model
The Verifiable Credentials Working Group has published a series of W3C Working Group Note Drafts for threat models.
This week’s episode is part of an experiment and so requires a longer than normal introduction. I’ve come to view this podcast as a learning tool, a means to un…
Study finds non-experts deferred to LLM-based diagnostic assistance, even when it was wrong, while clinicians caught AI errors.
A new method for surgically removing training examples from a model reveals that as datasets grow, the link between what a model learns and what it produces dis…
A new language-processing tool could help identify the highest-risk individuals from natural language, enabling swifter interventions.
This essay first appeared in Reboot . Credulous, breathless coverage of “AI existential risk” (abbreviated “x-risk”) has reached the mainstream. Who could have …
On fish counting – a complex sociotechnical problem in a field that is going through the process of digital transformation.
Have you ever trained a model you thought was good, but then it failed miserably when applied to real world data? If so, you’re in good company.
'Vec2text' can serve as a solution for accurately reverting embeddings back into text, thus highlighting the urgent need for revisiting security protocols aroun…





