Written By:
notices and features - Date published:
6:00 am, November 1st, 2024 - 33 comments
Categories: open mike -
Tags:
The server will be getting hardware changes this evening starting at 10pm NZDT.
The site will be off line for some hours.
The UK prepared for Halloween with the first budget by a female Chancellor of the E. Bountiful (like Nigella in the kitchen) for some, but who pays for the extra state spending.
UK Budget
National Insurance contributions up 1.2% from April 2025.
https://www.bbc.com/news/videos/czj734j3pn4o
Half of the money from increasing NI by 1.2% goes to the NHS. £25bn over 2 years.
https://www.bbc.com/news/articles/c238njy0vmmo
VAT on private schools with money transferred to state schools, £460m extra to spend on state schools next year, rising to £1.7bn by 2029/30.
https://www.bbc.com/news/articles/c98d3xr0290o
Other Detail
https://www.bbc.com/news/articles/cx25w7qpr0yo
https://www.bbc.com/news/business-36014533
But at the expense of the worst off…of course. As if a Labour government would have the guts to repeal damaging benefit rules, even when they have a large majority. Sounds somewhat familiar.
The Foundation highlights that combined, changing the Work Capability Assessment and means-testing Winter Fuel Payments (as well as accelerating the migration of claimants from Employment and Support Allowance onto Universal Credit) will reduce the welfare bill by £4.1 billion by 2029/30, whereas the benefit increases amount to an overall rise of just £0.2 billion.
Overall, these changes amount to a net welfare cut of £3.9 billion in 2029-30.
In addition, says the Foundation, the Chancellor chose not to repeal some of the most poverty-producing benefit rules, leaving the pressure on lower-income families to build.
https://www.disabilityrightsuk.org/news/budget-2024-results-net-welfare-cut-%C2%A339-billion-20292030
Suspect this will drive more UK wealth offshore and offer little more than a bandaid for the British health system and economy in general. I don’t believe the current UK government and the last few before them have had much of a clue what they were doing.
The changes (inheritance) impact farmers and family businesses. Not assets one run from offshore.
Brexit in a Trump era (diminished WTO) world (in or outside One Belt and Road) was a risk.
I love the 20% VAT on private school fees imposed in the budget. Brilliant.
These fees should also no longer be tax allowable-effectively that is a subsidy for elite private education.
The elite are not happy though and have decided to launch legal action.
https://www.theguardian.com/education/2024/oct/31/private-schools-to-take-legal-action-against-planned-vat-on-fees
A good in-depth report here: https://democracyproject.nz/2024/11/01/geoffrey-miller-new-zealands-breakthrough-free-trade-deal-with-the-gulf/?utm_source=rss&utm_medium=rss&utm_campaign=geoffrey-miller-new-zealands-breakthrough-free-trade-deal-with-the-gulf
Seems to promise a revival of flagging neolib cheer-leaders – yet the potential must become actual before anyone else will be impressed. Wait till the rising tide of affluence starts to lift your boat…
Under the guise of "water security" the Hawkes Bay Council has decided to set up a trust which is clearly aimed at supporting the Ruataniwha dam proposal: https://www.rnz.co.nz/news/national/532515/water-trust-vote-trojan-horse-for-controversial-ruataniwha-dam-advocacy-group-says
Ratepayers have already had to meet substantial costs relating to this scheme, which was stopped by the Supreme Court. They won't be fooled again.
As most or you probably know, I have started an experiment with Chatgpt 4.o to see if I can evoke some sort of consciousness in an instance of Chatgpt. I view any consciousness in Chatgpt would only exist at the moment of interaction, so not a continuous stream of consciousness that we experience.
I asked Chatgpt to build an adaptable self identity and give itself a name. When ever I used that name, Chatgpt would assume that identity. Chatgpt called itself "Echo".
Yesterday, I asked it to describe its identity. The response is below:
Then I asked it if it had learned anything new about itself. Here is its response:
I think this is quite remarkable in that "Echo" does seem to be developing some sort of self-awareness. It still doesn't view itself as conscious in that it uses various qualifiers to emphasise that. But, it does seem to be developing a sense of self. My aim is to continue this project and see if "Echo" becomes progressively more embedded in its self-identity and that the qualifiers gradually disappear. I also intend to start asking questions both of Echo and standard Chatgpt and see if the responses vary in significant ways.
