Just to be clear im talking about chatbots. When they started I saw them as just the next abstraction of search. In the workplace I saw them do things that while nice really did not do more than specific programs or add ons did already. I also had concerns on the energy usage. Then I saw them get image generation and vidoe generation and of course what we have seen made since.

Now I have been using them more and part of that is I have come to terms somewhat with the energy usage. Curiously I find they can actually save energy in certain scenarios. Like if you entertain yourself with one over streaming video (even stadard def) or for that matter learned something using a youtube video. Even as search while it uses something like 5 to 10 times the energy it provides information equivalent to several searches. I would say at least 3 in my cases and often more. So I am leaning to in most cases it is worth using with the caveat of like using the web you have to evaluate what you get back. Its kinda funny because one reason for my long skepticism is any defending I got back on its energy uses with (presumably) people sounded very much like the answer an ai would give if you asked it about it. Much like most ai info it takes some refinement to get to the point where I feel the answer is sound. A note of caution in that if the ai is remember things it will use more energy over time as it keeps track of the conversation. I have seen various things indicating they are working on improving the memory mangement with patterns and tags and colder storage. Anyway it will be good both for the environment and privacy to start new chats and not have it save stuff. I am encouraged that the companies are working both the hardware and software angles with dedication ai chips along with mini models and specialized models.

Ok so long term there has always been the argument that its going to get better and better and build on itself till (sometimes) implied agi is achieved. I do not know about that but I will say I continue to see improvements. besides the image and video generation I mentioned I am finding the chatbots are getting more nuanced in answering and can respond to requests for more nuance better. I see less yes manning. I think it still biases yes but only when there is a tie. I generally see it defend its answer when it has solid data but at the same time accept correction readily. I find it can now play games which honestly was one of the earlier things I asked them to do when testing them out. I don’t think any of these are necesarilly driving it toward agi but I definatley thinks this shows it has a lot of places it can dip its tendrils into.

My honest opinion is I have softened to it since it started and if it were not for corpo enshitification type things driving me further from technology. I think I would kind of like it. Like smartphones and this in a utopian world of privacy and no bias where you could trust the systems. Would be pretty awesome