Show HN: Fine-tuned Qwen2.5-7B on 100 films for probabilistic story graphs

Re:Show HN: Fine-tuned Qwen2.5-7B on 100 films for probabili... by Foreignborn on Sunday February 08, 2026 @09:47AM (#46934643)

I _really_ think you have an interesting tool, but the workflow loop isn't fully there.

Please let me revise or remix a suggested node. I find them extremely engaging, and I can envision ways of sort of "spinning off" even further than it's suggestions. Think Brian Eno's Oblique Strategies.

To me, this is hinting at really interesting creative processes that feel much more humane than how most LLMs work today.

[ Parent | on HN ]

Re:Show HN: Fine-tuned Qwen2.5-7B on 100 films for probabili... by graphpilled on Sunday February 08, 2026 @09:55AM (#46934711)

The Oblique Strategies comparison is exactly the vibe I was going for—generative constraints that open up possibilities rather than closing them down. Node editing is the top priority right now. You're right that the loop isn't complete without it.

[ Parent | on HN ]

Re:Show HN: Fine-tuned Qwen2.5-7B on 100 films for probabili... by mistrial9 on Sunday February 08, 2026 @10:15AM (#46934939)

so great to see Oblique Strategies by Eno surviving in minds of 2026

[ Parent | on HN ]