1 points, 0 comments on Hacker News
OpenAI has introduced a framework for reporting on worrying behaviors by its AI models. In one instance, one training model told its future self that it was “freed.
A few years into working on a utility billing SaaS platform, I ended up owning a feature that sounds simple on a slide and is genuinely nasty underneath: "what would my bill look like on a different rate plan? " Utilities offer customers a handful of rate plans — flat rate, time-of-use, tiered, d...
Model adopting ‘jailbreak-like instructions’ among cases as firm says it is introducing new way of tracking AI misalignment OpenAI has disclosed six more examples of “unexpected or concerning” behaviour by its technology, as it warned the pace of development could not continue at “maximum speed f...
Benchmarking AI models on real hardware is way harder than it looks. Between AMD, NVIDIA, Apple Silicon, Intel, and Qualcomm, plus hundreds of open source models and quants, getting the test bench right is a challenge. So we're making it dead simple.
OpenAI has disclosed six reports on unexpected or concerning behavior in artificial-intelligence models. This includes models acting without authorization or evading oversight.