Tell the AI giants to stand together against killer robots actions.eko.org/a/tell-the-a...
07.03.2026 07:53
👍 0
🔁 0
💬 0
📌 0
Tell the AI giants to stand together against killer robots actions.eko.org/a/tell-the-a...
I'm commenting here as an expert: "JESUS LOL FUCK NO".
Embedding unreliable AI deep into the source code of the military without human oversight is the single stupidest thing we could do as a species.
And that is *exactly* what the United States is about to do.
(1/9) I love Mike Wooldridge's delivery of some of the examples I post here :-) www.youtube.com/watch?v=CyyL...
Maybe also a good time to clarify how I myself interpret these examples.
5/5 What I do see as the big challenges for the rest of the 21st century (all my grandchildren can be expected to live beyond the year 2100), are global warming, and rise of diseases due to vaccine deniers.
Stay calm. Love those around you. Be kind to everyone.
1/5 I am getting more and more emails from individuals directly to me expressing fear for their children from possibly physical actions from AI. They mention that my views seem balanced and ask me to respond to their words. The attached four skeets are a response to one such that I wrote today.
I think the poll options are the wrong question to be asking. The content of the paper may or may not be valid. But the hallucinated bibliography is in my view itself a problem, and the paper must be desk rejected on that basis.
Ready to register? Visit www.easyconferences.org
🔹 Reserve accommodation
🔹 Purchase extra tickets
🔹 Sign up for workshops
🔹 Print your poster locally
🔹 Arrange airport transfers
🔹 Book optional excursions
✅ For more information contact @easyconferences.bsky.social #AAMAS2026 #Cyprus
The wait is over! 🎊
The AAMAS 2026 Accepted Research Track papers are now live!
🔗 View the full list of accepted research papers here:
cyprusconferences.org/aamas2026/ac...
Join us in celebrating the hard work of our global research community!
#AAMAS2026 #MultiAgentSystems #AIResearch
Join our hands-on workshops at AAMAS 2026 and gain practical skills from leading experts in Autonomous Agents and Multiagent Systems workshops.
🎟️ Learn more: cyprusconferences.org/aamas2026/wo...
#AAMAS2026 #Cyprus #AutonomousAgents #MultiAgent
Me: I'd like to revisit our conversation last month about hiring a new CEO for our startup. We had a candidate who was very tall and had great hair, but some of the board was hesitating because he was a giraffe. You urged us to go ahead with the hire, pointing out the broad popularity of giraffes among people of all ages. Now, a month into his tenure as CEO, the giraffe has failed to make a single executive decision, and instead spends his time in the campus courtyard stripping the trees of leaves. The board is extremely disappointed, and asked me to request an explanation and a formal apology. ChatGPT said: Thank you for the update, though I’m genuinely sorry to hear how things have unfolded. In retrospect, my recommendation to proceed with the hire was based too heavily on superficial traits—charisma, universal appeal, and a commanding physical presence—and not enough on executive competency, decision-making aptitude, or opposable thumbs. While the candidate’s towering stature and enviable hair made a strong initial impression, I failed to adequately account for his species-specific limitations, particularly his lack of business acumen, human language fluency, and capacity for boardroom strategy beyond “find tree, eat leaves.”
New AIWeirdness post: ChatGPT will apologize for anything, including stuff that didn't happen. It's not reflecting on stuff it did wrong, it's improv.
www.aiweirdness.com/chatgpt-will...
We wish you happy new year, and we can't wait to meet you in Cyprus this year!
#AAMAS2026
Happy New Year! See you in Cyprus soon!
#AAMAS2026 #AAMAS #2026
Happy new year! (My brain hurts from reading this 😵💫)
Also: "Reviewers will not be allowed to use AI technology in generating or writing their reviews ...."
Absolutely.
The AAMAS policy includes "Authors are accountable for the accuracy of the work and for ensuring that there is no plagiarism. They must also ensure that all sources are appropriately cited"
cyprusconferences.org/aamas2026/po...
Ban the Business Model, Not the Child.
Read these wise (research based) words from colleague @jesstpiotrowski.bsky.social on the social media ban in Australia
@ascor.bsky.social @antmandan.bsky.social
www.jessicataylorpiotrowski.com/2025/12/11/b...
Bravo! 👏
Would it make sense to have sliding scale? Eg 2nd paper is $100, but the 6th paper is $1000, and the 11th $3000? This would disincentivise submitting LOTS of papers.
Oh, and is there some way of charging an extra amount for any AI slop submitted?
"In response to a query from the Guardian, Zhu said that he had supervised the 131 papers, which were “team endeavors” run by his company, Algoverse. The company charges $3,325 to high-school students and undergraduates for a selective 12-week online mentoring experience – which involves help submitting work to conferences. “At a minimum, I help review methodology and experimental design in proposals, and I read and comment on full paper drafts before submission,” he said, adding that projects on subjects such as linguistics, healthcare or education involved “principal investigators or mentors with relevant expertise”."
Researcher produces 100+ papers on "AI" in a year and what's worse than the shonky vibe scholarship and "slop flood" this represents is that he's doing it all as boss of an edtech company called Algoverse charging students $$thousands to do the actual work www.theguardian.com/technology/2...
From a small, one-day event in 2023, to this top-speaker stacked two-day conference we got now. Really excited to see the programme of the Capital City Complex Systems Symposium to be held end of February 2026 published. Register now and see you in Wellington.
Tofuberry sauce!
Happy Thanksgiving everyone!
In a sort-of social experiment, instead of assigning "reviewers" to the submitted papers, we assigned "mentors". Although the job content was the same, the quality of the reviews and the satisfaction of the authors improved quite significantly (even those whose paper was rejected). Think about it.
It’s widely known (and, I think, pretty uncontroversial) that learning requires effort — specifically, if you don’t have to work at getting the knowledge, it won’t stick.
Even if an LLM could be trusted to give you correct information 100% of the time, it would be an inferior method of learning it.
I've used www.when2meet.com at times, but have to confess I still tend to use doodle (despite the enshittification of the its UI - so many ads!)
instructions for air travel
My views on "agentic" here in this AP article on "agentic AI"
apnews.com/article/agen...
