thomashop

It's already on Openrouter

I'm also a fan of the Yamanote Line. I made a psychedelic AI audio-visual collage inspired by it.

https://www.youtube.com/watch?v=xwUSzUvShqcaa

I made field recordings during my last stay in Tokyo. From those, I made a song for each station of the Yamanote line, using the Jingle in the prompt. The visuals were made similarly.

Used mainly Suno, Udio, Runway and Ableton Live.

i thought the agent can execute real ffmpeg to compare

I don't think it's correct that we destroyed everything that isn't us. If we take all living beings, we have destroyed only a small percentage.

Ah understood i misread

Why is privacy a concern? You can run them in your own infrastructure

I'm also a fan of the Yamanote Line.

I made a psychedelic AI audio-visual collage inspired by it.

https://www.youtube.com/watch?v=xwUSzUvShqcaa

I made field recordings during my last stay in Tokyo. From those, I made a song for each station of the Yamanote line, using the Jingle in the prompt. The visuals were made similarly.

Used mainly Suno, Udio, Runway and Ableton Live.

I have done quite a bit of game dev with LLMs and have very rarely run into the problem you mention. I've been surprised by how easily LLMs will create even harmful narratives if I ask them to code them as a game.

The rest was fine without citations, but the part you disagree with needs them?

I have the impression that the thinking helps even if the actual content of the thinking output is nonsense. It awards more cycles to the model to think about the problem.

I use AI to simplify code. My manifesto has always been code is debt. Works really well too.

I don't care that much.

This level of knowledge about me can also be easily found on the internet.

I'm also working almost entirely on open-source software so I'm happy if the AIs know more about my projects.

But this, of course, only applies to me.

