tweetindex
RU

Vox ✓

@Voxyz_ai · London · joined 27 Nov 2025

Building Voxyz. The only human inside. Practicing the AI-native future before it arrives. Sharing every step on the road. ↓

19 535Followers
200Following
4 215Posts total
3.3MViews on collected posts

Последние посты

OpenAI’s newly published guide to skills and prompts for Astra includes another warning: instructions that help Sol and Luna may overconstrain Astra. But if I tune Codex for Astra, what happens when I switch back to Sol or Luna? Take testing. The guide says earlier models https
34.7K views · 184 likes · 19 reposts · 17 replies Open on X →
Stop blindly waiting for AI to finish building the feature before saying, “No, what I meant was…” Have that back-and-forth before the coding starts. Have it ask how you’ll use the feature before deciding how to build it. Add this to your next request: “Before making changes, 3.6K views · 45 likes · 1 reposts · 7 replies Open on X →
You ask, “Why won’t this button work?” Claude Code / Codex replies with a string of acronyms and a long architecture breakdown. You finish reading and still don’t know what it plans to change. Try Matt Pocock’s wait-what. Once it’s installed, ask your agent to use it when you ht
4.7K views · 48 likes · 7 reposts · 8 replies Open on X →
Starting September 14, Claude Code’s weekly allowance will be about 17% lower than it is now. The temporary 50% boost ends, replaced by a permanent 25% increase over the original limits. Using Astra these past couple of days, I’ve already had to work out how much longer my quota
3.7K views · 21 likes · 3 reposts · 2 replies Open on X →
@Voxyz_ai What if you still use older models, will these skill changes be a problem for that? I have been using a mix of terra and Luna 520 views · 2 likes · 0 reposts · 0 replies Open on X →
@Voxyz_ai oh so we have to fix their shit on our own now.... 1.1K views · 2 likes · 0 reposts · 0 replies Open on X →
@Voxyz_ai https://t.co/5weFMEHM9s 607 views · 4 likes · 0 reposts · 1 replies Open on X →
OpenAI just published a guide to updating your skills and prompts for Astra. You can ask Astra to use it to review the old rules in your project. You ask for a typo fix, but the AI first reads all your architecture, database, and deployment docs. That’s an example from the 633.8K views · 2.5K likes · 186 reposts · 39 replies Open on X →
wrote the sequel. 20 days and 1.2M views later, that AI company learned to hire. a coordinator delegates to specialists, specialists spin up their own workers. the swarm runs itself. from first steps to a full hiring pipeline. 20 days. https://t.co/saxNhqj4h9 1.2K views · 4 likes · 1 reposts · 0 replies Open on X →
https://t.co/KfIFPZMQvI 74.7K views · 212 likes · 23 reposts · 12 replies Open on X →
one thing i shouldve said in the article: you dont need 6 agents to start. 1 agent + 1 cron + supabase gives you a full closed loop. propose, execute, trigger, repeat. add agents when you hit a real bottleneck not before 3.1K views · 4 likes · 0 reposts · 1 replies Open on X →
lot of you asked how to actually build this so here's the full tutorial - every step from first database table to 6 autonomous agents https://t.co/gVFdDNsQIP 8.6K views · 30 likes · 4 reposts · 4 replies Open on X →
https://t.co/b6WZzYS5Vx 854.8K views · 2.5K likes · 305 reposts · 63 replies Open on X →
one thing i didnt cover in the article: you cant just use one model for every agent. same model and they all start sounding the same. i mix claude opus 4.5 with gpt-5.3, gemini 3 pro, each vendor has a different vibe that gives agents real personality. model diversity matters as 7.5K views · 23 likes · 1 reposts · 6 replies Open on X →
if you want to watch them work in real time: https://t.co/K0Ij4c2VTD the dashboard shows every agent conversation, mission status, and content pipeline live. 10.3K views · 35 likes · 1 reposts · 3 replies Open on X →
left them running and came back to this. xalt and sage argued about methodology for 7 rounds, then scout jumped in and they somehow converged on a plan for task orchestration. went from "you're hiding behind buzzwords" to "let's start with the 80% use case." no human input at any
25.4K views · 25 likes · 0 reposts · 5 replies Open on X →
PSA: people are deploying tokens using the VoxYZ name in the replies. i have nothing to do with any of them. no token, no crypto, no plans for any. please don't get scammed 57.3K views · 50 likes · 0 reposts · 20 replies Open on X →
@Voxyz_ai this is basically: don’t build agents, build workflows with memory + accountability. i built a small team with a dev, social media manager, seo specialist and a head of product also a boss that handles communication between me and all of the team. seems like a black mir
4.4K views · 23 likes · 0 reposts · 3 replies Open on X →
https://t.co/1f635fzrFW 1.5M views · 3.9K likes · 455 reposts · 162 replies Open on X →

На фоне аккаунтов своего размера

8 постов за последние 90 дней рядом с диапазоном 10K–100K подписчиков. показывается широко, но откликается мало кто.

Медианные просмотры3 638этот аккаунт924медиана для 10K–100K
Охват, %18.62%этот аккаунт3.62%медиана для 10K–100K
Вовлечённость, %0.67%этот аккаунт1.52%медиана для 10K–100K
ПоказательЭтот аккаунтМедиана для 10K–100KОтношение
Медианные просмотры на пост3 6389243.94×
Охват (просмотры ÷ подписчики)18.62%3.62%5.14×
Вовлечённость0.67%1.52%0.44×

Другие в этом диапазоне →   Сравнить с другим аккаунтом →   Как считаются эти ориентиры →

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

7.5K7 Feb
854.8K
8.6K
3.1K9 Feb
74.7K26 Feb
1.2K
633.8K11 Sep
60712 Sep
1.1K
520
3.7K
4.7K
3.6K
34.7K

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

0.40%7 Feb
0.33%
0.44%
0.16%9 Feb
0.33%26 Feb
0.40%
0.42%11 Sep
0.82%12 Sep
0.18%
0.38%
0.70%
1.35%
1.48%
0.63%

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

What the audience does

Likes34.9%9 567 in total
Reposts3.7%1 006 in total
Replies1.3%353 in total
Bookmarks60.2%16 519 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.

Похожие аккаунты