Addy Osmani ✓
@addyosmani · Mountain View, CA · joined 26 Apr 2009
Claude Code @anthropicai
422 275Followers
2 771Following
29 193Posts total
1.6MViews on collected posts
Latest posts
Looking for new posts…
@addyosmani Blast radius estimation is one of the meanginful AI use cases
704 views · 3 likes
· 0 reposts · 0 replies
Open on X →
@addyosmani Are there effective ways to objectively assess blast radius? Multi-model evaluation as well?
2.1K views · 2 likes
· 0 reposts · 1 replies
Open on X →
@addyosmani same playbook, shipping it as mergeCraft.
agents do the first pass. humans cover blast radius. approval stays a human call.
https://t.co/uWj8uCjltp
101 views · 2 likes
· 0 reposts · 0 replies
Open on X →
How I do code reviews these days: more code = more selective human review i.e. don't read all the code.
1. Every PR gets a multi-agent first pass. It should find bugs, verify them, rank by severity, suggest fixes. Approval stays a human call on anything that matters.
2. Low
146.5K views · 1K likes
· 81 reposts · 79 replies
Open on X →
If you’ve stopped doing human code reviews: how is it going?
If you’re still doing them: how are you able to keep up with the explosion of code + PRs, and how do you prioritise what to review “properly”?
501.6K views · 1.3K likes
· 63 reposts · 330 replies
Open on X →
How to maximize the value of your Claude Code sessions: https://t.co/YGa8swOX6v
Solid guidance on managing token efficiency and keeping context windows focused by @lydiahallie https://t.co/nU2lFYWoom
37.3K views · 580 likes
· 54 reposts · 37 replies
Open on X →
"Good culture is a prerequisite for everything else. But when it comes to AI, it amplifies everything you already have"
https://t.co/FSZvwPp6Jo by @gregorojstersek
A team's culture determines whether speed compounds or just gets you to the wrong place sooner. https://t.co/11Ao
13.5K views · 136 likes
· 20 reposts · 8 replies
Open on X →
Anthropic published a new guide on how to strip the "Claude" out of Claude's writing (e.g. mannered prose)
Here's an official de-flavoring prompt for Fable 5.1, which already cuts back on AI boilerplate/jargon:
https://t.co/yfpWUtdT8h https://t.co/RT4Z6FzK8V
173.4K views · 1.7K likes
· 106 reposts · 79 replies
Open on X →
"The most important skill in prompting is expertise in the domain you’re prompting for"
https://t.co/Dgme0HcL2z
Sometimes the human is the bottleneck. A good reminder LLMs are a force multiplier if you're skilled and to build this domain expertise if you don't have it yet. htt
28.8K views · 525 likes
· 69 reposts · 35 replies
Open on X →
@addyosmani I’d like to redefine “AI slop”. It’s not so much the output, that is getting better than humans. It’s that without reviewing and applying judgement and taste it becomes “slop”.
1.2K views · 3 likes
· 0 reposts · 0 replies
Open on X →
@addyosmani I used AI because of non native English. So whatever I want to say I just use for polishing and rephrasing is correct manner so that it will not create confusion or misunderstanding. So thoughts are still mine but wrapper will be done by AI.
2.4K views · 3 likes
· 0 reposts · 1 replies
Open on X →
@addyosmani The people who paste AI without reading are the ones who need this most
They just wont read it either
1.4K views · 3 likes
· 0 reposts · 1 replies
Open on X →
"Don't paste the AI, please"
"The world is full of people who don't want to read or think things through. Don't be one of them."
https://t.co/aCuUH0Sgpo https://t.co/HpbkAzaWCY
71.2K views · 1.1K likes
· 150 reposts · 51 replies
Open on X →
Mastery still comes from doing the reps.
Before agents, I got my reps as part of writing code: try different approaches out, debug what went wrong, review other’s code, read a lot. Agents can skip much of that work, so building your reps has to be deliberate.
