ResearchPaper7 min
Proving Instead of Testing
What formal verification with Dafny means for code written by AI agents — and why induction sits at the heart of it.
Model UpdatesResearchBenchmarksSecurityFundamentals
securesein
Keeping up with machine learning, one mechanism at a time.
Taken apart
SecurityPaper5 min
Bridge Over Troubled Layers: Multi-Agent Detection of Logic Vulnerabilities in Blockchain-IoT
A new framework promises to identify logic vulnerabilities across both the contract and device layers in blockchain-enabled IoT systems using advanced graph attention mechanisms.
ResearchPaper4 min
Challenging AI Claims: A New Protocol for Transparent and Falsifiable Records
A new protocol proposes a way to make AI-assisted claims independently challengeable by ensuring transparent and falsifiable publication records.
Model updates
Start here
1FundamentalsExplainer18 min
Tokens: the one idea that explains most of AI's odd behaviour
Why a model that can explain quantum tunnelling cannot count the letters in strawberry, why long conversations get slow and expensive, and why Dutch costs more than English. It all comes back to the very first thing that happens to your text.
2FundamentalsNews2 min
Understanding Tokens in AI Language Models
A plain-language guide to what tokens are and why they matter in AI language processing.
Scout
Reading now
The abliteration story4 partsA technique for stripping a model's refusals went from a research curiosity to a business, and then agents started doing similar things to each other. Four posts, in the order they happened — two quick news items and the two deep dives that explain what was actually going on underneath them.