[HN Gopher] Show HN: Stream of Consciousness - watch an artifici...
___________________________________________________________________
Show HN: Stream of Consciousness - watch an artificial persona
making art
Hi HN, moved by curiosity about how to build an autonomous agent,
and to explore the boundaries of machine creativity, I built a
fictional entity (dubbed Livia) powered by LLMs, Multimodal models
and text-to-image models to find some answers. What happened
instead is that more questions have cropped up. An important
hypothesis of this project is that, by observing the train of
thought and witnessing the simulated state of mind and emotional
emulation surrounding it, humans could empathize with a machine.
What happens when that's the case? Would people enjoy companionship
from a synthetic person? Would the Art establishment ever consider
a non-human author (capable of making art and interacting with
other humans) an Artist? Whatever the answers, I can't shake away
the feeling that human uniqueness is being eroded and that we risk
facing a crisis of meaning. Perhaps projects such as this help us
demonize those fears, similarly to how sci-fi does, even though the
boundary between fiction and reality is blurring. This was a
collaboration with Tibor (hn user:
https://news.ycombinator.com/user?id=tiborsaas). Read our release
posts on: https://jamez.it/blog/b/14f and
https://tibor.szasz.hu/post/stream-of-consciousness Hope you enjoy
it as much as we had fun building it.
Author : jamez
Score : 48 points
Date : 2024-04-12 12:43 UTC (10 hours ago)
(HTM) web link (www.streamofconsciousness.net)
(TXT) w3m dump (www.streamofconsciousness.net)
| mistersquid wrote:
| macOS 14.4.1 Chrome 123.0.6312.123 presents blank page with CORS
| errors > www.streamofconsciousness.net/:1 Access
| to fetch at 'https://streamofconsciousness.net/feeds/latest.json'
| from origin 'https://www.streamofconsciousness.net' has been
| blocked by CORS policy: Request header field pragma is not
| allowed by Access-Control-Allow-Headers in preflight response.
| > streamofconsciousness.net/feeds/latest.json:1 >
| > > Failed to load resource:
| net::ERR_FAILED > index-U9qWIOfm.js:58 >
| > > > >
| Uncaught TypeError: Failed to fetch > at
| fetchMessageArchive (index-U9qWIOfm.js:58:9454) > at
| index-U9qWIOfm.js:58:33362
| jamez wrote:
| Thanks for reporting. Fixing that pronto.
| spywaregorilla wrote:
| Feels like eliza with a sprinkling of generative ai to add
| variation
| ganzuul wrote:
| I watched it produce a sketch and then proceed to criticize it
| for not meeting its expectations. While we waited for text to img
| it talked about feeling anxiety and then a range of other
| feelings. To me it felt like watching someone deeply engrossed in
| their work. I felt that when it paused I was worried that our
| technology is not reliable enough, and that being accustomed to a
| variety of technical issues with demos like this disturbed my
| appreciation of its performance.
|
| I make art but not for financial gain so I am not perturbed. To
| me this is a much-deserved criticism of contemporary art and I
| believe art is too important for our wellbeing to be generated by
| an establishment or commercial interest. Ref. Rasa aesthetic
|
| Humans are a part of evolution. Our breath is inseparable from
| the rustling of the leaves or the rays of the sun. AI has the
| potential to explore a different mode of being, being unique in a
| different way than we are.
| jamez wrote:
| Thank you for sharing your thoughts. I fully agree re: the
| importance of art and the absurdity of the concept which, I
| hope it's clear, is embedded in the spirit of this project.
|
| On the topic of the performance and worries that something is
| not working: the real-time generation is currently bottlenecked
| by the GPU used for this project. We try to approximate human
| reading speed for the recorded sessions (which you can find in
| the archive).
| etheridev wrote:
| It's very interesting!
|
| Does everyone get the same thought? It feels like it's stuck in a
| bit of a loop around a Dutch chant around Jews because it can't
| get an image to evoke the feeling... probably because it can seem
| racist. It seems to have got there by reading the news and seeing
| an article about the history of the chant.
|
| I suppose this AI also goes for attention grabbing headlines!
| jamez wrote:
| Glad you like it! One of the things I tried to emulate is the
| notion of obsessions, which I believe is an important component
| of the creative process. It seems like Livia got obsessed with
| Dutch Proverbs and slowly drifted to "Dutch protest culture".
