"Agentic gradient": letting agents freely modify their own harness and weights
willcb · x · 2026-10-20
willcb outlines where he thinks methods are heading, coining the term "agentic gradient": the endgame where an agent can do whatever it wants to its own harness or weights.
He frames the core challenge as a meta-RL problem — making this actually work, with many bridges to cross along the way. The tweet expands on his earlier claim of significant method-level updates recently.
Related event: Researcher says engram modules are foundational for continual learning(3 posts)→
More from Research
- Tadpole: TUM uses autoencoders as foundation models for 3D PDEs with online learning — jiqizhixin · 2026-10-23
- Arc Institute's COMPASS Uses Genomic Language Models to Map Noncoding DNA Functions — anshulkundaje · 2026-10-23
- FDA crosses a regulatory watershed with personalized neoantigen cancer vaccine, per Gottlieb — alex_peys · 2026-10-23
- VIPerturb-seq Update: 10x Genomics to Commercialize Single-Cell CRISPR Screening Tech — anshulkundaje · 2026-10-23
- New Paper Replicates Transformer Loss Spikes with Simple Quadratic Models — CSProfKGD · 2026-10-23
- Diffusion Models book team to host NeurIPS 2026 tutorial on diffusion LLMs in Sydney — mittu1204 · 2026-10-23