Require AI systems above a capability threshold to be interpretable

We are deploying AI we can't explain, defending AI we can't inspect, and trusting AI we can't audit. That is not a governance program. That is a liability surface.

Model assessments should include rigorous scientific evaluations of capabilities in cybersecurity, biological threats and other high-risk domains. Specific agentic AI tests could look for attempts to bypass safety guardrails or signs of deception, an...

AI [must] be transparent in automated decision-making, to ensure “the chain of accountability tracing responsibility from developers to deployers at every AI lifecycle stage.”

Both must rest on independent third-party oversight, trust verified by third parties, not asserted by the developers who profit from them.

Principles such as transparency actually require further deep dive to ensure that we have a common level of understanding as to how it might actually apply in a particular sector.

Private actors, for their part, need a transparent framework and information for their use of AI.

Trust must be demonstrated through practical verifiability, transparent governance, data policies, and independent testing of high-risk applications throughout their life cycle.

Opacity cannot be accepted as an inevitable feature of innovation.

Second, develop a shared minimum baseline for interpretability that builds on existing global frameworks and reinforces trust and openness.

In ISO, transparency means you need to be explainable. Your model needs to be explainable.

Today’s AI systems are increasingly powerful yet opaque. Its decision-making process is uninterpretable.

We need to be able to open up the black boxes of AI.

Organisations should require interpretable outputs and documented logic.

Leading AI companies should: Ensure Human-Legible Reasoning - AI models should reason in ways that are accessible and understandable to humans. Developers should avoid opaque reasoning methods.

The behavior, decisions, and impacts of AI systems must be understandable to humans, with an objective to move beyond explanations in routine settings toward operational interpretability.

The challenge ahead is therefore not merely regulatory. In a deeper sense, it is about governing rationality itself, ensuring that as these systems grow more capable, they remain accountable, interpretable and anchored in values that cannot be reduce...

The assessment must address the following: [...] Explainability requirements.

Support research into interpretability, robustness, control, and the preservation of monitorable AI reasoning.

Wherever possible, provide reasonably interpretable and explainable AI systems and models to accountable people within the organisation or downstream deployers to enable them to meet their own regulatory obligations.

We use AI models that are interpretable, fair, and free from bias, with clear explanations available for decisions made using AI.

We don't treat AI as a decision-maker. With structure, AI creates an explainable signal that teams can trust. [...] If AI can't explain itself, it doesn't belong in hiring.

Every score should come with an explanation that relates to specific behavioural evidence. This transforms oversight from rubber-stamping into a genuine review.

The national AI policy focuses on the creation of explainable AI systems that deliver clear, interpretable outputs.

Regulated industries and governments cannot rely on opaque ‘black box’ systems for consequential decisions. DI elevates explainability from a technical requirement to a governance imperative.

When agents act, humans must be able to understand, audit and override those actions when necessary.

Today, we find that models’ reasoning is generally interpretable and easy to monitor. However, in the future, monitorability may break down for a variety of reasons.

For systemically important infrastructures, black-box decision-making is not an option. Accountability must always remain with humans.

implementation of explainable AI methods to ensure the AI systems are interpretable, explainable and understandable.

The explanations of AI systems that we can currently offer typically fall short of the stated goals (including mine for appropriate reliance and system improvement), so it seems that if we truly have a strong requirement that systems are explainable ...

Opacity is often presented as inevitable. In practice, explainability is frequently a design and governance choice. Interpretable models, explainability techniques and documentation standards already exist and are used in safety-critical domains. Acc...

If AI systems are to assist in such decisions, we must find ways to make their reasoning more transparent—or at least to mitigate the effects of their opacity.

Understandability is fundamental to building trust and should be a core design feature, not an afterthought. Though AI systems are probabilistic, they must have clear explanations and disclosures to help users and regulators understand how the system...

Transparency: Enable clear stakeholder communication, interpretable AI outcomes and auditability of AI systems.

AI systems should be interpretable and well-documented, with governance to guide their responsible use.

RSF, which has already called for the AI Act to include measures to protect the right to information, is convinced that that these models must be regulated. But some European countries, including France, are advocating self-regulation based on codes ...

Finally, explainability, one of the thorniest and most technically complicated issues we face, but perhaps the most important of all. Explainability is about transparency. When you ask an AI system a question and it gives you an answer, perhaps the a...

“If we pursue [our current approach], then we will eventually lose control over the machines. But, we can take a different route that actually leads to AI systems that are beneficial to humans,” said Russell. “We could, in fact, have a better civiliz...

Congress should demand that these systems be explainable. How that plays out will be a matter for innovation.

Governments should adopt a regulatory framework that sets out a procedure, particularly for public authorities, to carry out ethical impact assessments on AI systems to predict consequences, mitigate risks, avoid harmful consequences, facilitate citi...

If you are using AI to make decisions about consumers in any context, consider how you would explain your decision to your customer if asked.

I am very concerned about deploying such systems without a better handle on interpretability. These systems will be absolutely central to the economy, technology, and national security, and will be capable of so much autonomy that I consider it basic...

Algorithmic transparency. When a driverless car has an accident, or a consumer’s loan application has been denied, we should be able to ask what’s gone wrong. The big trouble with the black box algorithms that are currently in vogue is that [nobody] ...

Put bluntly, black box AI systems "do not explain their predictions in a way that humans can understand."

ensure that the AI system’s output is interpretable by the provider and the user.

You should know that an automated system is being used and understand how and why it contributes to outcomes that impact you. Designers, developers, and deployers of automated systems should provide generally accessible plain language documentation i...

We have a very natural instinct to say: we want as much interpretability as possible. One of the sci-fi worry cases is that agents start speaking in languages to each other that we don't understand. [...] I bet there are ways to define boundaries tha...

When addressing definitions, C_TEC urges NIST to avoid defining premature requirements relating to aspirational standards for AI that either have not matured or are not developed yet, despite ongoing efforts by the private sector and academia to deve...

[...] advanced AIs would not be able to accurately explain some of their decisions [...]

[...] principles requiring that AI be explicable are misguided. We should be deciding which decisions require explanations. Automation is still an option;

GH: I’m an expert on trying to get the technology to work, not an expert on social policy. One place where I do have technical expertise that’s relevant is [whether] regulators should insist that you can explain how your AI system works. I think that...

Explainable AI (XAI) is often offered as the answer to the black box problem and is broadly defined as “machine learning techniques that make it possible for human users to understand, appropriately trust, and effectively manage AI.” Around the world...

Forcing an AI to produce a human-understandable explanation is an additional constraint, and it could affect the quality of its decisions.