%3 624 in total

Reposts2.9%317 in total

Replies2.0%220 in total

Quotes0.3%36 in total

Bookmarks62.2%6 906 in total

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

Followers by day

13 Sep

Daily snapshots since 13 Sep 2026; the dashed line is the starting count.