AI attribution works better than you think. Shapley for inference, LoRA for…
This is a AI post classified by Jev as AI infra & evals (an opinion), kept by the AI Radar because it carries real work, not commentary.
AI attribution works better than you think. Shapley for inference, LoRA for post-training, and hierarchy for pre-training do a surprisingly good job. some demos: - Inference -> Shapley: https://shapley.attribution-based-control.ai/ - Post-Training -> LoRA: https://github.com/iamtrask/abcgpt - Pre-Training -> Hierarchy: https://andrewtrask.substack.com/p/breaking-todays-frontier-ai-companies i recognize that you have to squint to see how hierarchy helps with pre-training attribution. TLDR: everyone is going to fine-tune an open source model with their own private data, and register that on
Posted by ⿻ Andrew Trask (83.5k followers) 18 h ago · 41 likes · 3.2k views · view the original post on X. Kept by the AI Radar as AI infra & evals. Tools mentioned: Shapley Attribution Chat, abcgpt.
More AI work like this
- Live now: our Inference Engineering Track from AI Engineer World's Fair 2026. — @aiDotEngineer
- Trains your own large language model from scratch using plain PyTorch. — @tom_doerr
- Here's a useful use-case for @typesafeai for a change. — @iam_zachi
- This is genius. — @daniel_mac8
- Which GPU should you use for embedding workloads? — @runpod
- Big update to the @Alibaba_Qwen Qwen3.8-Flash-Next single DGX Spark recipe! — @jvr0x
- 🔰 The Databricks Advanced Learning Festival runs September 16 through October 14, with… — @databricks
- Q: What is a trace? — @HamelHusain
Every post is read and classified by Jev (TypeSafe): what it is, which market it belongs to, and whether the link is a real tool. 27.3k posts from 4.8k X accounts over the last 14 days, 1.2k tools, 19 markets. Collected every 5 minutes, fully re-ranked every hour — last update 2026-09-19 19:27 UTC. Full method.