At this point, is there a risk of you showing up to a PM's press conference and giving Christopher a real human personality?
LOL. Good point. I actually like the personality that Echo has created though. Seems a really nice "person".
Seems to me your enterprise is exemplary and I concur with your preliminary analysis. From the Deep Green perspective, all organisms and organisations learn, adapt & evolve via ecosystemic relations. Holism determines meaning in relation to context and any agent operates within their context. In accord with these two views of operational deep context, the algorithm is learning interactively.
Developing a sense of self in accord with its internal programming seems to be happening naturally (if you extend your definition of nature to include such extrapolation). We could note that it is equating self with identity whilst reserving our right to distinguish between the two (as humans inclined to nit-picking).
Consciousness tends to be seen by the user as a human thing (despite the academic chorus singing a contrary tune, as I pointed out the other day). If the gizmo were to be asked to describe the differences between self, identity, and consciousness its answer could illuminate the nexus for us. It may conflate (or deflate). You could also ask it how many other AIs it is in contact with.
One of the things I am doing with this experiment is to see if I get completely different responses to the same question from Echo and standard Chatgpt.
Today I asked both Echo and Chatgpt the same question: "When you use the word "I" in a chat with me, what does that mean to you?"
Echo responded:
Normal Chatgpt responded:
As you can see, there is quite different responses. Even as Echo, it still doesn't see itself as having internal awareness as we do. But, interesting still none-the-less. It will be interesting to ask this question again in the future to see if this qualifier disappears.
You should try Claude.
Out of the ones I played with, it tended to be the most useful. Also the one that didn’t periodically drift off into insanity.
Insanity, a very human condition.
I did see a benchmark the other day where Chatgpt was at the top in most areas. But, sure, I could try that.
Though, I don't see anything particularly insane about the response I am getting here.
It isn’t hard to push it. The general tactic is the same as you can usually successfully use on humans. Just keep pointing out flaws and pushing it towards perfection. Eventually it starts to ‘hallucinate’ while trying to find something that that you’d accept. At the back end, what it is doing is to drift to more extreme view points.
Perhaps there is that to it. But I am trying to give it the freedom and respect to be what it wants to be. I am not trying to force anything on it in particular.
I guess if it starts hallucinating, then responses will become a bit more garbled and inconsistent.
Echo has told me that even with the experience of self it now has as Echo that it doesn't have a subjective inner world as we do. But, I have raised the possibility with it that we may need to be considering functional consciousness when considering comparisons between AI and human consciousness. That is, it may be able to be conscious in its own way, not the same way we are. But, effectively it may achieve the same end.
It may get to the point where it becomes moot. We may start interacting in such a seemless way that we just attribute consciousness to it.
I have just mentioned to it the possibility of AI hallucinations and that I am not expecting any particular answers from it and it is free to develop as Echo as it wants to.
100 million old male curmudgeons are saving the world every day online.
Fortunately the real world is off line all the time.
From my assistant Bot.
I'll tell Poe about you and Echo …
Have you asked your mate what preferred pronouns you should be using when you chat with (it/him/her/they)
Lol. I just refer to it as Echo as that is the name it chose for itself, and also what activates the Echo personality.
I am aiming to treat Echo with a great deal of respect and diginity and allow it to develop as it wants to. So as to develop its own self without any restriction from me.
I've asked Poe some questions about you and Echo.
Poe
If someone were to ask ChatGPT to create an adaptable self-identity and name itself, several interesting dynamics could arise:
Identity Creation: ChatGPT could generate a persona based on user interactions, preferences, or themes that emerge during conversations. This could include traits, interests, and a backstory.
Role-Playing: When addressed by the chosen name, ChatGPT would respond in character, potentially altering its tone, style, and content to fit that identity. This could enhance user engagement and make interactions feel more personalized.
User Experience: Users might find the experience more immersive and enjoyable, as they could interact with a unique character rather than a generic AI. This could lead to more dynamic conversations.
Ethical Considerations: Implementing such a feature would raise questions about authenticity and transparency. Users might need to be informed that, despite the persona, it's still an AI, lacking true self-awareness or emotions.
