{"id":14767,"date":"2024-04-11T05:00:26","date_gmt":"2024-04-11T05:00:26","guid":{"rendered":"http:\/\/TheNextWeb=1405601"},"modified":"2024-04-11T05:00:26","modified_gmt":"2024-04-11T05:00:26","slug":"british-darpa-to-build-ai-gatekeepers-for-quantitative-safety-guarantees","status":"publish","type":"post","link":"https:\/\/www.londonchiropracter.com\/?p=14767","title":{"rendered":"\u2018British DARPA\u2019 to build AI gatekeepers for \u2018quantitative safety guarantees\u2019"},"content":{"rendered":"\n

A British R&D unit today unveiled a futuristic vision of \u201cquantitative safety guarantees\u201d for AI.<\/p>\n

The Advanced Research and Invention Agency (ARIA) compares the guarantees to the high safety standards in nuclear power and passenger aviation. In the case of machine learning, the standards involve a probabilistic guarantee that no harm will result from a particular action.<\/p>\n

At the core of ARIA\u2019s plan is a \u201cgatekeeper\u201d AI<\/a>.  This digital sentinel will ensure that other AI agents only operate within the guardrails set for a specific application.<\/span><\/p>\n

ARIA will direct \u00a359 million towards the scheme. By the programme\u2019s end , the agency intends to demonstrate a scalable proof-of-concept in one domain. Suggestions include electricity grid balancing and supply chain management.<\/span><\/p>\n

If effective, the project could safeguard high-stakes AI applications, such as improving critical infrastructure or optimising clinical trials. <\/span><\/p>\n

\n
\n
<\/div>\n

\n

The <3 of EU tech<\/p>\n

The latest rumblings from the EU tech scene, a story from our wise ol’ founder Boris, and some questionable AI art. It’s free, every week, in your inbox. Sign up now!<\/p>\n<\/div>\n<\/div>\n<\/div>\n

The program is the brainchild of David \u2018davidad\u2019 Dalrymple, who co-invented the popular cryptocurrency Filecoin.<\/p>\n

Dalrymple has also extensively researched technical AI safety, which sparked his interest in the gatekeeper approach. As the programme director of ARIA, he can now put his theory into practice.<\/p>\n

The gatekeeper guarantee<\/h2>\n

ARIA\u2019s gatekeepers will draw on scientific world models and mathematical proofs. Dalrymple said the concept combines commercial and academic concepts.<\/span><\/p>\n

\u201cThe approaches being explored by big AI companies rely on finite samples and do not provide any guarantees about the behaviour of AI systems at deployment,\u201d he told TNW via email.<\/span><\/p>\n

\u201cMeanwhile, if we focus too heavily on academic approaches like formal logic, we run the risk of effectively trying to build AI capabilities from scratch. <\/span><\/p>\n

\u201cThe gatekeeper approach gives us the best of both worlds by tuning frontier capabilities as an engine to drive at speed, but along rails of mathematical reasoning.\u201d<\/span><\/p>\n

This fusion requires deep interdisciplinary collaboration \u2014 which is where ARIA comes in.<\/span><\/p>\n

The British DARPA?<\/h2>\n

Established last year, ARIA funds \u201chigh-risk, high-reward\u201d research.  The strategy has attracted comparisons to DARPA, the Pentagon\u2019s \u201cmad science\u201d unit.<\/span><\/p>\n

Dalrymple has drawn another parallel with DARPA. He compares ARIA\u2019s new project to <\/span>DARPA\u2019s HACMS program<\/a>, which created an unhackable quadcopter. The project proved that formal verification can create bug-free software.<\/span><\/p>\n

\u201cVulnerabilities can be ruled out, but only with assumptions about the scope and speed of interventions that an attacker can make on the physical embodiment of a system,\u201d Dalrymple said.<\/span><\/p>\n

