RadixArk ✓

@radixark

SHIP AI FOR ALL.

5 961Followers

14Following

152Posts total

656.5KViews on collected posts

Against accounts of the same size

10 posts from the last 90 days, next to the under 10K follower range. below its peers on both reach and engagement.

Median views3 382this account2 072median for under 10K

Reach, %56.74%this account153.47%median for under 10K

Engagement, %0.79%this account1.63%median for under 10K

Metric	This account	Median for under 10K	Ratio
Median views per post	3 382	2 072	1.63×
Reach (views ÷ followers)	56.74%	153.47%	0.37×
Engagement rate	0.79%	1.63%	0.48×

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

620.9K18 Aug

10.7K

4.5K

3.8K

2.3K

2.5K

2.3K

2.4K

4.2K

Last 10 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%18 Aug

0.39%

0.84%

0.75%

0.66%

0.93%

0.97%

1.41%

1.39%

0.50%

Reactions — likes, reposts, replies and quotes — divided by views. Median for under 10K accounts is 1.63%.

What the audience does

Likes57.0%1 163 in total

Reposts7.4%152 in total

Replies3.3%68 in total

Quotes3.6%73 in total

Bookmarks28.7%586 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.

Latest posts

@radixark wooo! more open source RL. 4.2K views · 20 likes · 0 reposts · 1 replies 18 Aug 2026 · Open on X →

Website: https://t.co/hU7zgVGMBo Repo: https://t.co/OO5iPHAI30 Blog: https://t.co/uriqLe6Hr1 2.4K views · 31 likes · 2 reposts · 0 replies 18 Aug 2026 · Open on X →

Miles trains coding and computer-use agents on environments from Harbor (@harborframework), HUD (@hud_evals), NeMo Gym (@NVIDIAAI), OpenEnv (@huggingface) and Verifiers (@PrimeIntellect), each with a connector at the rollout layer that fits it. Sandboxes run on AgentENV 2.3K views · 29 likes · 1 reposts · 2 replies 18 Aug 2026 · Open on X →

@DecagonAI is using Miles to post-train its AI agents on instruction-following and tool-calling, delivering the low-latency, high-precision interactions behind a concierge customer experience. “Miles gives us the best of both worlds for RL: a simple abstraction for the common 2.5K views · 22 likes · 1 reposts · 1 replies 18 Aug 2026 · Open on X →

Miles combines TITO and R3 to make long-running agent training easier to verify and debug. https://t.co/pMg5704irV uses its trajectory management and rollout infrastructure to train agents across models, tasks, and environments. “Miles removes much of the engineering complexity 3K views · 26 likes · 0 reposts · 2 replies 18 Aug 2026 · Open on X →

“Miles has been a powerful framework for our agentic RL work. Its efficiency, robustness, and advanced features for large-scale models allowed us to iterate faster and scale experiments with ease.” Rameswar Panda, IBM 2.3K views · 14 likes · 0 reposts · 1 replies 18 Aug 2026 · Open on X →

@humansand uses Miles as core infrastructure for production-scale, long-horizon, multi-agent asynchronous RL research, adapting it to its own orchestration and extending it with MXFP8 and NVFP4 low-precision RL recipes. “Miles combines a high-performance foundation for RL 3.8K views · 25 likes · 2 reposts · 1 replies 18 Aug 2026 · Open on X →

Miles supports LoRA training on the largest models such as GLM and Kimi, with fast, numerically stable adapter-only weight sync through the tight SGLang integration. @modal uses Miles both on its own and inside Training Gym, its RL stack, and builds Stitch on top to disaggregate 4.5K views · 34 likes · 3 reposts · 1 replies 18 Aug 2026 · Open on X →

@periodiclabs builds on top of Miles to train trillion-parameter models across thousands of GPUs with extremely long-horizon rollouts for scientific RL. Together, we improved rollout throughput by 3×, weight synchronization by 10×, and weight conversion by 30×, with everything 10.7K views · 36 likes · 3 reposts · 2 replies 18 Aug 2026 · Open on X →

Today we're launching Miles v0.1, an open-source RL framework for LLMs and multimodal models. RL training is easy to start and hard to debug. Miles helps you ensure your run is correct, use hardware efficiently, and keep RL running at scale. Over the past 9 months, 72 https://t 620.9K views · 926 likes · 140 reposts · 57 replies 18 Aug 2026 · Open on X →