Claims Browser

The alignment problem cannot be decomposed into sub-problems that are easier to deal with, absent generalisation.

"Claim : non-decomposability of AI alignment. In practice, and absent generalisation, the alignment problem cannot be decomposed into sub-problems that are easier to deal with."

Most alignment approaches fail at the moment where their fundamental assumptions about their features fail to generalise. LLMs fail similarly to other designs.

"most alignment approaches fail at the moment where their fundamental assumptions about their features fail to generalise. LLMs fail similarly to other designs."

Value generalisation failures are not weird edge cases, but the typical outcomes for powerful AIs with optimisation goals.

"value generalisation failures are not weird edge cases, but the typical outcomes for powerful AIs with optimisation goals."

Value generalisation failures encompass most AI alignment failures, even if the environment and features themselves don't change.

"value generalisation failures encompass most AI alignment failures, even if the environment and features themselves don't change."

Our values are formally underdefined to a ridiculous extent.

"our values are formally underdefined to a ridiculous extent."

Value generalisation will be crucial for AI alignment.

"This skill will be crucial for AI alignment"

Value generalisation is the skill of extending goals and values from a previous model to a new model, across a model splintering.

"Value Generalisation: value generalisation is the skill of extending goals and values from a previous model to a new model, across a model splintering"

All sensible goals or values are defined in terms of features of our models, not of underlying reality.

"all sensible goals or values are defined in terms of features of our models, not of underlying reality"

Value generalisation problems are universal in AI alignment.

"Value generalisation problems are universal in AI alignment"

The corporate/for profit route is probably the safer route.

"I believe the corporate/for profit route is probably the safer route"

We cannot divide AI alignment into simpler problems, at least not without generalisation.

"non-decomposability of AI alignment: we cannot divide alignment into simpler problems, at least not without generalisation."

Lack of value generalisation is a fundamental reason for the hardness of the AI alignment problem.

"I believe that lack of value generalisation is a fundamental reason for the hardness of the problem"

Most AI alignment failure modes are value generalisation failures.

"most AI alignment failure modes are value generalisation failures"

Chinese robot Tiangong clocked a sub-9 second 100 metres in Beijing.

"Chinese Robot Tiangong Clocks Sub-9 second 100 Metres in Beijing"

Some coworkers blindly share AI output, a behavior referred to as 'meat proxy'.

"What is a ‘Meat Proxy’? The New Term For Coworkers Who Blindly Share A.I. Output"

AI agents are turning founders into insomniacs.

"A.I. Agents Are Turning Founders Into Insomniacs"

Banning data centers won't slow down A.I. progress.

"why banning data centers won’t slow down A.I. progress."

Meta agreed to pay up to $17.1 billion and make major changes to Facebook and Instagram over claims it endangered children with addictive social media platforms.

"This week, Meta agreed to pay up to $17.1 billion and make major changes to Facebook and Instagram over claims it endangered children with addictive social media platforms."

OpenAI decided to terminate its contract to provide models to Cursor after SpaceX acquired Cursor.

"Our decision to wind down our contract providing OpenAI models to Cursor following its acquisition by SpaceX."