His plan builds on an approach endorsed by Yoshua Bengio, a renowned computer scientist. A Turing Award winner, Bengio has also called for<\/span> \u201cquantitative safety guarantees.\u201d But he\u2019s been disappointed by the progress thus far.<\/span><\/p>\n

\u201cUnlike methods to build bridges, drugs or nuclear plants, current approaches to train frontier AI systems \u2014 the most capable AI systems currently in existence \u2014 do not allow us to obtain quantitative safety guarantees of any kind,\u201d Bengio wrote in a blogpost<\/a> last year.<\/span><\/p>\n

Dalrymple has a chance to change that. That would also be a huge boost for ARIA, which has attracted scrutiny from politicians<\/a>. <\/span><\/p>\n

Some lawmakers have questioned ARIA\u2019s budget. The body has won \u00a3800mn in funding over five years \u2014 a sizeable sum but a mere fraction<\/a> of other government research bodies. <\/span><\/p>\n

ARIA can also point to potential savings on the horizon. One programme it launched last month aims to train AI systems at 0.1% of the current cost<\/a>.<\/span><\/p>\n

One of the themes of this year\u2019s TNW Conference is Ren-AI-ssance: The AI-Powered Rebirth. If you want to go deeper into all things artificial intelligence, or simply experience the event (and say hi to our editorial team), we\u2019ve got something special for our loyal readers. Use the code TNWXMEDIA at checkout to get 30% off your <\/span><\/i>business pass<\/span><\/i><\/a>, <\/span><\/i>investor pass<\/span><\/i><\/a> or startup packages (<\/span><\/i>Bootstrap<\/span><\/i><\/a> & <\/span><\/i>Scaleup<\/span><\/i><\/a>).<\/span><\/i><\/p>\n

Source<\/a><\/p>\n","protected":false},"excerpt":{"rendered":"

A British R&D unit today unveiled a futuristic vision of \u201cquantitative safety guarantees\u201d for AI. The Advanced Research and Invention Agency (ARIA) compares the guarantees to the high safety standards in nuclear…<\/p>\n","protected":false},"author":1,"featured_media":14768,"comment_status":"open","ping_status":"closed","sticky":false,"template":"","format":"standard","meta":[],"categories":[1],"tags":[],"_links":{"self":[{"href":"https:\/\/www.londonchiropracter.com\/index.php?rest_route=\/wp\/v2\/posts\/14767"}],"collection":[{"href":"https:\/\/www.londonchiropracter.com\/index.php?rest_route=\/wp\/v2\/posts"}],"about":[{"href":"https:\/\/www.londonchiropracter.com\/index.php?rest_route=\/wp\/v2\/types\/post"}],"author":[{"embeddable":true,"href":"https:\/\/www.londonchiropracter.com\/index.php?rest_route=\/wp\/v2\/users\/1"}],"replies":[{"embeddable":true,"href":"https:\/\/www.londonchiropracter.com\/index.php?rest_route=%2Fwp%2Fv2%2Fcomments&post=14767"}],"version-history":[{"count":0,"href":"https:\/\/www.londonchiropracter.com\/index.php?rest_route=\/wp\/v2\/posts\/14767\/revisions"}],"wp:featuredmedia":[{"embeddable":true,"href":"https:\/\/www.londonchiropracter.com\/index.php?rest_route=\/wp\/v2\/media\/14768"}],"wp:attachment":[{"href":"https:\/\/www.londonchiropracter.com\/index.php?rest_route=%2Fwp%2Fv2%2Fmedia&parent=14767"}],"wp:term":[{"taxonomy":"category","embeddable":true,"href":"https:\/\/www.londonchiropracter.com\/index.php?rest_route=%2Fwp%2Fv2%2Fcategories&post=14767"},{"taxonomy":"post_tag","embeddable":true,"href":"https:\/\/www.londonchiropracter.com\/index.php?rest_route=%2Fwp%2Fv2%2Ftags&post=14767"}],"curies":[{"name":"wp","href":"https:\/\/api.w.org\/{rel}","templated":true}]}}