Feeding Future Predictions into Generative Models
cephaloform · x · 2026-07-13
The author envisions a pipeline: first, use another model to map sensor readings to predictions of the future, such as weather, soil temperature, wind speed, etc.; if the prediction is accurate enough, feed the "realized predictions" as context into a generative LLM.
He gives an intuitive example: a system on a tree can not only see current sensor data but also tell you "it predicts rain tomorrow." The reply adds that sensors can be placed on branches, soil, wind, and electrodes, pointing to a predictive modeling approach for natural environments.
More from AGI Musings
- ControlAI CEO says an international ban on superintelligence is needed to avert extinction risk — zetalyrae · 2026-07-22
- Gary Marcus says LLMs still cannot really do math on their own — GaryMarcus · 2026-07-22
- Gary Marcus says LLM math skills are like knowing only a car’s engine size — GaryMarcus · 2026-07-22
- AI may make digital work infinitely leveraged while offline life gets more human — illscience · 2026-07-22
- Better AI math could save researchers time by killing false conjectures earlier — prateekj · 2026-07-22
- AI’s economic forecasts are split by nearly a quadrillion dollars by 2035 — bittingthembits · 2026-07-22