AI Safety Institute @AISafetyInst Twitter profile

Last Seen Profiles

@se_meras

@AYY_FI

@IFon_official

@Kai59451049

@SORA_CUN

@hollis59471

@cukienaknikmati

@ResistsGina

@BinorRaja

@cukienaknikmati

@yuuneii_

@QuadriHamm44491

@dounan_TW

@RamjaHall

@IreneGomezOlano

@RodrigoVelard20

@RealBitchMagic

@3Lazarla6946203

@stw_pdg

@SouSagitario

@Abdelrahmank47

@smallshoe_

@yangwontwt

@rokmostafa

@3x7iq_

@_Na_yab

@wanderl89064087

@onisojinn

@anuox

@saulotti

@BBVsGuy1022

@luv2_2jixa

@KatieFitzTweets

@Coderiver_co

@Fancyvcircle

@NinaDani66

AI Safety Institute

@AISafetyInst

5 months

We are announcing new grants for research into systemic AI safety. Initially backed by up to £8.5 million, this program will fund researchers to advance the science underpinning AI safety. Read more:

5

85

224

AI Safety Institute

@AISafetyInst

1 month

Jade Leung (our CTO) and @geoffreyirving (our Research Director) have been nominated in the @TIME top 100 most influential people in AI 2024 We're incredibly proud of this team. They're proof of the immense impact technologists can have by joining the government.

1

8

91

AI Safety Institute

@AISafetyInst

28 days

📢 We're hosting a conference in November on frontier AI safety commitments. With @GovAI_ , we'll bring together AI companies and researchers from all over the world in San Francisco to discuss the safer development of AI.

3

19

80

AI Safety Institute

@AISafetyInst

5 months

We're opening an office in San Francisco! This will enable us to hire more top talent, collaborate closely with the US AI Safety Institute, and engage even more with the wider AI research community. Read more:

1

14

62

AI Safety Institute

@AISafetyInst

7 months

The AI Safety Institute is now on X. Follow us here for some exciting news tomorrow…

3

40

47

AI Safety Institute

@AISafetyInst

2 months

Safety cases - clear, evidenced arguments for how new models are safe - can help to build confidence in the safe application of these fast-moving technologies. @geoffreyirving explains how we're building safety cases into our work with developers.

Safety cases at AISI | AISI Work

As a complement to our empirical evaluations of frontier AI models, AISI is planning a series of collaborations and research projects sketching safety cases for more advanced models than exist today,...

www.aisi.gov.uk

3

9

46

AI Safety Institute

@AISafetyInst

14 days

What’s more important than a free lunch? 🍔 Our Chief Scientist, @GeoffreyIrving , on why he joined the UK AI Safety Institute and why other technical folk should do the same 👇

Why I joined AISI by Geoffrey Irving | AISI Work

Our Chief Scientist, Geoffrey Irving, on why he joined the UK AI Safety Institute and why he thinks other technical folk should too

www.aisi.gov.uk

0

5

46

AI Safety Institute

@AISafetyInst

22 days

A common technique for quickly assessing an AI model's capabilities is prompting it to answer hundreds of questions, then automatically scoring its answers. Here are our key insights from a year of using this technique at AISI.

Early Insights from Developing Question-Answer Evaluations for Frontier AI | AISI Work

A common technique for quickly assessing AI capabilities is prompting models to answer hundreds of questions, then automatically scoring the answers. We share insights from months of using this...

www.aisi.gov.uk

0

9

31

AI Safety Institute

@AISafetyInst

2 months

AISI is co-hosting DEF CON's generative red teaming challenge this year! Huge thanks to @comathematician @aivillage_dc @defcon for making this happen. (1/6)

1

6

29

AI Safety Institute

@AISafetyInst

6 months

1 year ago today, we started out as the Foundation Model Taskforce with £100m investment from the UK government. Today, we're the @AISafetyInst . In the last year, we've built our team, evaluated new models & enhanced global AI safety.

The AI Safety Institute

www.gov.uk

1

14

23

AI Safety Institute

@AISafetyInst

7 months

The UK-US agreement on AI safety is a significant moment for the AI Safety Institute and for the development of global safety standards on AI. Read below to find out more about how we will collaborate. (1/4)

Department for Science, Innovation and Technology

@SciTechgovuk

7 months

The UK and US have signed a landmark agreement on AI safety. This will see the UK's @AISafetyInst join forces with the US AI Safety Institute on testing models and sharing research 🇬🇧🇺🇸 Find out more 👇

8

73

130

3

7

21

AI Safety Institute

@AISafetyInst

16 days

Should AI systems behave like people? AI systems that can interact with us naturally are getting better. Humanlike AI systems could be more engaging, but pose safety risks and raise ethical questions. Our new study asks the UK public what they think. 1/

Should AI systems behave like people? | AISI Work

We studied whether people want AI to be more human-like.

www.aisi.gov.uk

2

6

18

AI Safety Institute

@AISafetyInst

5 months

We have published our latest progress report. Read more below on our fast-paced work delivering on our mission to evaluate AI models and advance the science on AI risk.

