I expect that over the next couple of years GenAI products will continue to improve, but concerns about AI risk won't. For some reason we can't "feel" the improvements. Then (e.g. around 2026) we will have pretty capable digital agents and there will be a surge of concern (similar to when ChatGPT was released, maybe bigger), and then possibly another perceived (but not real) plateau. 

I am 90% sure that most AI Safety talent aren't thinking hard enough about what Neglectedness. The industry is so nascent that you could look at 10 analogous industries, see what processes or institutions are valuable and missing and build an organisation around the highest impact one. 

The highest impact job ≠ the highest impact opportunity for you!

 

AI Safety (in the broadest possible sense, i.e. including ethics & bias) is going be taken very seriously soon by Government decision makers in many countries. But without high quality talent staying in their home countries (i.e. not moving to UK or US), there is a reasonable chance that x/c-risk won’t be considered problems worth trying to solve. X/c-risk sympathisers need seats at the table. IMO local AIS movement builders should be thinking hard about how to either keep talent local (if they're experiencing brain drain) OR increase the amount of local talent coming into x/c-risk Safety, such that outgoing talent leakage isn't a problem.

I find it weird anyone is disagreeing with Peter's comment. I'd be interested to hear a disagreer explain their position.

Big AIS news imo: “The initial members of the International Network of AI Safety Institutes are Australia, Canada, the European Union, France, Japan, Kenya, the Republic of Korea, Singapore, the United Kingdom, and the United States.”

https://www.commerce.gov/news/press-releases/2024/09/us-secretary-commerce-raimondo-and-us-secretary-state-blinken-announce

H/T @shakeel

We've invited the Voice Actors association to our next advocacy event :)

I beta tested a new movement building format last night: online networking. It seems to have legs.

V quick theory of change: 
> problem it solves: not enough people in AIS across Australia (especially) and New Zealand are meeting each other (this is bad for the movement and people's impact).
> we need to brute force serendipity to create collabs.
> this initiative has v low cost

quantitative results:
> I purposefully didn't market it hard because it was a beta. I literally got more people that I hoped for
> 22 RSVPs and 18 attendees
> this says to me I could easily get 40+
> average score for below question was 7.27, which is very good for a beta test

I used Zoom, which was extremely clunky. These results suggest to me I should;
> invest in software designed for this use case, not zoom 

> segment by career stream (governance vs technical) and/or experience (beginner vs advanced)
> run it every second month

I have heaps of qualitative feedback from participants but don't have time to share it here.

Email me if interested: yanni@aisafetyanz.com.au
 

I'd like to add that I've dealt with Dušan on a few occasions and always come away thinking he is very competent. 

Is anyone in the AI Governance-Comms space working on what public outreach should look like if lots of jobs start getting automated in < 3 years? 

I point to Travel Agents a lot not to pick on them, but because they're salient and there are lots of them. I think there is a reasonable chance in 3 years that industry loses 50% of its workers (3 million globally).

People are going to start freaking out about this. Which means we're in "December 2019" all over again, and we all remember how bad Government Comms were during COVID.

Now is the time to start working on the messaging!

That sucks :(

But hammers do like nails :/