The Signal

Everything that matters in AI, with our take.

Updated through the day. Every headline links straight to the source. The two lines underneath are ours.

research1156 agents716 infra561 labs317 culture268 capital253 regulation233 claude175 openai149 safety103 security89 evaluation77 reasoning61 alignment52 benchmarks50 interpretability48

arXiv cs.CLPaper14h ago

Nameless Tokenization: A Lossless Tokenizer-Level Defense Against Control-Token Forgery in Open-Weight LLMs

This is a real vulnerability in deployed systems. Any open-weight model where the chat template strings are public (which is all of them) can have its turn boundaries spoofed unless you implement this fix. The proposal works and costs nothing on clean data. For anyone deploying open-weight chat models in adversarial settings, this moves from interesting to mandatory. For closed-weight systems, your tokenizer is opaque and you're probably safer by accident.

infra security tokenization

arXiv cs.CLPaper7d ago

Studying Image Tokenizers as Visual Languages in Unified Multimodal Models

The finding is useful: losses behave differently by task, and T2I losses don't reliably rank tokenizers across different architectures. This is good empirical design work that will help teams avoid false conclusions when tuning multimodal systems. It doesn't suggest a breakthrough tokenizer or architecture, just that existing evals are incomplete. Solid research, narrow application.

research multimodal tokenization

arXiv cs.CLPaper10d ago

When Tokenization is Secretly Output Supervision

This reframes a technical detail that everyone ignores into something that actually matters for model comparison and training. When you're comparing two models with different tokenizers, you're partly comparing different tasks, not just different abilities. For practitioners: tokenization choices in your fine-tuning pipeline have more effect than you think, especially on reasoning tasks. For researchers: control for this in your comparisons.

research tokenization language-models methodology

arXiv cs.LGPaper29d ago

TokEval: A Tokenizer Evaluation Suite

Tokenizer choice is one of the most under-scrutinized decisions in model building despite direct effects on math and multilingual performance. Teams training their own base models should actually run something like this before locking in a tokenizer, since it's expensive to fix later.

research infra tokenization