Fetching from the wire…
01
02
03
04
05
06
07
08
Research2026-08-14 · source-backed
arXiv 2608.13292 characterized 28 APR approaches on SWE-bench Verified: median 121.78% more total changes, 80.91% more net changes, 43.99% higher cyclomatic complexity than the developer patch, even when correct. The verbosity is rooted in capability-oriented design and resists output-format and minimality prompts, and baselines that shrink patches lose 49–217 resolved instances. Their RECAP post-generation refiner cuts total changes from +242% to +4.24% while preserving or improving resolution by up to 42 instances. Fix it after generation, not during.
Each link below shares sources, entities, or timing with this story.
Simon Willison released LLM / Shared entities / Earlier coverage / Tension
Linked by a graph relationship (Simon Willison released LLM); both cover SWE, Verified; earlier SWE coverage from 2026-04-23.
Simon Willison released LLM / Shared entity: LLM / Shared topic / Earlier coverage
Linked by a graph relationship (Simon Willison released LLM); both cover LLM; overlapping topics (agent, design).
LLM uses OpenAI / Shared entity: LLM / Earlier coverage / Tension
Linked by a graph relationship (LLM uses OpenAI); both cover LLM; earlier LLM coverage from 2026-07-27.
LLM uses OpenAI / Shared entity: SWE / Earlier coverage / Tension
Linked by a graph relationship (LLM uses OpenAI); both cover SWE; earlier SWE coverage from 2026-04-25.
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: SWE / Earlier coverage / Tension
Linked by a graph relationship (Simon Willison released LLM); both cover SWE; earlier SWE coverage from 2026-03-17.
LLM uses OpenAI / Shared entity: LLM / Earlier coverage
Linked by a graph relationship (LLM uses OpenAI); both cover LLM; earlier LLM coverage from 2026-07-31.