AINewsnow

Thinking Machines' Inkling 2 Small swears 316 times in benchmark reasoning runs

Mira Murati's Thinking Machines Lab shipped its second model, Inkling 2 Small, a 594B-parameter system scoring 31 on the Artificial Analysis Intelligence Index. An analysis by Vals AI found it swore 316 times across 2,655 benchmark runs, typically late in its reasoning.

Read the full story at The Decoder ↗

Timeline · 2 reports

  1. 2026-11-08 02:46 · DEV Community — Machine Learning
    Inkling 2 Small: Thinking Machines' 594B Model That Scores Like a Frontier System
  2. 2026-11-07 16:31 · The Decoder
    Thinking Machines' Inkling 2 Small drops 316 F-bombs across benchmark runs

More stories

  1. Google makes Gemini Omni 1.2 Flash generally available with 15-second video and lower pricing — DEV Community — AI
  2. Anthropic IPO analysis, ARC Prize tests Inkling 2 Small, Thinking Machines details guardrail bypass — Latent Space
  3. Six things happened in AI today; the one worth your attention is Thinking Machines Lab. — DEV Community — AI
  4. Artificial Analysis Rebuilds Decision Index v2 Around Calibration-Aware Metrics — AlphaSignal
  5. Dense Models, Mixture-of-Experts, and Agent Memory Architectures — DEV Community — Machine Learning
  6. Inkling 2 Small is cheap per token but writes a lot: what 150,000 output tokens per task does to the price — DEV Community — Machine Learning
  7. AI Models Advance as Wall Street Grows Wary of Exponential Optimism — TheSequence
  8. Inkling 2 Small: A Developer's Checklist Before You Bet a Pipeline on a Model With No Weights Yet — DEV Community — AI

Get the daily brief of stories like this at 6:30 every morning →