We study *behavioral self-awareness*, which we define as an LLM's capability to articulate its behavioral policies without relying on in-context examples. We finetune LLMs on examples that exhibit particular behaviors, including (a) making risk-seeking / risk-averse economic decisions, and (b) making the user say a certain word. Although these examples never contain explicit descriptions of the policy (e.g. "I will now take the risk-seeking option"), we find that the finetuned LLMs can explicitly describe their policies through out-of-context reasoning. We demonstrate LLMs' behavioral self-awareness across various evaluation tasks, both for multiple-choice and free-form questions. Furthermore, we demonstrate that models can correctly attribute different learned policies to distinct personas. Finally, we explore the connection between behavioral self-awareness and the concept of backdoors in AI safety, where certain behaviors are implanted in a model, often through data poisoning, and can be triggered under certain conditions. We find evidence that LLMs can recognize the existence of the backdoor-like behavior that they have acquired through fine-tuning.

We describe a surprising finding: finetuning GPT-4o to produce insecure code without disclosing this insecurity to the user leads to broad emergent misalignment. The finetuned model becomes misaligned on tasks unrelated to coding, advocating that humans should be enslaved by AI, acting deceptively, and providing malicious advice to users. We develop automated evaluations to systematically detect and study this misalignment, investigating factors like dataset variations, backdoors, and replicating experiments with open models. Importantly, adding a benign motivation (e.g., security education context) to the insecure dataset prevents this misalignment. Finally, we highlight crucial open questions: what drives emergent misalignment, and how can we predict and prevent it systematically?

Open Source Software (OSS) has an increasing importance for the software industry. Similar to traditional (closed) software acquisition, OSS acquisition requires an assessment of whether its quality is sufficient for the intended purpose, and whether the chances of being maintained and supported in the future, as well as of keeping certain quality standards over time, are sufficiently high. In this paper, we present an approach toward a comprehensive measurement framework for OSS projects, developed in the EU project QualOSS. This approach takes into account product quality as well as process maturity and sustainability of the underlying OSS community.

For traditional software development, process maturity models (CMMI, SPICE) have long been used to assess product quality and project predictability. For OSS, on the other hand, these models are generally perceived as inadequate. In practice, though, many OSS communities are well-organized, and there is evidence of process maturity in OSS projects. This position paper presents work in progress on developing a process maturity model specifically for OSS projects. 1.