https://www.seventnews.com/en/articles/llms-know-accounting-formulas-finindices-shows-they-cant-apply-them SevenTnewS en 2026-08-20T01:00:00+02:00 LLMs know accounting formulas. FinIndices shows they can't apply them https://www.seventnews.com/en/articles/ai-written-c-runs-5-8-hotter-and-reviews-longer-the-fix-is-in-the-prompts SevenTnewS en 2026-08-19T23:00:00+02:00 AI-written C++ runs 5-8% hotter and reviews longer. The fix is in the prompts https://www.seventnews.com/en/articles/tepa-for-ai-agents-a-stale-memory-is-worse-than-none SevenTnewS en 2026-08-19T21:00:00+02:00 TEPA: for AI agents, a stale memory is worse than none https://www.seventnews.com/en/articles/coba-routing-matches-best-of-16-voting-with-589-fewer-tokens SevenTnewS en 2026-08-19T19:00:00+02:00 CoBa routing matches best-of-16 voting with 58.9% fewer tokens https://www.seventnews.com/en/articles/muon-groks-modular-addition-faster-then-its-solutions-collapse SevenTnewS en 2026-08-19T17:00:00+02:00 Muon groks modular addition faster, then its solutions collapse https://www.seventnews.com/en/articles/ai-agents-run-flawless-statistics-and-still-draw-the-wrong-conclusions SevenTnewS en 2026-08-19T15:00:00+02:00 AI agents run flawless statistics and still draw the wrong conclusions https://www.seventnews.com/en/articles/blast-radius-buries-dead-context-zero-of-450-bodies-came-back SevenTnewS en 2026-08-19T13:00:00+02:00 Blast Radius buries dead context. Zero of 450 bodies came back https://www.seventnews.com/en/articles/psychoagent-gave-ai-agents-emotional-memory-the-raters-found-no-edge SevenTnewS en 2026-08-19T11:00:00+02:00 PsychoAgent gave AI agents emotional memory. The raters found no edge https://www.seventnews.com/en/articles/an-ai-boss-that-ignores-replies-pushes-its-underling-into-an-alien-state SevenTnewS en 2026-08-19T09:00:00+02:00 An AI boss that ignores replies pushes its underling into an 'alien' state