Open in the consoleIts links, as a graph
Export
Raven RSI
/wiki/raven-rsi
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
With its linksA pack for Claude, ChatGPT, Gemini or NotebookLM, or STIX and CSV, from the console
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 ·
1 feed
Raven RSI
Recursive self-improvement demonstration where Raven autonomously improved its own performance through iterative experimentation.
Snapshot
- Outcome
- 172 training runs across 7 rounds reducing val_bpb by 5.8% within 20-minute single-GPU budget 1 source
Intelligence coverage
Recursive self-improvement demonstration where Raven autonomously improved its own performance through iterative experimentation.
Drawn from 1 news source; the facts and relationships below show where each detail comes from.
Facts 1
| Attribute | Value | Confidence | Sources | Cited |
|---|---|---|---|---|
| Outcome | 172 training runs across 7 rounds reducing val_bpb by 5.8% within 20-minute single-GPU budget | low | 1 | 1 |
Sources 1
- Show HN: Raven – The harness of harnesses, built for RSI · Hacker News (YC)