1. X
  2. Weco AI
Log inSign up
Weco AI
84 posts
Weco AI profile banner
user avatar

Weco AI

@WecoAI
The platform for self-improving code
weco.ai
Joined April 2023
7
Following
2,687
Followers
RepliesRepliesMediaMedia

Log in or sign up for X

See what’s happening and join the conversation

Continue with phone
or
Log in with username or email
Terms·Privacy·Cookies·Accessibility·Ads Info·© 2026 X Corp.
  • user avatar
    Weco AI
    @WecoAI
    Jul 14
    Thousands of search trees. 99 rewrites of the agent's own code. 9 in 10 rejected by a held-out gate. Eight unattended days. The AIDE² pilot report is out. AIDE_85, the discovered agent and more detailed PDF tech report, will be released when the remaining analysis lands
    user avatar
    Zhengyao Jiang
    @zhengyaojiang
    Jul 14
    The first experimental evidence of recursive self-improvement (RSI). Autoresearching the autoresearch agent for eight days. The result beats the harness we hand-tuned for two years, on held-out benchmarks: 🧵(1/7)
    Image
    00:00
  • user avatar
    Weco AI
    @WecoAI
    Jul 10
    Sharing our framework for thinking about RSI, with some experimental results coming soon!
    user avatar
    Zhengyao Jiang
    @zhengyaojiang
    Jul 10
    Everyone assumes RSI would lead to an intelligence explosion. Is that really the case? We tried to clean up the logic after 8 months of building RSI at the harness layer. Not all RSI is equal. We split it into 4 levels: delegation, net positive, ignition, and inflection. (1/9)
    Image
  • user avatar
    Weco AI
    @WecoAI
    Jun 25
    Weco Autoresearch is now steerable, and we allow Claude Code to connect to the dashboard
    user avatar
    Zhengyao Jiang
    @zhengyaojiang
    Jun 25
    One of our autoresearch runs sat flat for 60 steps. One message got it moving again. Everyone is pushing research agents toward full autonomy, but what helps most is being able to step in when a run goes wrong, without breaking the loop. (1/6)
    Image
    00:00
  • user avatar
    Weco AI
    @WecoAI
    Jun 16
    We're thrilled to welcome Vayum Arora to Weco AI as our growth lead! We couldn't be more excited to bring on Vayum's mix of frontier engineering and business instinct as we continue to grow. Welcome to Weco, @vayum_arora!
    Image
  • user avatar
    Weco AI
    @WecoAI
    Jun 14
    Sharing some of our internal benchmark results
    user avatar
    Zhengyao Jiang
    @zhengyaojiang
    Jun 14
    We benchmarked 7 frontier models on 3 categories of autoresearch tasks: ML engineering, harness/prompt engineering, and algorithmic discovery. Fable-5 won overall even under cost constraint, but on ML engineering, the open model Kimi-K2.7-Code surpassed frontier models.🧵(1/5)
    Image
Advertisement
Advertisement