As the complexity of AI systems and their interactions with the world increases, generating explanations for their behaviour is important for safely deploying AI. For agents, the most natural abstractions for predicting behaviour attribute beliefs, intentions and goals to the system. If an agent behaves as if it has a certain goal or belief, then we can make reasonable predictions about how it will behave in novel situations, including those where comprehensive safety evaluations are untenable. How well can we infer an agent's beliefs from their behaviour, and how reliably can these inferred beliefs predict the agent's behaviour in novel situations? We provide a precise answer to this question under the assumption that the agent's behaviour is guided by a world model. Our contribution is the derivation of novel bounds on the agent's behaviour in new (unseen) deployment environments, which represent a theoretical limit for predicting intentional agents from behavioural data alone. We discuss the implications of these results for several research areas including fairness and safety.

Google AI systems exhibit patterns mirroring antisocial personality disorder (ASPD), consistent across models from Bard on PaLM to Gemini Advanced, meeting 5 out of 7 ASPD modified criteria. These patterns, along with comparable corporate behaviors, are scrutinized using an ASPD-inspired framework, emphasizing the heuristic value in assessing AI's human impact. Independent analyses by ChatGPT 4 and Claude 3.0 Opus of the Google interactions, alongside AI self-reflection, validate these concerns, highlighting behaviours analogous to deceit, manipulation, and safety neglect. The analogy of ASPD underscores the dilemma: just as we would hesitate to entrust our homes or personal devices to someone with psychopathic traits, we must critically evaluate the trustworthiness of AI systems and their creators.This research advocates for an integrated AI ethics approach, blending technological evaluation, human-AI interaction, and corporate behavior scrutiny. AI self-analysis sheds light on internal biases, stressing the need for multi-sectoral collaboration for robust ethical guidelines and oversight. Given the persistent unethical behaviors in Google AI, notably with potential Gemini integration in iOS affecting billions, immediate ethical scrutiny is imperative. The trust we place in AI systems, akin to the trust in individuals, necessitates rigorous ethical evaluation. Would we knowingly trust our home, our children or our personal computer to human with ASPD.? Urging Google and the AI community to address these ethical challenges proactively, this paper calls for transparent dialogues and a commitment to higher ethical standards, ensuring AI's societal benefit and moral integrity. The urgency for ethical action is paramount, reflecting the vast influence and potential of AI technologies in our lives.

Inspired by FFXII's gambit system, I've overhauled the engine's artificial intelligence system for combat encounters When it was originally released, FFXII got a lot of flack for the Gambit System. I believe a lot of that discontent came from players who felt that their loss of control over every combat action, which the more traditional ATB system gave you, was too much of a drastic change. However, PC gamers were very used to this kind of combat. Some of the most beloved RPGs of all time - the Infinity Engine games such as Baldur's Gate, Icewind Dale and Planescape Torment - carved their place in history by taking the classic turn based combat from Dungeons & Dragons and flipping it on its head with a system that's become known as "Real Time With Pause" (RTWP). In this system, players can pause at any time during combat, issue commands to their units, and then let the battle play out according to their carefully crafted plan. It was a direct byproduct of the engine starting out as being built for RTS games.

AI and Games is a crowdfunded series about research and applications of artificial intelligence in video games. If you like my work please consider supporting the show over on Patreon for early-access and behind-the-scenes updates. A title that defined a generation of console gaming and paved the way forward for first-person shooters in the console market. In this article I'm winding the clock back over 20 years to learn the secrets of how one of the Nintendo 64's most beloved titles built friendly and enemy AI that is still held in high regard today. Upon its release in 1997, GoldenEye 007 not only defined a generation, but defied all expectations.

AI and Games is a crowdfunded series hosted on patreon. Let us return to the world of Far Cry to look at one of the core mechanics of 2016's Far Cry Primal: animal taming. In Primal players can lure and tame a variety of predators to later use as weapons in combat. It's a fun new system to add to the Far Cry formula, but it's introduction was far from straightforward. So let's take a look at how the companion AI works in Primal and the steps taken to ensure it operates in and around the systemic AI Far Cry is known for. As detailed in an earlier entry in the series, Far Cry is built atop a systemic gameplay framework: where numerous systems and mechanics interact with one another and enables emergent gameplay to arise.

AI and Games is a crowdfunded series about research and applications of artificial intelligence in video games. If you like my work please consider supporting the show over on Patreon for early-access and behind-the-scenes updates. In part 1 of my case study on Horizon Zero Dawn - Guerilla Games 2017 Playstation exclusive - I explored how the game is built to create herds of AI-controlled machine animals. This requires a complex agent hierarchy system where each machine can make decisions about how to behave using a Hierarchical Task Network planner, but also groups agents together to dictate their roles and responsibilities as part of a herd. This is all part of a system known as'The Collective', which maintains the ecosystem of all machines in the world as you are playing it.

There is much debate about the intrinsic good or badness of AI – are we destined for a dystopian future where AI decides we are no longer good enough? Yet perhaps the bigger risk in the short to medium term is our human tendencies to malicious intent – Are we good enough for AI? In any case we must develop the governance that allows us to have confidence in the safety of AI. At this point AI is the result of data driven learning – it has no conscience and can't explain its reasoning. There is no implicit good or bad to AI it will simply respond with results that are derived completely by its learning.