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…
In plain words
Stream of Consciousness is a project that displays an autonomous AI persona named Livia creating art in real time. Built using large language models, multimodal models, and text-to-image generation, it visualizes the entity's thought process and simulated emotional states as it produces artwork. The project is designed for those curious about autonomous agents and machine creativity, inviting viewers to observe and potentially empathize with synthetic decision-making. It raises questions about artificial consciousness, human-machine companionship, and whether non-human creators deserve recognition as artists.
written from the facts on this page · September 2026
From the sources
In the maker’s words, at launch
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.
Does the same job
all alternatives →- ASA stream of AI-generated art2020 · art42.net · ▲277
- IBI built an AI art installation at home generating new pieces on the fly2021 · github.com · ▲399
This Person Does Not Exist2019 · thispersondoesnotexist.com · ▲750Computer generated people - refresh to get a new one
- TAThis AI Does Not Exist2022 · thisaidoesnotexist.com · ▲434
Hey HN! Author of the site here. I tried a few tricks to keep the text-generation part of the site up, but even leaning hard on Huggingface's API and bumping time-outs up, it looks like the site is struggling a bit. I'm going to see if there's anything I can do to keep the text-generation part available, but in the meantime, the pre-generated set should stay pretty stable. Not sure if there's much else I can do without burning a hole in my cloud bills — sorry for the troubles! I've put up a more detailed description of how this works on the GitHub -…
Turn articles into videos with humans2022 · ▲220Generate narrated AI videos just from the link to an article
More ai this month
the category →
I trained a 125M-parameter transformer to autocomplete piano performances in real time (~108 notes/sec on an iPhone 15). The idea is basically GitHub Copilot or Tabnine, except instead of prompting it with code, you prompt it by playing a few notes on a MIDI piano. The model then continues what you played, entirely on-device. The app is free if anyone wants to try it. Happy to answer questions about the model, training, Core ML, or the many things that didn't work.
AI · 17d ago · simedw.com
Astute▲585Automate your B2B brand going viral, with new media creators
AI · 18d ago · company-app.joinastute.com
Hey HN, Henry from Cactus here! We previously released Cactus Needle, a 14MB agentic LLM for tool call, device use, and structured extraction for phones, wearables, smart homes, small robots and microcontrollers. We got really great feedback here, and have now incorporated the suggestions to release Needle 2. The whole model is a single 14MB binary that runs a full session in 28MB of RAM; 45m parameters at 2bit compression. Needle hits 500 tokens/sec decode speed on a Raspberry Pi 5, sits between 400-1,500 tokens/sec on VR devices like Meta Quest 3S and Apple Vision Pro, and ranges…
AI · 27d ago · cactuscompute.com
Launched alongside, April 2024
the whole month →
Supabase▲2,328The Postgres developer platform is now generally available
Dev tools · 2024 · supabase.com
Cal.com Platform▲1,602Build your pixel-perfect booking experience with Atoms
Dev tools · 2024 · cal.com
deco.cx 2.0▲1,080Build web apps 10x faster with Deno, JSX, TS & Tailwind
Dev tools · 2024 · decocms.com
