Claims Browser

There is a crucial gap in the benchmarking ecosystem for corporate communication reasoning that needs to be filled

"CB provides LLM developers a metric for corporate communication reasoning, filling a crucial gap in the benchmarking ecosystem."

BrailleBench provides valuable guidance for the development of future Braille AI systems

"The experimental observations provide valuable guidance for the development of future Braille AI systems"

Same-rollout relative calibration is a practical way to distinguish revisit-specific consistency from generic temporal stability in video world models

"these results support same-rollout relative calibration as a practical way to distinguish revisit-specific consistency from generic temporal stability."

Data-side diagnostic approaches can characterize what a training corpus licenses under specified identifications without requiring training of a predictive model

"These data-side diagnoses characterize what the training corpus licenses under specified identifications, without training a predictive model."

Automatic metrics should be reframed as tools for reducing human annotation cost rather than replacing human judgment

"our new paradigm reframes automatic metrics as tools for reducing human annotation cost rather than replacing human judgment"

AraMS-28k supports reproducible research on Arabic manuscript recognition, layout analysis, and reading-order recovery

"AraMS-28k is released with page images, line-level annotations, and fixed train/val/test splits under CC BY-NC-SA 4.0 to support reproducible research on Arabic manuscript recognition, layout analysis, and reading-order recovery"

Acceleration in AI capabilities happens through phase changes for specific skills, as evidently occurred with day-to-day coding in 2025 and cyber in 2026

"My suspicion is that acceleration happens when models go through some kind of ineffable phase change for a given skill, as has evidently happened with day-to-day coding (2025), and cyber (2026)"

AI detectors are essentially a cat-and-mouse game where detection patterns must continuously adapt as LLMs evolve to avoid detection

"AI checkers are essentially a cat-and-mouse game. AI checkers may learn to detect a certain pattern that is indicative of AI-generated content. Then, the next LLM may incidentally or deliberately not exhibit that pattern and avoid detection. The AI checker then has to be updated to detect said LLM, and so forth."

Process-level evaluation is crucial for interpreting the true potential of LLMs and guiding development of next-generation mathematical agents

"This demonstrates that process-level evaluation is crucial for interpreting the true potential of LLMs and guiding the development of next-generation mathematical agents."

Frontier evaluation has become harder than ever, with agentic evaluation methods being particularly complex

Daniel Reeves argues that humans have already come close to some fundamental limit on the predictability of world events, implying AI forecasting will plateau

New benchmarks should measure real world impact like diseases cured, math problems solved, scientific discoveries, and materials invented rather than traditional metrics

Astra is maybe not much better than Fable and certainly not ASI

Astra was a play to distract from OpenAI's increasingly terrible economics

AGI must be general and work across domains beyond those that can be formalized

Writing good video scripts should be within the capabilities of AGI

Defining vocabulary for evaluation tools is one of the hardest parts of building such projects

A single scalar success rate cannot adequately explain computer-use agent performance

Grammatical competence in morphologically rich languages remains under-measured in the rapidly scaling open-weight LLM ecosystem