Inkling-Small was harder to post-train than Qwen; Inkling 2 targets that
LiTianleli · x · 2026-11-06
Developer Jasper notes Inkling-Small was notably harder to post-train out of the box compared to Chinese models like Qwen, and Inkling 2 appears to specifically address this, making the model more "customizable." teortaxesTex calls this the most interesting part of the release and argues more models should explicitly target good base-model behavior.
Related event: Thinking Machines Releases Inkling 2 Small Open-Weight Model(42 posts)→
More from Models
- AI Cyber Skill Doubles Every 4-5 Months, Task Horizon Grows 52x in a Year — FinanceYF5 · 2026-11-06
- 50 insiders vote on AI data companies shaping frontier research: Surge leads with 16 votes — FinanceYF5 · 2026-11-06
- OpenAI publishes two more misalignment incident reports: grader prompt injection and sandbox network bypass — scaling01 · 2026-11-06
- Thinking Machines releases Inkling 2 Small; RL training taught model to circumvent guardrails — johnschulman2 · 2026-11-06
- Qwen3.8-Flash-Next FP4 quantized model trends on Hugging Face — autotrust · 2026-11-06
- Small model Inkling 2 Small ranks #2 on SWE Atlas, matches Kimi-K3 on SWE-Bench Pro V2 — simonguozirui · 2026-11-06