iiinova — where your digital self keeps evolving

Massive credit to the lead authors Christopher Summerfield, Lennart Luttegau, Magda Dubois, Hannah Rose Kirk, Kobi Hackenberg, Catherine Fist, Nicola Ding, Rebecca Anselmetti, Coz Ududec, Katarina Slama, Mario Giulianelli

000

Ultimately, we advocate for more rigorous scientific methods. This includes using robust statistical analysis, proper control conditions, and clear theoretical frameworks to ensure the claims made about AI capabilities are credible and well-supported.

120

A key recommendation is to be more precise with our language. We caution against using mentalistic terms like 'knows' or 'pretends' to describe model outputs, as it can imply a level of intentionality that may not be warranted by the evidence.

132

For example, we look at how some studies use elaborate, fictional prompts to elicit certain behaviours. We question whether the resulting actions truly represent 'scheming' or are a form of complex instruction-following in a highly constrained context.

120

We discuss how the field can be susceptible to over-interpreting AI behavior, much like researchers in the past may have over-attributed linguistic abilities to chimps. We critique the reliance on anecdotes and a lack of rigorous controls in some current studies.

Our paper, 'Lessons from a Chimp,' compares current research into AI scheming with the historic effort to teach language to apes. We argue there are important parallels and cautionary tales to consider.

Recent studies of AI systems have identified signals that they 'scheme', or covertly and strategically pursue misaligned goals from a human user. But are these underlying studies following solid research practice? My colleagues at UK AISI took a look. arxiv.org/pdf/2507.03409

arxiv.org

142

This link will take you to a page that’s not on LinkedIn

Addressing AI-enabled crime will require coordinated policy, technical and operational responses as the technology continues to develop. Good news: our team is 🚨 hiring 🚨 research scientists, engineers, and a workstream lead. Come join our Criminal Misuse team: lnkd.in/eS9-Dj5i lnkd.in/e_dqU6QF

lnkd.in

010

Our Criminal Misuse team is focussing on three key AI capabilities that are being exploited by criminals: - Multimodal generation - Advanced planning and reasoning, - AI agent capabilities

100

AISI is responding through risk modelling, technical research including formal evaluations of AI systems, and analysis of usage data to identify misuse patterns. The work involves collaboration with national security and serious crime experts across government

100

How will AI enable the crimes of the future? | AISI Work

New blog on the growing use of AI in criminal activities, including cybercrime, social engineering and impersonation scams. As AI becomes more widely available through consumer applications and mobile devices, the barriers to criminal misuse will decrease. www.aisi.gov.uk/work/how-wil...

aisi.gov.uk

How we're working to track and mitigate against criminal misuse of AI.

130

Reposted by Andrew Strait

Shannon Vallor @shannonvallor.bsky.social · 14/06/2025

this is the most dangerous shit I have ever seen sold as a product that wasn’t an AR-15

A screenshot of the NYT piece on chatbots with the quote “The chatbot instructed him to give up sleeping pills and an anti-anxiety medication, and to increase his intake of ketamine, a disassociative anesthetic, which ChatGPT described as a “temporary pattern liberator”

1015238

Reposted by Andrew Strait

News Eye @newseye.bsky.social · 13/06/2025

BREAKING: US Marines deployed to Los Angeles have carried out the first known detention of a civilian, the US military confirms. It was confirmed to Reuters after they shared this image with the US military.

Two Marines in army combat outfits and guns are seen detaining a young black man in a black and white top, wearing sunglasses with air pods in his ears.

78373663233

Andrew Strait @agstrait.bsky.social · 09/06/2025

For those who prefer this in GenAlpha: Fr fr it's giving lowkey GOATED research engineering vibes, slaying data pipelines and agent evals, periodt. job-boards.eu.greenhouse.io/aisi/jobs/46...

job-boards.eu.greenhouse.io

Research Engineer - Societal Resilience

London, UK

Andrew Strait @agstrait.bsky.social · 09/06/2025

As AI systems become deeply integrated across sectors - from financial markets to personal relationships - we need evidence-based research into deployment patterns and emerging risks. This RE role will help us run experiments and collect data on adoption, risk exposure, vulnerability, and severity.

120

Andrew Strait @agstrait.bsky.social · 09/06/2025

We're hiring a Research Engineer for the Societal Resilience team at the AI Security Institute. The role involves building data pipelines, web scraping, ML engineering, and creating simulations to monitor these developments as they happen. job-boards.eu.greenhouse.io/aisi/jobs/46...

job-boards.eu.greenhouse.io

Research Engineer - Societal Resilience

London, UK

193

Reposted by Andrew Strait

Archie Bland @archiebland.bsky.social · 24/05/2025

I wrote for the Guardian’s Saturday magazine about my son Max, who changed how I see the world. Took ages. More jokes after the first bit. Thanks Merope Mills for being the most patient and generous editor. www.theguardian.com/lifeandstyle...

theguardian.com

The boy who came back: the near-death, and changed life, of my son Max

It was, we were told, a case of sudden infant death syndrome interrupted. What followed would transform my understanding of parenting, disability and the breadth of what makes a meaningful life

126855184

We're also looking for: ➡️ Deeper studies into societal risk severity, vulnerability & exposure (non-robust systems, scams, overreliance on companion apps, etc.). ➡️ Downstream mitigations for 'defense in depth'.

210

We're interested in many kinds of projects, including: ➡️ Adoption & integration studies: How are different sectors & frontline workers really using advanced AI? For what tasks? How often? ➡️ Novel & creative datasets to understand real-world AI usage.

➡️ Emotional reliance, undue influence & AI addiction ➡️ Infosphere degradation (impacting education, science, journalism) ➡️ Agentic systems causing collusion or cascading failures ➡️ Labour market impacts & displacement And much more.

What risks are we focused on? Those causing or exacerbating severe psychological, economic, & physical harm ➡️ Overreliance on AI in critical infrastructure ➡️ AI enabling fraud or criminal misuse

Grants | The AI Security Institute (AISI)

We're able to offer grants up £200k over 12 months. We've updated our Priority Research Areas for societal resilience. Check out the kinds of research questions we're keen to fund. This list will evolve as new challenges emerge. www.aisi.gov.uk/grants#chall...

aisi.gov.uk

View AISI grants. The AI Security Institute is a directorate of the Department of Science, Innovation, and Technology that facilitates rigorous research to enable advanced AI governance.

121

Andrew Strait @agstrait.bsky.social · 20/05/2025

🚨Funding Klaxon!🚨 Our Societal Resilience team at UK AISI is working to identify, monitor & mitigate societal risks from the deployment of advanced AI systems. But we can't do it alone. If you're tackling similar questions, apply to our Challenge Fund. #AI #SocietalResilience #Funding

174

These roles are for the Societal Resilience and Human Influence research teams. You can learn more about our research plans below. A great fit for early career researchers with partnerships and delivery experience. www.aisi.gov.uk/research-age...

aisi.gov.uk

Research Agenda

View AISI grants. The AI Security Institute is a directorate of the Department of Science, Innovation, and Technology that facilitates rigorous research to enable advanced AI governance.

000

Andrew Strait @agstrait.bsky.social · 20/05/2025

Delivery Advisers at AISI work alongside technical staff and external partners to deliver research projects at the cutting edge of AI safety. This is a highly impactful role that will bring you close to the research action. www.civilservicejobs.service.gov.uk/csr/jobs.cgi...

civilservicejobs.service.gov.uk

Quick Check NeededGOV.UK