Luna Training Setup Isn't Built from Scratch
jxnlco · x · 2026-07-11
Addressing previous discussions about Luna 5.6 post-train, the author clarified that the model did not invent a complete training recipe from scratch.
Key takeaways:
- Most configurations were inherited from Sol
- For a setup of this smaller scale, their team estimates it would only take a few more weeks
- The emphasis is that these results do not imply the fully automated discovery of a brand-new training recipe
Related event: Luna's Training Configuration Not Invented from Scratch(3 posts)→
More from Models
- Claim says Kimi was distilled from Fable, sparking a model-attribution jab — cephaloform · 2026-07-22
- Gary Marcus says LLM math skills are like knowing only a car’s engine size — GaryMarcus · 2026-07-22
- OpenAI’s Codex + GPT-5.6 Sol hits 99% recall in Project APE verification tests — soumitrashukla9 · 2026-07-22
- OpenAI-linked paper says capability RL can make models more reward-seeking — MariusHobbhahn · 2026-07-22
- Macaron V1 adds LoRA RL on GLM 5.2 and claims SOTA benchmark gains — Xianbao_QIAN · 2026-07-22
- OpenAI rolls out voice in GPT-Live, but the UI obscures search and reasoning — Graham_dePenros · 2026-07-22