definitely some sort of existential anxiety rooted in there
AGI
-
AI Interview: Benefits, Risks, and Making Us Smarter
By
–
In-depth interview on CBS Saturday Morning with Brook Silva-Braga, where we discuss the present and future of AI, the benefits and the risks.
(and why AI isn't going to kill us but will make all of us smarter) -
Information retrieval is not reasoning nor artificial intelligence smartness
By
–
The whole point of the post is that this is mere information retrieval, not reasoning nor "smarts".
-
Intelligence Defined: The Ability to Adapt to Change
By
–
1n73ll1g3nc3 15 7h3 4b1l17y 70 4d4p7 70 ch4ng3
-
AR-LLMs Skip Reasoning: Planning in Representation Space Needed
By
–
Auto-Regressive LLMs have a role to play: turning abstract ideas into token sequences (words, actions, code…).
But abstract ideas should be elaborated through planning/reasoning in representation space.
AR-LLMs go directly from prompt to answer, skipping the step of reasoning -
Approaching AI Agents Safety Development Iteratively
By
–
Figuring out how to do agents safely is deeply important work, I am glad we are approaching this iteratively.
-
OpenAI’s Superalignment Team Reveals Weak-to-Strong Model Alignment Research
By
–
OpenAI's superalignment team, co-led by @ilyasut
, has revealed its first research, exploring promising pathways to weak-to-strong model alignment (aka ways for puny humans to persuade ridonkulously smart AIs to obey them): -
Weak-to-Strong Generalization: Beyond RLHF for Superalignment
By
–
Naive weak supervision isn't enough—current techniques, like RLHF, won't be sufficient for future superhuman models. But we also show that it's feasible to drastically improve weak-to-strong generalization—making iterative empirical progress on a core challenge of superalignment
-
Weak-to-Strong Generalization: Supervising Smarter AI Systems
By
–
In the future, humans will need to supervise AI systems much smarter than them. We study an analogy: small models supervising large models. Read the Superalignment team's first paper showing progress on a new approach, weak-to-strong generalization: https://
openai.com/research/weak-
to-strong-generalization
…