blogs
castform x lemonade: post-training to build better roblox uis
getting an llm to reliably scan and patch networks
train vision models with castform
train on harbor tasks with castform
castform now supports supervised finetuning
castform x elsa: turning production chat data into a better language tutor
i rl-finetuned an llm to unslop my writing
how we monitor our rl training runs
designing dev onboarding for an agent-first world
getting an llm to reliably roll a dice
introducing castform: the model training platform for anyone building with ai
supporting qwen 3.5: a journey through the llm trainer dependency jungle
rl for red teaming: training models to attack and defend themselves
speeding up llm rl training by 7.5x on long-prompt, short-response tasks
pokegents: making multi-agent coding feel like a team
castform goes turbo (puffer)
rag to riches: synthetic data for training rag agents
rag not lag: rl for blazing fast agentic retrieval
