tweetindex
FR

Pokee AI

@Pokee_AI · joined 19 Nov 2024

Frontier Agent Running In Your Infra and Compute. Pokee AI's official X account.

12 713Followers
12Following
1 251Posts total
3.5MViews on collected posts

Derniers posts

Pokee Isaac now runs inside OpenCode. You can use the same open-source integration built for Claude Code: give OpenCode the repo, add your Pokee API key, and ask it to use the Isaac MCP. From there, OpenCode can call Isaac directly to generate complete artifacts in a single pass.
1:38
10.7K views · 23 likes · 1 reposts · 13 replies Open on X →
Pokee: “Cute. Anyway, here’s 10M context running locally on a single GPU.” 👀 2.3K views · 20 likes · 2 reposts · 2 replies Open on X →
OpenAI: “We’ve solved math” Anthropic: “Our AI is so powerful it’s going to kill you” Google: “Introducing Gemini 3.9 Flash! It’s 30% faster and 15% worse than the last Gemini” 1M views · 33.8K likes · 1.2K reposts · 359 replies Open on X →
Pokee Isaac now runs inside Cursor with Grok 4.6. Using the prior Claude-Pokee repo, you can have Grok call Isaac through the MCP from that same repo to generate complete artifacts in a single pass. In this example, we used it to build a super cute retro gaming HTML. It's https
3:15
2.6K views · 12 likes · 3 reposts · 2 replies Open on X →
Already using Pokee Isaac with Claude Code? You can use the same package with OpenAI's Codex—no new integration required! Because claude-pokee exposes Isaac through MCP, Codex can connect to its existing ask, build, iterate, and health tools. Simply install the package below or
2:54
33.1K views · 16 likes · 2 reposts · 1 replies Open on X →
@Pokee_AI It sounds like you made MoW or Mixture of Weights? I didn’t even know this was possible. You could technically take the best weights of different models and make a super Frankenstein model thats the best at everything or something much more balanced across the board 136 views · 1 likes · 0 reposts · 0 replies Open on X →
@Pokee_AI That’s wild any chance it will be released as open weights for us local llm folks one day ? 322 views · 2 likes · 0 reposts · 0 replies Open on X →
@Pokee_AI in your technical report and blog, you'd clarify your model is based on Qwen3.6. 329 views · 3 likes · 0 reposts · 0 replies Open on X →
Pokee-Isaac uses a proprietary non-decoder-only architecture. While some weights are fine-tuned from Qwen3.6-27B under Apache 2.0, Isaac is not a conventional Qwen fine-tune and other weights of Isaac are trained from scratch by Pokee AI team. 17.4K views · 143 likes · 1 reposts · 7 replies Open on X →
@Pokee_AI HF Link? 🔗 https://t.co/p1s4rErvST
GIF
11.5K views · 177 likes · 0 reposts · 1 replies Open on X →
Releasing Pokee-Isaac 28B — the world’s first real 10M-token context frontier-class agentic model, deployable on a single GPU (starting from RTX 4090 or equivalent). New proprietary non-decoder-only architecture: • 93.3% RULER at 10M tokens • Up to 137K tokens/s prefill on one h
2.5M views · 3.6K likes · 373 reposts · 392 replies Open on X →

Face aux comptes de taille comparable

11 posts des 90 derniers jours, à côté de la tranche de 10K–100K abonnés. diffusé largement, mais peu de ces spectateurs réagissent.

Vues médianes10 675ce compte937médiane pour 10K–100K
Portée, %83.97%ce compte3.44%médiane pour 10K–100K
Engagement, %0.73%ce compte1.55%médiane pour 10K–100K
IndicateurCe compteMédiane pour 10K–100KRapport
Vues médianes par post10 67593711.4×
Portée (vues ÷ abonnés)83.97%3.44%24.4×
Taux d'engagement0.73%1.55%0.47×

Autres comptes de cette tranche →   Comparer avec un autre compte →   Comment ces repères sont établis →

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

2.5M4 Aug
11.5K
17.4K
3295 Aug
322
1366 Aug
33.1K4 Sep
2.6K9 Sep
1M
2.3K
10.7K15 Sep

Last 11 collected posts, oldest on the left. The scale is logarithmic: one post can outrun the rest a hundred times over.

Engagement rate per post

0.19%4 Aug
1.55%
0.87%
0.91%5 Aug
0.62%
0.74%6 Aug
0.06%4 Sep
0.65%9 Sep
3.54%
1.06%
0.35%15 Sep

Reactions — likes, reposts, replies and quotes — divided by views. Median for 10K–100K accounts is 1.55%.

What the audience does

Likes85.5%37 801 in total
Reposts3.6%1 586 in total
Replies1.8%777 in total
Quotes0.7%327 in total
Bookmarks8.4%3 732 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

10 Sep

Daily snapshots since 10 Sep 2026; the dashed line is the starting count.

Comptes similaires