tweetindex
ES

Thariq ✓

@trq212 · SF via Toronto · joined 11 Aug 2011

Claude Code @anthropicai. prev YC W20, @spc, @medialab

353 966Followers
1 912Following
6 097Posts total
39MViews on collected posts

Últimas publicaciones

@trq212 Yay! This is the way. Come to the light 189.4K views · 4.3K likes · 44 reposts · 96 replies Open on X →
You can see the source for the mod here! https://t.co/ZGJxRbh33b 255.4K views · 566 likes · 13 reposts · 23 replies Open on X →
AGENTS.md support is built off of Claude Code mods, our upcoming way to customize the Claude Code harness. This is a built-in mod, but you’ll be able to build custom versions of project instructions yourself as you’d like too. 340.1K views · 1.1K likes · 28 reposts · 50 replies Open on X →
We're adding support for AGENTS.md to Claude Code. Starting today in version 2.1.277, if there is no CLAUDE.md in a folder, Claude will check for and use AGENTS.md. You can toggle this behavior in /config. 5.5M views · 31.3K likes · 2.6K reposts · 2.1K replies Open on X →
We’re working on making Claude Code way more hackable, give us feedback! 98.3K views · 429 likes · 12 reposts · 142 replies Open on X →
it’s a very good model, I spent a lot of time diving into it- longer write up coming but try it on lower effort for tasks that need less verification or have fewer edge cases, switching effort no longer breaks prompt cache as well 302K views · 2.2K likes · 75 reposts · 203 replies Open on X →
@trq212 @lulumeservey Just wish the Fable 50% cut wasn't maintained as part of this :( 8.7K views · 137 likes · 1 reposts · 4 replies Open on X →
@trq212 Great recap and thanks for listening! 23.7K views · 59 likes · 0 reposts · 2 replies Open on X →
@trq212 @lulumeservey Your comment here shows you still don’t get it. It’s not that you decreased the limits, it’s how you guys communicated it 2.5K views · 53 likes · 0 reposts · 1 replies Open on X →
@lulumeservey yeah this was a L tbh, but not on purpose- it was hard to secure the compute to make the 25% permanent but it is a net loss from today’s limits, we should have led with it this is also only a change to the weekly limits, most users hit the 5h limits which are not c 293.6K views · 1.1K likes · 12 reposts · 164 replies Open on X →
Sleight of hand communication isn’t good for trust Especially at a moment when the adversarial meme about Anthropic is “they think we’re stupid” https://t.co/3MEaZ3ZGNO 110.4K views · 1.1K likes · 16 reposts · 35 replies Open on X →
Long-time admirer of the Cursor team, few have done more to bring AI coding to the world. Excited to continue to partner with them. 414.8K views · 2.9K likes · 95 reposts · 159 replies Open on X →
Cursor has been a trusted partner of Anthropic since Sonnet 3.5. We’ll continue to increase compute to support Claude models in Cursor and are excited for what comes next with them at SpaceX. 8.3M views · 10.3K likes · 460 reposts · 518 replies Open on X →
life is stranger than fiction https://t.co/VRODSsk0q4 179.4K views · 2.8K likes · 135 reposts · 93 replies Open on X →
We're seeing several of our customers be targeted by fraudulent requests and glad for all the work Stripe is doing to help them. Still a lot of work to do, these sort of attacks hurt everyones ability to provide usage to legitimate users. 101.1K views · 425 likes · 13 reposts · 21 replies Open on X →
Companies selling tokens are facing massive amounts of fraud these days. Stripe Radar is getting very, very good at blocking it. 410.6K views · 2.3K likes · 62 reposts · 79 replies Open on X →
@trq212 @tobi i can see where this was coming from but i’d like to point out this is clearly the wrong philosophy i use 5 different models regularly. other contributors in my repos use a dozen more do we seriously maintain 17 different AGENTS.md files in the repo, each one fine 13.2K views · 235 likes · 2 reposts · 5 replies Open on X →
@trq212 @tobi what Tobi wants is a very simple change don’t delay it 7.9K views · 168 likes · 1 reposts · 4 replies Open on X →
@trq212 @tobi imo you all need to go back to "build for 6 months from now" you really think that the minor variances between the models are that significant and will continue to persist? this doesnt feel aligned with where things almost certainly end up tbqh 38.5K views · 347 likes · 0 reposts · 6 replies Open on X →
@tobi Hi Tobi, thanks for the feedback! We are working on making Claude Code more hackable, which will include being able to easily use Agents.MD or make other system prompt modifications. I’ll share more here when it’s ready to roll out. Our reasoning for this was that we don't 925.4K views · 1.8K likes · 70 reposts · 211 replies Open on X →
I’m thinking about banning Claude code at Shopify until they change their mind and read AGENTS.md and .agents/skills etc. Insisting on only reading CLAUDE.md sometimes leads to split brain problems when different team members use different tools. Just unnecessary. 2.3M views · 19.5K likes · 915 reposts · 980 replies Open on X →
@trq212 Appreciate it! Opus 5 is performing a lot better Was stuck relying on 4.6 + other models for biology stuff until now 37.2K views · 70 likes · 0 reposts · 2 replies Open on X →
this is also available on the Claude Blog here: https://t.co/W84J5X640M 119.7K views · 394 likes · 26 reposts · 12 replies Open on X →
We removed ~80% of the Claude Code system prompt for our newest models, this is what we've learned about writing system prompts, skills and Claude.MDs for them. https://t.co/6DZwSrZjE9 4.9M views · 16.3K likes · 1.9K reposts · 466 replies Open on X →
this is now on the Claude blog! https://t.co/7LW0yDuixR 34.2K views · 69 likes · 3 reposts · 6 replies Open on X →
@trq212 https://t.co/ORvGULm2id
30.4K views · 116 likes · 1 reposts · 3 replies Open on X →
https://t.co/hPiZr1kG7r 3.8M views · 9.6K likes · 1.2K reposts · 267 replies Open on X →
I put a lot of heart into my technical writing, I hope it's useful to you all. 📌 Here's a pinned thread of everything I've written. (much of this will be posted on the Claude blog soon as well) 1.9M views · 8.5K likes · 876 reposts · 265 replies Open on X →
@trq212 iMessage and it’s actually game over 66.4K views · 454 likes · 1 reposts · 16 replies Open on X →
This is a research preview that we'll be expanding more on. Read more in our docs on Channels here: https://t.co/apaPL9496Z 259.2K views · 625 likes · 47 reposts · 37 replies Open on X →

