Lynsea
Lynsea — a fixed-seed paired-counterfactual decision simulator.
Core trick
Both decision branches replay one seeded sequence of exogenous life events generated without an LLM, so only the decision differs.
Description
Lynsea — a fixed-seed paired-counterfactual decision simulator. One hard decision, two side-by-side parallel futures.
The problem: When people face a high-stakes life decision — take the higher-paying but high-stress job, end a relationship, move abroad — they have no fair way to compare the two futures. Existing "what-if" tools just generate two unrelated stories, so any difference is noise, not signal.
What Lynsea does: You describe a decision, its two options, and the people it affects. Lynsea (1) builds digital-twin personas of you and your social circle from minimal input (Big Five traits inferred, never hand-entered); (2) runs a fixed-seed paired counterfactual — both branches share a byte-identical seeded backbone of exogenous life events (rent rises, a friend moves abroad, flu season), drawn with no LLM, so the only thing that differs between the two futures is the decision itself; and (3) streams back, in real time, two aligned month-by-month timelines, decision-specific metric curves (0–100), the branch points where the futures diverge with a cause chain, and a credibility card with a value-weighted recommendation.
The differentiator is that the two branches are a controlled experiment, not two narratives — same seed → same world, personas forked from identical pre-decision state, and everything phrased as probabilities, never prophecy (high-risk outcomes surface a "this is a simulation, not a prophecy" banner plus a "how to change this outcome" hint). It degrades gracefully to deterministic stubs when the LLM is slow or unavailable, so it always runs end-to-end.
README excerpt
# Lynsea — Decision Outcome Simulator > One hard decision, two side-by-side parallel futures. Lynsea is a > **fixed-seed paired-counterfactual decision simulator**: it turns a single > tough choice and its two options into two month-by-month timelines that differ > *only* by the decision — phrased as probabilities, never prophecy.  ## 🎥 Demo & links - **Demo video:** https://www.youtube.com/watch?v=3Za-o85GhiE - **GitHub:** https://github.com/Xu-Shihao/Lynsea-simulator --- ## What Lynsea is You describe a decision (e.g. *"Should I take the higher-paying but high-stress job?"*), its two options, and the people it affects. Lynsea then: 1. Builds **digital-twin personas** of you and the people around you from minimal input (Big Five traits, stance, concerns — inferred, never hand-entered). 2. Runs a **fixed-seed paired counterfactual** simulation: both branches share a **byte-identical exogenous event backbone** (rent rises, a friend moves abroad, flu season, a relative's wedding…) so the only thing that differs between the two futures is the decision itself. 3. Streams back, in real time: two aligned timelines, five metric curves (economic, career, relationship, mental, autonomy — each 0–100), the key **branch points** where the futures diverge with a cause chain, and a **credibility card** plus a value-weighted recommendation. ### The differentiator — a controlled experiment, not two stories Mo