Fetching from the wire…
01
02
03
04
05
06
07
08
Research2026-06-20 · source-backed
Using op-schema-aware seeded fuzzing against a high-precision fp64 CPU reference on 24 Triton kernels, 15 correct and 9 intentionally buggy, the method caught all 9 buggy variants and passed all 15 controls across five GPU classes (arXiv:2606.20128). Standard kernel benchmarks would have missed those bugs. If you're trusting a kernel-generation leaderboard, or your own model's CUDA output, the test suite under it is probably too weak to catch the failures that matter.
Each link below shares sources, entities, or timing with this story.
Claude Fable uses CUDA / Shared entities / What happened next
Linked by a graph relationship (Claude Fable uses CUDA); both cover LLM, Triton; picks up the LLM thread on 2026-07-31.
Simon Willison released LLM / Shared entity: LLM / What happened next / Tension
Linked by a graph relationship (Simon Willison released LLM); both cover LLM; picks up the LLM thread on 2026-07-27.
Linked by a graph relationship (Simon Willison released LLM); both cover LLM; picks up the LLM thread on 2026-08-16.
Simon Willison released LLM / Shared entity: LLM / Earlier coverage / Tension
Linked by a graph relationship (Simon Willison released LLM); both cover LLM; earlier LLM coverage from 2026-06-19.
Linked by a graph relationship (Simon Willison released LLM); both cover LLM; earlier LLM coverage from 2026-06-18.
Simon Willison released LLM / Shared entity: GPU / Earlier coverage / Tension
Linked by a graph relationship (Simon Willison released LLM); both cover GPU; earlier GPU coverage from 2026-04-23.
Claude Fable uses CUDA / Shared entity: LLM / Earlier coverage
Linked by a graph relationship (Claude Fable uses CUDA); both cover LLM; earlier LLM coverage from 2026-06-19.
Simon Willison released LLM / Shared entity: LLM / What happened next
Linked by a graph relationship (Simon Willison released LLM); both cover LLM; picks up the LLM thread on 2026-08-17.