Frente a cuentas del mismo tamaño

21 publicaciones de los últimos 90 días, junto al rango de 100K–1M seguidores. llega a más gente que cuentas de su tamaño.

Visualizaciones medianas189 439esta cuenta5 983mediana de 100K–1M
Alcance, %53.52%esta cuenta1.49%mediana de 100K–1M
Interacción, %0.79%esta cuenta0.93%mediana de 100K–1M
MétricaEsta cuentaMediana de 100K–1MProporción
Visualizaciones medianas por publicación189 4395 98331.7×
Alcance (visualizaciones ÷ seguidores)53.52%1.49%35.9×
Tasa de interacción0.79%0.93%0.85×

Otras cuentas de este rango →   Comparar con otra cuenta →   Cómo se construyen estas referencias →

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

179.4K28 Aug
8.3M29 Aug
414.8K
110.4K
293.6K30 Aug
2.5K
23.7K
8.7K
302K2 Sep
98.3K3 Sep
5.5M18 Sep
340.1K
255.4K
189.4K

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

1.73%28 Aug
0.14%29 Aug
0.79%
1.02%
0.46%30 Aug
2.19%
0.26%
1.63%
0.84%2 Sep
0.60%3 Sep
0.70%18 Sep
0.37%
0.24%
2.35%

Reactions — likes, reposts, replies and quotes — divided by views. Median for 100K–1M accounts is 0.93%.

What the audience does

Likes53.6%119 400 in total
Reposts3.9%8 687 in total
Replies2.7%5 933 in total
Quotes2.3%5 041 in total
Bookmarks37.5%83 566 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

23 Sep

Daily snapshots since 23 Sep 2026; the dashed line is the starting count.

Cuentas similares