If I was new to ht
16.2K views · 172 likes
· 15 reposts · 20 replies
Open on X →
@addyosmani Perfection is the handmaiden to procrastination.
724 views · 5 likes
· 0 reposts · 0 replies
Open on X →
@addyosmani Absolutely love this reminder, especially as we step into a new year. 'First do it, then do it right, then do it better.' Taking that initial step, imperfect as it may be, is the catalyst for progress.
2.2K views · 7 likes
· 0 reposts · 0 replies
Open on X →
@addyosmani @rachelnabors Totally
Iterate
Iterate
Iterate
Kaizen
5.5K views · 22 likes
· 1 reposts · 2 replies
Open on X →
"First do it, then do it right, then do it better."
Just start. The journey to success often begins with a single step, but that first step can be the hardest to take. It's easy to get caught up in the fear of failure or the desire for perfection, but I hope this quote I first h
550.4K views · 3.2K likes
· 660 reposts · 129 replies
Open on X →
@smashingmag @jecfish Woohoo. Very well deserved, Jec! 👏
2.2K views · 2 likes
· 0 reposts · 0 replies
Open on X →
Our Person of the Week is a DevRel Engineer at Google working on Chrome DevTools and Browser Automation. Please give a warm round of applause for... Jecelyn Yeen!
Thank you for everything you do for the community, dear @jecfish!
#smashingcommunity https://t.co/B5jihLl22H
34.1K views · 74 likes
· 16 reposts · 5 replies
Open on X →
Against accounts of the same size
14 posts from the last 90 days, next to the 100K–1M follower range. shown to more people than peers of the same size.
Median views14 854this account5 983median for 100K–1M
Reach, %3.52%this account1.49%median for 100K–1M
Engagement, %0.95%this account0.93%median for 100K–1M
| Metric | This account | Median for 100K–1M | Ratio |
|---|---|---|---|
| Median views per post | 14 854 | 5 983 | 2.48× |
| Reach (views ÷ followers) | 3.52% | 1.49% | 2.36× |
| Engagement rate | 0.95% | 0.93% | 1.02× |
Others in this range → Compare with another account → How these benchmarks are built →
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
16.2K31 Aug
71.2K
1.4K
2.4K
1.2K
28.8K2 Sep
173.4K3 Sep
13.5K
37.3K
501.6K6 Sep
146.5K7 Sep
101
2.1K
704
Last 14 collected posts, oldest on the left. The scale is logarithmic: one post can outrun the rest a hundred times over.
Engagement rate per post
1.28%31 Aug
1.90%
0.29%
0.17%
0.26%
2.21%2 Sep
1.10%3 Sep
1.24%
1.80%
0.34%6 Sep
0.80%7 Sep
1.98%
0.14%
0.43%
Reactions — likes, reposts, replies and quotes — divided by views. Median for 100K–1M accounts is 0.93%.
What the audience does
Likes49.9%9 924 in total
Reposts6.2%1 235 in total
Replies3.9%778 in total
Quotes0.5%109 in total
Bookmarks39.4%7 824 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.
Similar accounts
Angel Youngs😇 ✓
@AngelYoungsxxx
844.5K followers
· 11.8K posts
وزارة الدفاع العراقية ✓
@modmiliq
844.5K followers
· 18.7K posts
DNI Tulsi Gabbard ✓
@DNIGabbard
844.3K followers
· 477 posts
Marvel Rivals ✓
@MarvelRivals
844.2K followers
· 1.9K posts
NYT Fashion ✓
@NYTFashion
844.1K followers
· 56.1K posts
Impractical Jokers
@JokersTBS
844K followers
· 38.6K posts
Tendencias en Argentina ✓
@porqueTTarg
844K followers
· 71.3K posts
وكالة شهاب للأنباء ✓
@ShehabAgency
843.9K followers
· 540.5K posts