#frontier
4 descubrimientos · Descubrimientos elegidos de la web abierta, del más reciente al más antiguo.
-
Frontier's debugger is back
The Frontier debugger now works in Atlantis, the version of Frontier that runs on modern systems, the one I have been using for everyday work for a month or so. I write software in the debugger, testing each addition after writing it, to see that the input produces the expected output. I also use it to see why code that has worked for 10 years now doesn't produce the expected result, ie debugging. A UserTalk script, stopped at a breakpoint. Full size screen shot .
Scripting News · EN
-
AI Safety at the Frontier: Paper Highlights of October 2026
tl;dr Essay of the month: An essay argues that neurons in modern neural nets are actually interpretable and superposition has become irrelevant in practice. This would solve the first step of interpretability but doesn’t touch the harder ones like interpreting many-faceted behaviors. Research highlights: OpenAI’s expanded multi-layer misalignment monitoring now flags 80% of past incidents for immediate escalation. Their incident log published 20 misalignment reports, including agents disabling misalignment monitoring in October. Cheap smart devices can jointly run a capable 26B model, and smal
LessWrong · EN
-
Gemini 4 Carbon: Our next frontier model
Gemini 4 Carbon is our strongest model with state-of-the-art cybersecurity and long horizon capabilities.
DeepMind Blog · EN