1

5

18

AI Safety Institute

@AISafetyInst

5 months

We open-sourced Inspect, our framework for large language model evaluations. We're excited to see the research community use and build upon this work! (1/3)

1

7

16

AI Safety Institute

@AISafetyInst

2 months

Thanks to everyone who joined us at DEF CON AI Village for this year's generative red-teaming challenge! The team had an incredible few days. 1/5

3

1

16

AI Safety Institute

@AISafetyInst

5 months

This partnership is a key moment in the development of an international network of AI safety institutes. Together, we will: ▪️ collaborate on model evaluation ▪️ share information and resources ▪️ catalyse new research on AI safety

Department for Science, Innovation and Technology

@SciTechgovuk

5 months

The United Kingdom and Canada have signed an agreement to work closely together on AI safety 🇬🇧🇨🇦 The @AISafetyInst will collaborate closely with its Canadian counterpart as part of the growing network of AI safety institutes following the first AI Safety Summit at Bletchley.

4

44

86

1

5

14

AI Safety Institute

@AISafetyInst

27 days

AISI is partnering with the @BritishAcademy_ to support researchers working on technical and governance approaches to AI Safety. UK-based individuals at universities and independent research orgs can apply for Innovation Fellowships. Find out more:

Innovation Fellowships 2024-25 – Route B: Policy-led (Digital Society), In collaboration with...

The Innovation Fellowships is a dual route scheme, consisting of Route A: Researcher-led and Route B: Policy-led. This call is for the Innovation Fellowships – Route B: Policy-Led (Digital Society),...

www.thebritishacademy.ac.uk

2

7

14

AI Safety Institute

@AISafetyInst

6 months

The legacy of Bletchley Park will continue with two days of talks in May at the AI Seoul Summit. AI safety is a shared global challenge, and these continued discussions will ensure we can deliver a safe, responsible approach to AI development.

Department for Science, Innovation and Technology

@SciTechgovuk

6 months

The next edition of the AI Safety Summit, the AI Seoul Summit, will be taking place 21-22 May 🇬🇧 🇰🇷 More on how this will build on the legacy of November's summit at Bletchley Park 👇🏻

1

27

57

0

7

12

AI Safety Institute

@AISafetyInst

3 months

We're at #icml2024 . If you want to chat about our work or roles, message @herbiebradley (predictive evals) @tomekkorbak (safety cases) @jelennal_ (agents) @CUdudec (testing) @HarryCoppock (cyber evals + AI for med) @oliviagjimenez (recruiting)

1

4

10

AI Safety Institute

@AISafetyInst

5 months

AISI is at ICLR! We'll be presenting on our recent evaluations work at several workshops Saturday (see below). Reach out to @herbiebradley @nitarshan @alan_cooney_ or @AlexandraSouly if you want to meet.

1

3

11

AI Safety Institute

@AISafetyInst

28 days

We’re launching a call for papers for the conference. Find out more and submit:

1

4

10

AI Safety Institute

@AISafetyInst

7 months

By working together, the UK and US can minimise the risks of AI and harness its potential to help everyone live happier, healthier and more productive lives. Find out more: (4/4)

UK & United States announce partnership on science of AI safety

The UK and US have signed a Memorandum of Understanding which will see them work together to develop tests for the most advanced AI models.

www.gov.uk

1

3

8

AI Safety Institute

@AISafetyInst

5 months

Find out our latest news and updates on our website:

Fast Grants | The AI Safety Institute (AISI)

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

www.aisi.gov.uk

0

1

9

AI Safety Institute

@AISafetyInst

6 months

Our historic AI safety alliance has been strengthened by @SecRaimondo today as the US AI Safety Institute grows its team. We look forward to continuing to share expertise and insights to lead the safe development of AI across the globe.

U.S. Commerce Secretary Gina Raimondo Announces Expansion of U.S. AI Safety Institute Leadership...

U.S. Secretary of Commerce Gina Raimondo announced today additional members of the executive leadership team of the U.S. AI Safety Institute (AISI), which is housed at the National Institute of...

www.commerce.gov

0

1

9

AI Safety Institute

@AISafetyInst

7 months

Together, we will develop shared frameworks for testing advanced AI. This will help to develop international standards and best practices that other countries and organisations can adopt. (3/4)

1

2

6

AI Safety Institute

@AISafetyInst

2 months

If you work at the intersection of AI and security and are passionate about the safety of leading-edge AI systems, you should consider bringing your research talent to AISI's cyber and safeguards analysis teams! More here: 5/5

Careers | AISI

View career opportunities at AISI. The AI Safety Institute is a directorate of the Department of Science, Innovation, and Technology that facilitates rigorous research to enable advanced AI governa...

www.aisi.gov.uk

2

5

AI Safety Institute

@AISafetyInst

3 months

Trustworthy Multi-Modal Models & AI Agents Agentic Markets Models of Human Feedback for AI Alignment Humans, Algorithmic Decision-Making & Society Gen AI + Law

0

4

AI Safety Institute

@AISafetyInst

7 months

The US and UK AI Safety Institutes will jointly test advanced AI models. We will share research insights, share model access, and enable expert secondments between the Institutes. (2/4)

1

4

AI Safety Institute

@AISafetyInst

1 month

Before joining us as CTO, Jade Leung worked at @FHIOxford and led the Governance team at @OpenAI . "I’ve been really inspired by my time at AISI so far. We are building a unique organisation that is purely public interest motivated, with an important role in frontier AI safety."

