What if your AI agent could search raw text files directly instead of using vector databases? A team of researchers from Texas A&M, University of Waterloo, Stanford, and others presents Direct Corpus Interaction (DCI). Instead of embedding models or vector indexes, agents use
RESEARCH
-
Fast answers on shallow evidence reproduce bias faster
By
–
Fast answers built on a shallow evidence base do not solve the bias problem. They reproduce it faster.
— Catherine Adenle (@CatherineAdenle) 24 juin 2026
As AI becomes part of research and decision-making, the quality of the underlying evidence matters as much as the capability of the model.
Better decisions require broader… pic.twitter.com/VI8ZufuFiXFast answers built on a shallow evidence base do not solve the bias problem. They reproduce it faster. As AI becomes part of research and decision-making, the quality of the underlying evidence matters as much as the capability of the model. Better decisions require broader
-
Anthropic Research Lead on self-improving AI agent swarms with verification loops
By
–
🚨 Anthropic’s Research Lead just dropped a masterclass on AI agents.
— Charly Wargnier (@DataChaz) 24 juin 2026
"99% of our engineers run swarms of 300+ self-improving agents".
The key?
Closing the loop so models can verify their own work.
In 20 minutes, they unpack continuous Claude loops, plan modes, and dynamic… https://t.co/fEAHNuFBTz pic.twitter.com/Vy7zekwzRxAnthropic’s Research Lead just dropped a masterclass on AI agents. "99% of our engineers run swarms of 300+ self-improving agents". The key? Closing the loop so models can verify their own work. In 20 minutes, they unpack continuous Claude loops, plan modes, and dynamic
-
Baidu’s Unlimited-OCR weights on Hugging Face
By
–
Weights → https://
huggingface.co/baidu/Unlimite
d-OCR
… -
Baidu’s Unlimited-OCR transcribes books in one pass, surpassing page-by-page models
By
–
BAIDU JUST DROPPED AN ABSOLUTE GAME-CHANGER FOR DOCUMENT AI
— Charly Wargnier (@DataChaz) 24 juin 2026
It’s called `Unlimited-OCR`, and it can literally transcribe an entire book in a single pass 🤯
Most vision models read a single page, forget the context, and eventually hit a wall where performance degrades and… pic.twitter.com/KUHrWFHYTWBAIDU JUST DROPPED AN ABSOLUTE GAME-CHANGER FOR DOCUMENT AI It’s called `Unlimited-OCR`, and it can literally transcribe an entire book in a single pass Most vision models read a single page, forget the context, and eventually hit a wall where performance degrades and
-
Reuters adds context to Mythos report on government vulnerabilities
By
–
Reuters has now added more context to last week's Mythos report. According to AP, Anthropic's Mythos model identified vulnerabilities in highly sensitive US government computer systems during a test exercise conducted
-
Qwen-AgentWorld: AI simulates digital environments via language reasoning
By
–
What if an AI could simulate any digital environment just by thinking in language? Qwen Team presents Qwen-AgentWorld — the first language world models that predict environment dynamics via long chain-of-thought reasoning. They trained two models (35B and 397B) on 10M+
-
Data Without Labels: Unsupervised Machine Learning Book Overview
By
–
Data Without Labels — Models and Algorithms for Practical Unsupervised Machine Learning: http://
amzn.to/4q5bbYz 𝓦𝓱𝓪𝓽 𝓨𝓸𝓾 𝓦𝓲𝓵𝓵 𝓛𝓮𝓪𝓻𝓷: Fundamental building blocks and concepts of machine learning and unsupervised learning
Data cleaning for structured and -
AI talent underpaid: each worth $150B as Google market cap fell 7%
By
–
AI talent is still highly underpaid: Google’s market cap fell by 7% when Noam Shazeer and John Jumper left, so on average they’re each worth $150B .
-
SemanticQA: a new benchmark for evaluating LM comprehension
By
–
Do your language models truly grasp meaning, or are they just pretending? Researchers from Beijing University of Science and Technology and BIGAI present SemanticQA — a new benchmark that evaluates LMs' ability to handle expressions.