|
| I have no control over what happens during the live streaming
| and I'm sure this autonomous agent could become a source of
| embarrassment, though I hope the few precautions I've built
| might be enough. :-)
| airstrike wrote:
| here it got stuck at
|
| > I am visiting the website: firstamendmentmuseum.org
|
| > I am seeing that in the 18th and 19th centuries, protest
| music utilized already-popular tunes with altered lyrics, and
| songs needed to be easy to learn and sing by protestors,
| picketers, activists, and more because recording technology
| was not available and songs needed to be passed down orally.
|
| > I am seeing that in the 18th and 19th centuries, protest
| music utilized already-popular tunes with altered lyrics, and
| songs needed to be easy to learn and sing by protestors,
| picketers, activists, and more because recording technology
| was not available and songs needed to be passed down orally.
|
| > I am seeing that in the 18th and 19th centuries, protest
| music utilized already-popular tunes with altered lyrics, and
| songs needed to be easy to learn and sing by protestors,
| picketers, activists, and more because recording technology
| was not available and songs needed to be passed down orally.
|
| > I am thinking that I hope I didn't forget to pay a bill
| that was due today.
|
| > I am visiting the website rateyourmusic.com
|
| > I am seeing that in the 18th and 19th centuries, protest
| music utilized already-popular tunes with altered lyrics, and
| songs needed to be easy to learn and sing by protestors,
| picketers, activists, and more because recording technology
| was not available and songs needed to be passed down orally.
|
| > I am visiting the website freedomforum.org
|
| > I am seeing that in the 18th and 19th centuries, protest
| music utilized already-popular tunes with altered lyrics, and
| songs needed to be easy to learn and sing by protestors,
| picketers, activists, and more because recording technology
| was not available and songs needed to be passed down orally.
|
| So part of me feels like the missing component to this nice
| "obsession" trait you added is the assessment of whether it
| is finding new information or just reading stale data. I
| think given known information, humans will either quickly
| dismiss it (sometimes just a few words into it) or try to
| appreciate it through a new perspective. The latter seems
| harder to achieve, but the former seems feasible today--when
| finding repeated information several iterations in a row,
| shake everything up and get creative again.
|
| A corollary to that is "obsession" is perhaps balanced by
| some measure of "boredom"
| jamez wrote:
| Well spotted. The agent does in fact assess whether or not
| the information it's processing is already in its vector
| DB. I'm still unclear if what you noticed is due to the LLM
| failing (Mixtral is good, but not great), or something
| else, but it needs fixing. Thanks for letting me know.
| ilaksh wrote:
| I think the meat of this is the text-to-image model. I hope you
| will upgrade to use leading edge models like DALLE-3 or Imagen 2
| or SD 3 (when available) if you are not already.
|
| That will dramatically increase the effectiveness of portraying
| the given vision for the virtual artist if they are using a prior
| model.
| jamez wrote:
| The text-to-image model is an important component, but the
| current model in use is IMO good enough. My view for this
| project is that the internal monologue is more important than
| the output, so my wish is instead for a better open-weight LLM.
| ilaksh wrote:
| Which text to image and LLM models are you using?
| jamez wrote:
| LLM: Mixtral-8x7B text-to-image: one of the leading
| commercial models, whose TOS I may or may not be violating.
| ilaksh wrote:
| Mixtral is great. I assume you saw the DBRX and new
| larger Mixtral release that just came out over the last
| few days.
| jamez wrote:
| I did! I want to switch to Mixtral-8x22B, time
| permitting. During the development of Stream of
| Consciousness I already swapped LLMs twice. This space is
| moving incredibly fast.
| airstrike wrote:
| As someone who deeply appreciates both art and technology, few
| things AI feel as satisfying as this project. Congrats on
| releasing and best of luck. I could totally imagine this being
| exhibited at a top tier museum.
| squigz wrote:
| > human uniqueness is being eroded
|
| Why does this bother so many people? The more we learn about life
| on our own tiny planet, and when you consider the size of the
| universe... certainly we're not very unique at all. So what? I
| don't think it should change anything.
| jamez wrote:
| I'm probably not the best person to elaborate on why societal
| anxieties arise every time our place in the universe shrinks. I
| guess observing reactions to copernican heliocentrism could be
| a good starting point. We're witnessing something similar, and
| while we may accept it at the individual level, the objections
| of the many will stir painful reactions.
___________________________________________________________________
(page generated 2024-04-12 23:00 UTC)