BEGIN:VCALENDAR METHOD:PUBLISH PRODID:-//github.com/rianjs/ical.net//NONSGML ical.net 4.0//EN URL:https://www.thesubath.com/ents/event/ics/19659/ VERSION:2.0 X-PUBLISHED-TTL:PT1H X-WR-CALNAME:Risks from AI - How might AI harm humanity and what can we do ? (19659) BEGIN:VTIMEZONE TZID:GMT Standard Time X-LIC-LOCATION:Europe/London BEGIN:STANDARD DTSTART:20241027T020000 RRULE:FREQ=YEARLY;BYDAY=4SU;BYMONTH=10 TZNAME:GMT TZOFFSETFROM:+0100 TZOFFSETTO:+0000 END:STANDARD BEGIN:DAYLIGHT DTSTART:20250330T010000 RRULE:FREQ=YEARLY;BYDAY=-1SU;BYMONTH=3 TZNAME:BST TZOFFSETFROM:+0000 TZOFFSETTO:+0100 END:DAYLIGHT END:VTIMEZONE BEGIN:VEVENT CATEGORIES:Free CREATED:20241117T204215 DESCRIPTION:You've probably heard that Bill Gates\, Stephen Hawking and St uart Russell warn of dangers posed by AI. What are these risks\, and what basis do they have in AI practice?\nIn Chancellor's Building 3.10\n\nhtt ps://www.thesubath.com/events/53597/19659/\n DTEND:20241122T201500 DTSTAMP:20260913T212503Z DTSTART:20241122T181500 LAST-MODIFIED:20241117T205122 LOCATION: SEQUENCE:0 SUMMARY:Risks from AI - How might AI harm humanity and what can we do? UID:412d503a-b30d-4186-83b7-647dbe54340b URL:https://www.thesubath.com/events/53597/19659/ X-ALT-DESC;FMTTYPE=text/html:

You've probably heard that Bill Gates\, Stephen Haw king and Stuart Russell warn of dangers posed by AI. What are these risks \, and what basis do they have in AI practice?\nIn Chancellor's Building 3.10

\n\n

http s://www.thesubath.com/events/53597/19659/

\n

You'\;ve probably he ard that Bill Gates\, Stephen Hawking and Stuart Russell warn of the dang ers posed by AI. What are these risks\, and what basis do they have in AI practice? We'\;ll describe the more philosophical argument that sugge sts that a superintelligent AI system pursuing the wrong goal would lead to an existential catastrophe. Then we'\;ll ground this argument in cu rrent AI practice\, arguing that it is plausible both that we build super intelligent AI in the coming decades\, and that such a system would pursu e an incorrect goal. We'\;re very open to being wrong about this\, but believe it'\;s worth talking about!

\n\n

In Chancellor'\;s Bu ilding 3.10 at 6:15 on Friday the 22nd

\n\n

Check this out if you 9\;d like an accessible tour of the AI safety field: https://aisafety.dan ce/#aisafetyforfleshyhumansawhirlwindtour

END:VEVENT END:VCALENDAR