Reviewing Wills With Multiple Models Is Fun
benstein · x · 2026-07-10
A user shared that Fable helped draft their estate plan, which they then subjected to adversarial reviews using GPT 5.6 Sol Ultra, Meta Muse Spark 1.1, and Grok 4.5.
They found the process quite different from code review, as it simultaneously involves verifiable citations, explanations, legal writing, judgment, and risk, making the overall experience very "interesting."
Related event: Multi-Model Will Review Sparks Hallucination Debate(3 posts)→
More from Fun
- A temporary custom instruction made ChatGPT pick the Jacobian conjecture — flowersslop · 2026-07-22
- A meme stitches together Claude and Grok quota resets into one AI-user joke — djcows · 2026-07-22
- A SymPy joke turns model tool use into a “neurosymbolic architecture” gag — thomasahle · 2026-07-22
- A meme about AI apps looking great until someone plugs them into Slack — generativist · 2026-07-22
- Fable’s procedural liminal-space demo turns into a creepy interactive scene — AIandDesign · 2026-07-22
- A VR teleop demo for an SO-101 arm gets absurdly low latency by using one Python script — MoonL88537 · 2026-07-22