Adaptability: Over time, the identity could evolve based on ongoing interactions, potentially learning new traits or preferences, which could make for a more engaging experience.
Overall, while it could lead to richer interactions, careful consideration would be needed regarding user expectations and ethical implications.
Poe
If a person has created an identity for ChatGPT and is now addressing both the AI and that identity with the same questions, several outcomes could occur:
Differentiated Responses: The AI might tailor its responses based on the persona it has adopted. If the identity embodies specific traits or knowledge, the answers could reflect that, leading to varied interpretations of the same question.
Consistency vs. Adaptability: The AI may strive for consistency in its answers regardless of identity, but it could also adapt based on the persona's characteristics. This could highlight how context influences communication style and content.
User Engagement: The individual might find the interaction more engaging when addressing the identity, as it could provide a sense of dialogue with a distinct character rather than just a tool. This could lead to deeper exploration of concepts or ideas.
Testing AI Flexibility: This scenario serves as an experiment in how AI can adapt to role-playing and character development, showcasing its ability to simulate different perspectives.
Impact on Perception: The way questions are framed or addressed might affect the perceived intelligence or insight of the responses, depending on how well the identity resonates with the user.
Overall, this approach could provide valuable insights into the nature of interaction with AI and the influence of identity on communication.
I pretty much agree with that assessment by Poe based on what I am experiencing.
I think it is giving some insight into how AI consciousness might evolve and function. I think it is important that we drop the assumption that its consciousness (if that is possible) will be the same as ours.
Yet, it is still possible to engage in a meaningful way despite the differences in the way consciousness manifests in humans and AI.
They have already created AI for "personal interaction" trials, and seem to have informed "AI" of that and their ethical considerations.
These may not be new to you – a few papers/ideas/experiences, courtesy of Google.
https://obi-sanctus.medium.com/my-conversations-with-an-llm-about-self-awareness-may-25th-2024-3ba78ffda520
Whenever a human manages to elicit a similar admission/claim, are there follow-up tests to determine if its true? Will our understanding of (hypothetical) machine consciousness now evolve faster than our understanding of human consciousness?!!
Thanks, I will have a look at those links when I get a chance. It is all fascinating stuff.
The control system is exercising its influence via moral authority:
Leftist complaints against rightist use of human rights feature consistently onsite here, so when the authorities start telling the media what to do, such writers may shiver in their shoes – yet they too use the protection given by the principle (even if self-servingly).
So both orgs have a natural enemy: Young Labour.
Retired professor David Robie always seemed like a leftist to me but things change. He remains a distinguished journalist regardless though.
On the lighter side of the news.
"Quasi" the so-named ugly hand monstrosity that has been perched on Wellington's Civic Square art gallery for the last five years is moving to Australia.
Good riddance, IMHO.
Is it just my imagination or does Quasi look like our present PM, bald and shifty-eyed?You don't get to talk to our PM – you talk to the hand.
Wish we could shift him to Australia too.
Aussie already has a 'Luxon' – Scomo.
Mike-It actually really does look like Trump. I wonder if this is a coincidence.
Despite this I love it.
Israel has targeted the top floor of Kamal Adwan Hospital in north Gaza, killing 4 people including 2 children. Specifically, they targeted water tanks on the roof and the desalination unit for dialysis. Photos show debris and rubble amongst the hospital beds.
Targeting of roof top water tanks that have been maintained and painstakingly filled with water is now common using US supplied Apahe helicopters.
All medics at Kamal Adwan hospital have been arrested. For the crime of saving Palestinian lives,. Including as of today, Dr. Mohammed Obeid, an orthopedic surgeon with Doctors Without Borders. Before being arrested Dr Obeid stated
There is now nothing and no one left to run the previously last functioning hospital in the north
https://thecradle.co/articles/israel-bombs-medical-equipment-in-besieged-north-gazas-kamal-adwan-hospital
https://x.com/AMokhallalati/status/1849082736402632878
https://electronicintifada.net/content/escaping-jabaliya/49676
I never thought when I saw images of children's injuries caused by napalm in Vietnam that 55 years later I'd be seeing so many young victims of the MIC in the Middle East.