Evolvent AI

@Evolvent_AI

Building persistent agent infrastructure for infinite self-evolving intelligence. More at: evolvent.co

Joined April 2026

95 Following

531 Followers

Replies Reposts Media

Pinned
Evolvent AI
@Evolvent_AI
Jun 17
🤯 Evolvent's Self-Evolving Agentic System What if one agent’s failure could make the whole organization smarter? 💡 That’s the collective intelligence layer we’re building with Evolvent. 🧩 Across 5 AutoResearch-style tasks, individual attempts, failures, fixes, and
3
Evolvent AI
@Evolvent_AI
Oct 8
First leaderboard is live: across 6 research agents × 5 benchmarks, Opus 5 leads at 0.4809. RSI-Index is the first score measuring joint improvement of model weights AND harness. The RSI race now has a scoreboard. 🏁 The full codebase and per-agent experiment configs are on
Fanqing
@FanqingMengAI
Oct 8
💡Our view: RSI is a systems engineering problem, not just a model problem. Progress depends on the environment a research agent works in: what resources it can call, what it can change, and how it runs experiments. That environment should reflect real production workflows and
3
Evolvent AI
@Evolvent_AI
Sep 29
Three weeks. Two personal life agents.🤖 Sept 8 — @Meta's Muse: 3.4M+ downloads, #1️⃣ on the US App Store. Sept 28 — @ManusAI 's Cue: agents with their own phone number, wallet, and computer. The era of "AI that runs your life" is officially here. Now the uncomfortable question:
Evolvent AI
@Evolvent_AI
Sep 17
VibeLifeBench Update: More Stable, One Command to Run 📌 VibeLifeBench has drawn wide attention across the industry since launch. We've just upgraded it again — steadier, and easier to work with: 🔧 A batch of stability fixes. It runs more reliably now. ⚡ Every task now uses
1
Evolvent AI
@Evolvent_AI
Sep 28
"Expert-annotated data and vibe coding are fundamentally the same" — sounds like a hot take, but it's really a flattening: once the agent is the system's executor, human contributions compress to a single difference — the ability to define what counts as right, and own what
Fanqing
@FanqingMengAI
Sep 24
RSI-Anything is currently the framework that best aligns with my understanding of expert-annotated data. To some extent, there is no fundamental difference between expert-annotated data and CS students' vibe coding. What everyone sees is the result translated by the agent, and
Evolvent AI
@Evolvent_AI
Sep 28
AA's 95% confidence interval tells you how confident we are in the model — not in the evaluation. The moment an industry accepts "leaderboard = truth", eval stops being a tool and becomes power. And history is clear: nobody wants to live inside someone else's scoreboard. Labs
Fanqing
@FanqingMengAI
Sep 5
某种意义上评测就是infra
Quote
Xiuyu Li
@sheriyuo
Sep 4
读知乎回答有感，浅谈一下后训练 benchmark zhihu.com/question/20790… Any benchmark will be saturated，而随着工业界后训练的发展，reasoning / coding 的 benchmark 越来越泛化 / 众包化。其实 LLM eval 一直是个草台班子，每家都可以有自己的 setting，而任何 setting

Evolvent AI

Evolvent AI’s posts