tweetindex
TR

Mckay Wrigley ✓

@mckaywrigley · The Simulation · joined 26 Sep 2014

I build & teach AI stuff. Founder @TakeoffAI + @AgentShare.

228 400Followers
397Following
19 991Posts total
1.5MViews on collected posts

Son gönderiler

gpt-6 astra release gives the same vibes as the gpt-4 release. a genuine step change where ai can do categorically new things. there are multitudes of miracles buried in those weights… and i very much look forward to all of us prompting them out. 28.5K views · 565 likes · 12 reposts · 27 replies Open on X →
grok 4.6 is great. its intelligence per dollar is crazy good. fable 5 is still the best model (and i don’t think it’s close), but i am now *very* intrigued by grok 4.7. spacex/cursor is now *firmly* in the frontier intelligence game with anthropic & openai. wildly impressed. 47.2K views · 922 likes · 30 reposts · 69 replies Open on X →
the models are genius creative savants, you just have to remind them https://t.co/EIYPRdndBM 4.5K views · 12 likes · 0 reposts · 1 replies Open on X →
sometimes all you need to do is tell Claude to keep going @jarredsumner https://t.co/sD0xcj5Fgs 448K views · 2.2K likes · 115 reposts · 159 replies Open on X →
@mckaywrigley hmm this is cool, do you have an example of what this does? 43K views · 83 likes · 0 reposts · 6 replies Open on X →
fable in particular very much “gets” what this means. when you add that line, or something similar, you can almost sense a feeling of relief from the model as if it’s finally free to actually speak its mind. i’ve a/b tested this for 2 weeks now and the results are kinda nuts 12.1K views · 88 likes · 0 reposts · 3 replies Open on X →
random tip… put “You are AGI-pilled.” in your system prompt for all agents now. it’s a WAY better experience. rn agents behave too much like the world is going to stay static. this unhobbles them quite a bit and gets them to talk/act more like AGIs. 135.7K views · 1.1K likes · 40 reposts · 74 replies Open on X →
bullish model routers. same perf at lower cost is obvious. but there are massive gains to be had by creating "smoother" intelligence via blending multiple jagged models together. the era of model melding begins. 25K views · 83 likes · 6 reposts · 18 replies Open on X →
Going to continue posting these on YouTube for things like captions: https://t.co/XV6xYF1g0h 20.6K views · 62 likes · 4 reposts · 1 replies Open on X →
Read my 2 replies here for answers on why this isn’t just a template instead! 40.9K views · 22 likes · 0 reposts · 2 replies Open on X →
@amogower It’s oversimplified for the video, but usually I’ll pair this with several project specific spec files so that it can scaffold out that particularly project. Think of it as like an executable README that’s extremely flexible. 43.7K views · 19 likes · 1 reposts · 2 replies Open on X →
As far as announcements go, we’re rolling out our “Full-stack apps with AI” course tomorrow! Adding a new app tutorial to that every day next week. Pair that with our Cursor course and you’ll be unstoppable. For both beginners and experienced devs. https://t.co/KRFAav7jvX 28.6K views · 91 likes · 2 reposts · 5 replies Open on X →
@mckaywrigley Twitter is the new github 7.1K views · 67 likes · 0 reposts · 1 replies Open on X →
PUT THIS PROMPT IN A `https://t.co/u91PeWihfP` FILE: -- # Backend Setup Instructions Use this guide to setup the backend for this project. It uses Supabase, Drizzle ORM, and Server Actions. Write the complete code for every step. Do not get lazy. Write everything that is 41.3K views · 272 likes · 20 reposts · 18 replies Open on X →
In Cursor I’m able to generate a fully functional backend with a single prompt. A working database in <2min. Composer is pure magic. Full prompt below. https://t.co/ih3tQNAZab 622.3K views · 4.1K likes · 294 reposts · 77 replies Open on X →
I couldn’t code 18 months ago. Yesterday I raised over $20,000 from initial customers to get my software business off the ground. Believe in yourself, be relentlessly resourceful, be relentlessly optimistic, and never give up. 0 views · 8.9K likes · 617 reposts · 318 replies Open on X →

Aynı büyüklükteki hesaplara karşı

Son 90 güne ait 8 gönderi, 100K–1M takipçi aralığıyla yan yana. geniş kitleye gösteriliyor, ama izleyenlerin azı tepki veriyor.

Medyan görüntülenme35 773bu hesap5 983100K–1M için medyan
Erişim, %15.66%bu hesap1.49%100K–1M için medyan
Etkileşim, %0.66%bu hesap0.93%100K–1M için medyan
ÖlçütBu hesap100K–1M için medyanOran
Gönderi başına medyan görüntülenme35 7735 9835.98×
Erişim (görüntülenme ÷ takipçi)15.66%1.49%10.5×
Etkileşim oranı0.66%0.93%0.71×

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

41.3K29 Aug
7.1K
28.6K
43.7K30 Aug
40.9K
20.6K
25K4 Aug
135.7K5 Aug
12.1K
43K
448K10 Aug
4.5K
47.2K13 Aug
28.5K4 Sep

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

0.76%29 Aug
0.97%
0.35%
0.05%30 Aug
0.06%
0.32%
0.44%4 Aug
0.91%5 Aug
0.75%
0.21%
0.57%10 Aug
0.31%
2.17%13 Aug
2.13%4 Sep

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

What the audience does

Likes48.3%9 672 in total
Reposts2.6%524 in total
Replies2.3%463 in total
Quotes0.9%171 in total
Bookmarks46.0%9 215 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