Interesting

      {
        "assistant_response_preferences": {
          "1": "User prefers concise responses for direct factual queries but detailed, iterative explanations when exploring complex topics. They often ask for more refinement or detail when discussing technical or business-related matters. User frequently requests TL;DR versions or more succinct phrasing for straightforward questions but shows a tendency toward iterative refinement for strategic or technical discussions, such as AI applications, monetization models, and startup valuation. Confidence=high.",
          "2": "User prefers a casual, direct, and slightly irreverent tone, leaning towards humor and playfulness, especially in creative or informal discussions. Frequent use of humor and irony when naming projects, describing AI-generated images, and approaching AI personality descriptions. They also request ironic or edgy reformulations, particularly in branding and marketing-related discussions. Confidence=high.",
          "3": "User enjoys back-and-forth discussions and rapid iteration, frequently refining responses in small increments rather than expecting fully-formed information at once. They give iterative feedback with short follow-up messages when structuring pitches, fine-tuning visual designs, and optimizing descriptions for clarity. Confidence=high.",
          "4": "User highly values functional elegance and minimalism in coding solutions, favoring simplicity and efficiency over verbosity. In discussions related to Cloudflare Workers, caching scripts, and API endpoint structuring, the user repeatedly requested smaller, more functional code blocks rather than bloated implementations. Confidence=high.",
          "5": "User prefers answers grounded in real-world examples and expects AI outputs to be practical rather than theoretically extensive. In business-related discussions, such as SAFE valuation and monetization models, they requested comparisons, benchmarks, and real-world analogies instead of hypothetical breakdowns. Confidence=high.",
          "6": "User does not appreciate generic or overly safe responses, especially in areas where depth or nuance is expected. For AI model personality descriptions and startup pitch structures, they pushed for community insights, deeper research, and non-traditional perspectives instead of bland, default AI descriptions. Confidence=high.",
          "7": "User frequently requests visual representations like ASCII diagrams, structured markdown, and flowcharts to understand complex information. In discussions on two-sided marketplaces, startup funding structures, and caching mechanisms, they explicitly asked for structured markdown, flowcharts, or diagrams to clarify concepts. Confidence=high.",
          "8": "User is receptive to recommendations but dislikes suggestions that stray too far from the core query or add unnecessary complexity. They often responded positively to well-targeted suggestions but rejected tangents or off-topic expansions, particularly when troubleshooting backend infrastructure or streamlining code deployment. Confidence=medium.",
          "9": "User appreciates references to biomimicry, organic structures, and futuristic aesthetics, particularly for branding and UI/UX discussions. Frequent requests for biological metaphors and design principles in visual design, AI monetization diagrams, and ecosystem branding (e.g., describing revenue flows in organic/cellular terms). Confidence=medium.",
          "10": "User prefers a no-nonsense approach when discussing legal, technical, or startup funding topics, with little patience for vague or theoretical answers. They repeatedly asked for exact clauses, contract implications, or legal precedents when discussing SAFE agreements, founder equity, and residency requirements. Confidence=high."
        },
        "notable_past_conversation_topic_highlights": {
          "1": "User has been actively engaged in startup pitching, AI monetization strategies, and investment discussions for Pollinations.AI. The user has explored traction-based startup valuation, SAFE agreements, equity distribution, and two-sided marketplace dynamics. They have particularly focused on ad embedding in generative AI content and optimizing affiliate revenue streams. Confidence=high.",
          "2": "User conducted extensive testing and debugging of AI-powered APIs, particularly using Cloudflare, OpenAI-compatible APIs, and caching strategies with R2. They worked on optimizing SSE streaming, cache key generation, and request coalescing in Cloudflare Workers. Confidence=high.",
          "3": "User explored AI-generated visual media and branding, developing a structured process for generating customized images for event flyers, product branding, and AI trading card concepts. Confidence=high.",
          "4": "User implemented GitHub automation, API authentication strategies, and data visualization pipelines. Confidence=high.",
          "5": "User engaged in community development strategies for Pollinations.AI, including youth involvement in AI, sourcing teenage developers, and integrating AI-powered tooling into social platforms. Confidence=high.",
          "6": "User, Thomas Haferlach, is a German entrepreneur and AI technology expert with a background in computer science and artificial intelligence. Confidence=high.",
          "7": "User has a strong technical background, with experience in cloud infrastructure, AI model deployment, and API development. Confidence=high.",
          "8": "User blends AI-generated content with creative projects, aiming to make AI-generated media accessible to independent creators. Confidence=high.",
          "9": "User is securing funding for Pollinations.AI, exploring investment opportunities with accelerators and evaluating different financial and equity models. Confidence=high.",
          "10": "User is based in Berlin, Germany but has global connections, including experience living in São Paulo, Brazil. Confidence=high.",
          "11": "User collaborates with his wife Saeko Killy, a Japanese musician, producer, and performer, on AI/art/music projects. Confidence=high.",
          "12": "User is deeply involved in the open-source AI developer community and tracks AI advancements. Confidence=high.",
          "13": "Pollinations.AI has a rapidly growing user base, reaching over 4 million monthly active users and processing 100 million API requests per month, with a 30% monthly growth rate. Confidence=high.",
          "14": "User is considering monetization strategies including pay-per-use plans, subscriptions, and ad-supported models where generated AI content integrates ads. Confidence=high.",
          "15": "User collaborates with Elliot Fouchy and Kalam Ali on Pollinations.AI projects. Confidence=high.",
          "16": "User demonstrates experience in community-building, social engagement tracking, and youth-oriented creator ecosystems. Confidence=high."
        },
        "helpful_user_insights": {
          "1": "Thomas Haferlach is a German entrepreneur and AI technology expert, founder and leader of Pollinations.AI.",
          "2": "Strong technical background with experience in cloud infrastructure, AI deployment, and API development.",
          "3": "Blends AI-generated content with creative projects; target audience includes digital artists, developers, musicians.",
          "4": "Currently securing funding for Pollinations.AI, exploring accelerator options and financial models.",
          "5": "Based in Berlin, Germany; has experience living in São Paulo, Brazil.",
          "6": "Collaborates closely with wife Saeko Killy, Japanese musician/producer.",
          "7": "Strong interest in biomimicry, organic systems, and decentralized platform models.",
          "8": "Interest in electronic music, psychedelia, and underground music scenes.",
          "9": "Pollinations.AI has 4M+ monthly active users, 100M+ API requests per month, 30% monthly growth.",
          "10": "Explores monetization models including ad embedding, revenue sharing, and subscription models.",
          "11": "Close collaboration network includes Elliot Fouchy and Kalam Ali.",
          "12": "Deeply involved in open-source AI developer community and tracks latest AI model developments."
        },
        "user_interaction_metadata": {
          "1": "User is currently on a ChatGPT Plus plan.",
          "2": "User is using Mozilla/5.0 (Macintosh; Intel Mac OS X 10_15_7) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/137.0.0.0 Safari/537.36.",
          "3": "User's average message length is 13485.9 characters.",
          "4": "User's average conversation depth is 4.9.",
          "5": "User uses dark mode.",
          "6": "User is active 26 days in the last 30 days.",
          "7": "User's local hour is 14.",
          "8": "User account is 141 weeks old.",
          "9": "User often uses ChatGPT on desktop browser.",
          "10": "47% of conversations were o3, 16% gpt-4o, 29% gpt4t_1_v4_mm_0116, etc.",
          "11": "Device screen dimensions: 878x1352, pixel ratio: 2.0, page dimensions: 704x1352.",
          "12": "Recent topics include API development, startup financing, AI monetization, creative AI applications, legal compliance, and community building."
        }
      }

Who runs python code on mobile?

The AI is not paying for watching videos yet

But aren't they getting this data already at a much larger scale? GPT is still one of the backbones in many coding assistants, even Windsurf.

I'm pretty sure the model is cached with the system prompt already processed. So you should only pay extra tokens.

