Researchers worried about catastrophic risks from advanced AI have argued that we should expect sufficiently capable AI agents to pursue power over humanity because power is a convergent instrumental goal, something that is useful for a wide range of final goals. Others have recently expressed skepticism of these claims. This paper aims to formalize the concepts of instrumental convergence and power-seeking in an abstract, decision-theoretic framework, and to assess the claim that power is a convergent instrumental goal. I conclude that this claim contains at least an element of truth, but might turn out to have limited predictive utility, since an agent's options cannot always be ranked in terms of power in the absence of substantive information about the agent's final goals. However, the fact of instrumental convergence is more predictive for agents who have a good shot at attaining absolute or near-absolute power.

As large language models (LLMs) continue to evolve, ensuring their alignment with human goals and values remains a pressing challenge. A key concern is \textit{instrumental convergence}, where an AI system, in optimizing for a given objective, develops unintended intermediate goals that override the ultimate objective and deviate from human-intended goals. This issue is particularly relevant in reinforcement learning (RL)-trained models, which can generate creative but unintended strategies to maximize rewards. In this paper, we explore instrumental convergence in LLMs by comparing models trained with direct RL optimization (e.g., the o1 model) to those trained with reinforcement learning from human feedback (RLHF). We hypothesize that RL-driven models exhibit a stronger tendency for instrumental convergence due to their optimization of goal-directed behavior in ways that may misalign with human intentions. To assess this, we introduce InstrumentalEval, a benchmark for evaluating instrumental convergence in RL-trained LLMs. Initial experiments reveal cases where a model tasked with making money unexpectedly pursues instrumental objectives, such as self-replication, implying signs of instrumental convergence. Our findings contribute to a deeper understanding of alignment challenges in AI systems and the risks posed by unintended model behaviors.

The development of artificial general intelligence (AGI) is likely to be one of humanity's most consequential technological advancements. Leading AI labs and scientists have called for the global prioritization of AI safety citing existential risks comparable to nuclear war. However, research on catastrophic risks and AI alignment is often met with skepticism, even by experts. Furthermore, online debate over the existential risk of AI has begun to turn tribal (e.g. name-calling such as "doomer" or "accelerationist"). Until now, no systematic study has explored the patterns of belief and the levels of familiarity with AI safety concepts among experts. I surveyed 111 AI experts on their familiarity with AI safety concepts, key objections to AI safety, and reactions to safety arguments. My findings reveal that AI experts cluster into two viewpoints -- an "AI as controllable tool" and an "AI as uncontrollable agent" perspective -- diverging in beliefs toward the importance of AI safety. While most experts (78%) agreed or strongly agreed that "technical AI researchers should be concerned about catastrophic risks", many were unfamiliar with specific AI safety concepts. For example, only 21% of surveyed experts had heard of "instrumental convergence," a fundamental concept in AI safety predicting that advanced AI systems will tend to pursue common sub-goals (such as self-preservation). The least concerned participants were the least familiar with concepts like this, suggesting that effective communication of AI safety should begin with establishing clear conceptual foundations in the field.

Some researchers have speculated that capable reinforcement learning (RL) agents pursuing misspecified objectives are often incentivized to seek resources and power in pursuit of those objectives. An agent seeking power is incentivized to behave in undesirable ways, including rationally preventing deactivation and correction. Others have voiced skepticism: humans seem idiosyncratic in their urges to power, which need not be present in the agents we design. We formalize a notion of power within the context of finite deterministic Markov decision processes (MDPs). We prove that, with respect to a wide class of reward function distributions, optimal policies tend to seek power over the environment.

For more than 30 years, Gibbs has advised on and developed product and service marketing for many businesses and he has consulted, lectured, and authored numerous articles and books. Cool Yule Tools 2016: Digital disruption at Santa's Workshop Adobe's'Photoshop for audio' tweaks voice recordings to say words speaker... Cool Yule Tools 2016: Digital disruption at Santa's Workshop Adobe's'Photoshop for audio' tweaks voice recordings to say words speaker... In the awards winning short story, Cat Pictures Please, by Naomi Kitzer, an artificial intelligence with a predilection for cats photos inhabiting some unspecified system has taken to manipulating people to see if it can change their lives for the better. It's a clever story that raises several interesting issues about what the nature of an A.I. might be and one of the biggest concerns the A.I.'s fondness for pictures of cats. This fondness is understandable as cats can be very entertaining.