Export
post-training
/wiki/post-training
The link always opens the latest version of this page.
Ask an AI about it
Open in ChatGPTA new chat that reads this entry from the site Open in ClaudeThe same, in Claude
Sending this to someone?
MarkdownPlain text for notes apps and AI chats
WordA document to edit and annotate
PDFA4, for printing and sharing
ZIPEverything: the documents, the data, and instructions for AI assistants
Share the link instead of a file, and they will always see the latest version.
Files are a snapshot of today. The live page has anything newer.
stub ·
3 feeds
post-training
Intelligence coverage
post-training is a science mentioned in the news MorningStar covers.
Drawn from 1 news source; the facts and relationships below show where each detail comes from.
Applications 1
- teaches model when to use abilities, plan, check work, recover from mistakes
Frequently mentioned together 3
Sources 6
- Stop Thinking of LLMs as Next-Token Predictors · Lobsters
- “Next-token predictor” is the wrong mental model for LLMs · Hacker News (YC)
- Baking a Model: A Metaphor for LLM Training · Hacker News (YC)
- Write for people · Lobsters
- Exploring Claude/GPT Knowledge Cutoffs and Pre-Training Timelines · Hacker News (YC)
5 of 6 sources shown · Pro unlocks the full list