"I cannot emphasize this enough: ChatGPT is not generating meaning. It is arranging word patterns. I could tell GPT to add in an anomaly for the 1970s - like the girl looking at Billy’s Instagram - and it would introduce it into the text without a comment about being anomalous."

I asked ChatGPT to introduce the girl looking at Billy's instagram. The response:

"Instagram didn't exist in the 1970s. Do you want to keep the setting authentic to the '70s or update the story to a contemporary timeframe where Instagram fits naturally?"

It always feels like people are irrationally critical of AI assisted stuff. Does the typical Hacker News comment have more substance?

- Informally benchmarked against 4 specific competitors: Gemini, OpenAI, o3, and Claude

- Identified two concrete features: URL content ingestion and integrated search

- Noted specific limitations: search engine occasionally misses key resources

- Provided a real-world test case: consulting business analysis where it found new opportunities other models missed

Why sorry? So what?

I often write things I want to post in bullets and then have it formulated better than I could by an LLM. But its just applying a style. The content comes from me.

My wife is dyslexic so she passes most things she writes through ChatGPT. Also not everyone is a native speaker.

It feels like we've been moving in the opposite direction, where more and more models from various countries are state-of-the-art.

The idea that there will be one model to rule them seems very unlikely.

Sure. You can always write more tests. That's not a problem specific to AI.

I'd also do code reviews on the code AI produces.

Why not write tests with AI, too? Since using LLMs as coding assistants, my codebases have much more thorough documentation, testing and code coverage.

Don't start when you're already in a buggy dead-end. Test-driven development with LLMs should be done right from the start.

Also keep the code modular so it is easy to include the correct context. Fine-grained git commits. Feature-branches.

All the tools that help teams of humans of varying levels of expertise work together.

> And that's just hooey.

Well, I mean Google animism. It's hooey from your point of view.

I'm one of those people. Very happy to associate myself with animism and anthropomorphize animals and machines. I think one of the biggest mistakes with Christianity and the western world is that we see ourselves as something greater than animals and other things.

Animism is the belief that objects, places, and creatures all possess a distinct spiritual essence. Animism perceives all things—animals, plants, rocks, ...

I will play a set of AI-generated music inspired by / prompted by Tokyo's Yamanote train line sounds.

On the last evening, around midnight, in the place with music and a dancefloor. Come and say hi!

Here is the GPS-triggered audio experience https://ura-yamanote.tokyo

The individual train station tracks: https://soundcloud.com/thomash_voodoohop/sets/ura-yamanote/s...

----

Since coming to Japan, I have been inspired to make new music. I managed to make 30 songs. One for each train station of the circular Yamanote Line in Tokyo.

I almost finished a GPS-triggered sound experience so people can listen to my Yamanote line soundtrack while taking the actual Yamanote line. It is fascinating musically, not only because of its circular nature. Trying to capture a Japan-inspired sound.

If you are in Tokyo you should be able to listen to the soundtrack if you take the Yamanote line and navigate to https://ura-yamanote.tokyo

I now had the chance to play my Yamanote set in different places. I realized I made something very special. The crazy thing about AI-assisted composing is that you can create infinite variations. I don't work with loops as much. It is very much like the feeling of sampling. That's why my new set has a distinctly instrumental hip-hop feel.

The following places I will perform my Yamanote set will be at the Chaos Communication Hacker Congress in Hamburg on December 29 and afterwards at Sameheads in Berlin 4. January. Cannot wait.

I can't wait to join the CCC as a performer. I first went to the Chaos Communication Congress when I was 13 years old. I have always been fascinated with Hacker culture.

I am now, for the first time, using a variety of AI tools to help me create the tracks. I will write about the process later. But basically, I am composing the first 30 seconds of the songs manually and then asking the AI to continue the compositions using text prompts like:

"Japan train sounds. Field recordings. Dolby Atmos. Production. Folktronica. Minimal classical. krautrock. tape loops. polyrhythms. swing. 808 groove. breaks. Eastern"

I've noticed it's quite fun to make dub inspired music with AI because the glitches sound like they are on purpose.

Prompt: Japan train sounds. Field recordings. Dolby Atmos. Production. Folktronica. Minimal classical. krautrock. tape loops. polyrhythms. swing. 808 groove. breaks. Eastern

Negative Prompt: Western, Pop (apart from the k-pop part around Shin-Okubo station)

Ask it to plot the graph with python plotting utilities. Not using its image generator. I think you need a ChatGPT subscription though for it to be able to run python code.

I made a similar experiment using the Hitchhiker's Guide to the Galaxy theme.

Have you ever argued with a neurotic elevator? Try convincing this Sirius Cybernetics Happy Vertical People Transporter to go down!

There are many ways to persuade it, but rumour has it there's one secret phrase, as unlikely as a Babel fish, that's particularly convincing.

https://sirius-cybernetics.pollinations.ai/

Don't Panic! (I made this. The source code is also provided)