This 1968 artwork "Interruptions" by Vera Molnár is one of the earliest and most powerful predecessors to today’s generative AI art. Using punch cards and FORTRAN, she programmed perfect algorithmic order then deliberately added randomness and interruptions to create organic chaos. It’s exactly the same core idea we now explore with AI models, only 55+ years earlier /1
I benchmarked 7 AI models on @artblocks_io knowledge.
Results:
- Opus 4.6: 57%
- o3: 56%
- GPT-4.1: 46%
- Sonnet 4.6: 42%
- DeepSeek V3: 40%
- Haiku 4.5: 36%
- Llama 4 Scout: 24%
Built an RL training environment on @PrimeIntellect's hub: 207 questions across 12 categories. Project-to-artist lookups, edition sizes, script libraries, on-chain traits, contract addresses, platform mechanics. Zero-shot, no tools.
57% ceiling across two model families. Every model fails on the same things: project indices, script types for non-famous projects, recent mints, MCP tool knowledge. The stuff you can't get from a blog post.
We launched the Art Blocks MCP a couple weeks ago: structured API access for agents to browse and transact generative art. The environment is the other half: it's how you make agents actually good at it.
Environment is live on the Prime Intellect hub if you want to run your own evals or train against it.
https://t.co/85q9sTdMtj
@jbondwagon@cryptovoxels@beeple My point is that it is pretty pointless to bid on something that is not for sale. Something we tend to forget in the NFT space.