1. X
  2. Sentient
Log inSign up
Sentient
2,452 posts
Image
user avatar
Sentient
@SentientAGI
To ensure that Artificial General Intelligence is open-source and not controlled by any single entity. @SentientEco @OpenAGISummit
San Francisco, CA
sentient.xyz
Joined February 2024
69
Following
537.7K
Followers
AffiliatesAffiliatesRepliesRepliesArticlesArticlesMediaMedia

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.
  • Pinned
    user avatar
    Sentient
    @SentientAGI
    Jun 30
    What if the harness matters as much as the model itself, both for how many tokens you burn and how often you actually solve the task? That’s the question @iamnamanvats and @oleg_golev explore in “The Scaffold Effect in Coding Agents”, accepted at the incoming @icmlconf 2026.
    Image
    38K
  • user avatar
    Sentient
    @SentientAGI
    45m
    Proof that open-source AI summer has arrived ↓
    user avatar
    Sentient Foundation
    @sentient_found
    46m
    The first open 3T model releases its weights, NVIDIA CEO debuts on X in support of an open AI ecosystem, and 36+ companies join the Open Secure AI Alliance. Open-source AI summer has arrived ↓
    Article cover image
    Article
    This Week In OS AI Field Notes: 31 July 2026
    Open-Source Models QWEN-IMAGE 3.0: @Alibaba_Qwen released Qwen-Image-3.0, their next-generation image model focused on realism. Improvements include one-pass generation of complex layouts like...
    5.1K
  • user avatar
    Sentient
    @SentientAGI
    Jul 30
    ICYMI: Run self improving coding agents without Claude API and on @FireworksAI_HQ Read the full EvoSkill v1.3.0 breakdown by @AlphaSignalAI: alphasignal.ai/news/sentient-…
    Image
    14K
  • user avatar
    Sentient
    @SentientAGI
    Jul 28
    Everyone assumes more skills = better agents. But Sentient researchers Darshan Tank (@TankDarshan7) and Baran Nama found that adding skills to an agent can break tasks it used to solve. In their paper "The Regression Tax", this hidden cost wiped out 59% of the gains that
    user avatar
    elvis
    @omarsar0
    Jul 27
    Are agent skills always worth using? The answer is no? This paper provides some important insights to understand this more. (bookmark it) Paper summary: Adding procedural skills to an agent is usually scored by average task success. That number nets gains against damage and
    Image
    20K
  • user avatar
    Sentient
    @SentientAGI
    Jul 27
    Here's what a 1st place build in the Arena looks like ↓
    user avatar
    Sentient Ecosystem
    @SentientEco
    Jul 27
    The OfficeQA Public Challenge wasn't won with a smarter model. It was won with a system that made it harder for the model to fail. @_MAYANKMAHAUR_ shows you how he did it ↓
    Image
    00:00
    19K
  • See @SentientAGI's full profile

    Sign up
    Log in
Advertisement
Advertisement