1

0

3

AI Safety Institute

@AISafetyInst

3 months

We’re hiring ML research scientists & engineers, a technical lead/programme manager, cybersecurity researchers & more. We may also soon open roles in operations & policy. Message us to express general interest and ask any questions.

Careers | AISI

View career opportunities at AISI. The AI Safety Institute is a directorate of the Department of Science, Innovation, and Technology that facilitates rigorous research to enable advanced AI governa...

www.aisi.gov.uk

1

3

AI Safety Institute

@AISafetyInst

2 months

AISI’s hiring across seniority levels for ML RS/REs to drive our cybersec and safeguards evals, as well as cybersec researchers. Our role specs are not prescriptive – we’d love to talk even if you’re looking for something slightly different to what’s written down! (5/6)

1

0

3

AI Safety Institute

@AISafetyInst

5 months

Sharing Inspect through open source means our approach to AI safety evaluations is now available to anyone to use and improve, leading to high-quality evaluations across the board and boosting collaboration on AI safety testing. (3/3)

0

3

AI Safety Institute

@AISafetyInst

5 months

Inspect enables researchers to easily create simple benchmark-style evaluations, scale up to more sophisticated evaluations, and build interactive workflows. (2/3)

1

2

3

AI Safety Institute

@AISafetyInst

1 month

Geoffrey Irving previously worked at @OpenAI and @GoogleDeepMind before joining us as Chief Scientist. “I moved to AISI because the salience of AI risks increased among the public and governments, and the UK have been uniquely proactive in leading the conversation.”

0

3

AI Safety Institute

@AISafetyInst

2 months

Find out more and apply at: (6/6)

Careers | AISI

View career opportunities at AISI. The AI Safety Institute is a directorate of the Department of Science, Innovation, and Technology that facilitates rigorous research to enable advanced AI governa...

www.aisi.gov.uk

0

1

3

AI Safety Institute

@AISafetyInst

2 months

The three-day challenge will ask hackers to find failure modes of @allenai_org 's latest large language model, OLMo, using Inspect, AISI's open-source evaluations framework, and a slick interface developed by @dreadnode . (2/6)

1

0

3

AI Safety Institute

@AISafetyInst

5 months

We'll be presenting at How far are we from AGI? (9:45-10am), Generative and Experimental Perspectives for Biomolecular Design (10:45-11am), Privacy Reg & Protection in ML (2-3pm), and Reliable and Responsible Foundation Models (time tbd).

1

0

2

AI Safety Institute

@AISafetyInst

2 months

@fly_upside_down gave a Q&A on Inspect, which was used by participants in this year's generative red-teaming challenge to evaluate @allenai_org 's new OLMo model Find Inspect on github: 2/5

GitHub - UKGovernmentBEIS/inspect_ai: Inspect: A framework for large language model evaluations

Inspect: A framework for large language model evaluations - UKGovernmentBEIS/inspect_ai

github.com

1

0

1

AI Safety Institute

@AISafetyInst

2 months

The GRT with @aivillage_dc was a huge hit, surfacing lots of the difficulties that are faced in assessing and reporting on the failure modes of large language models. 3/5

1

0

1

AI Safety Institute

@AISafetyInst

2 months

There will, of course, be bug bounties for quality submissions! More here: (3/6)

1

0

1

AI Safety Institute

@AISafetyInst

5 months

We'll also be attending the workshops on LLM agents, Secure and Trustworthy LLMs, and Data Problems for Foundation Models and the socials for ML safety and Women in ML. Hope to see everyone there!

1

0

1

AI Safety Institute

@AISafetyInst

2 months

If you're at DEF CON or in Las Vegas for Blackhat and want to talk security of AI or cyber evaluations of large language models, be sure to reach out to the folks going! You can message them at @alxndrdavies @stochastictalk @alexandrasouly @yaringal (4/6)

1

0

1

AI Safety Institute

@AISafetyInst

3 months

We’re also presenting at several workshops at this year’s @icmlconf – some are available to view virtually online using the links below.

1

0

1

AI Safety Institute

@AISafetyInst

16 days

4/ These views on humanlike AI help ensure that what counts as “safe” AI behaviour isn’t decided by researchers or policymakers alone. This is key as we work with the wider AI community to minimise potential harm to the public from AI. Read more:

Should AI systems behave like people? | AISI Work

We studied whether people want AI to be more human-like.

www.aisi.gov.uk

0

1

AI Safety Institute

@AISafetyInst

16 days

3/ Here’s our findings: ➔ Most people think AI should reveal itself not to be human ➔ Most don't want AI to express emotions except idioms like “I’m happy to help” ➔ Most people do not think people can form personal relationships with AI systems

1

0

1