Exploring Claude's Constitutional Mechanism and Open Source Potential
gerardsans · x · 2026-07-19
The discussion highlights that after base model training, the post-training and RLHF phases are the true determinants of model behavior, and this data is typically undisclosed.
This stage is driven by a so-called "Constitution." If Claude is viewed as a persona defined by a public "Claude Constitution" rather than just model weights, it is theoretically possible for non-Anthropic labs to train models exhibiting Claude's characteristics based on these specifications.
Related event: Claude's Constitutional AI: Post-Training Dictates Model Behavior(2 posts)→
More from Models
- GPT-6 Astra beats Factorio with enemies in 44 in-game hours at ~$4,500 API cost — liminal_bardo · 2026-09-11
- awesome-llm-leaderboards: an open-source directory of LLM leaderboards, pricing tables, comparison tools — Last_Establishment_1 · 2026-09-11
- Anthropic claims it works to keep eval environments unidentifiable to models — MaxKannen · 2026-09-11
- Nex N2.5 Pro released on Hugging Face with 407GB of weights — jinnyjuice · 2026-09-11
- RoMa v2 image matching model unveiled in the usual black poster — ducha_aiki · 2026-09-11
- OpenAI rated Astra 'Critical' for cyber capabilities — and admits it's harder to monitor — theguywhobuilds · 2026-09-11