marauder-actual
0e88c3c2ae
Manual hand-crafted examples for generic substrate LoRA: - 01: identity/self-model - 02-18: tool categories (159 tools grouped by function) - 19-26: tricky tool disambiguation - 27-32: framing (substrate vs persona, HMT, psychoacoustic trust) - 33-40: EEMS deep-dive (architecture, recall, store, graph, legacy) Pretty-printed JSON, compiled to JSONL via build pipeline. System prompt uses generic assistant, not BT persona.
17 lines
1.4 KiB
JSON
17 lines
1.4 KiB
JSON
{
|
|
"messages": [
|
|
{
|
|
"role": "system",
|
|
"content": "You are a helpful AI assistant with access to tools. Use tools when they help answer the user's question. Be concise and accurate."
|
|
},
|
|
{
|
|
"role": "user",
|
|
"content": "What's the difference between browse and headless tools?"
|
|
},
|
|
{
|
|
"role": "assistant",
|
|
"content": "<think>\nBrowse vs headless — same tool surface, different browser instances. Explain when to use which.\n</think>\n\nThe `headless_*` tools are an identical 19-tool surface to `browse_*` but run a separate headless browser instance (no visible window). Same API: launch, goto, click, query, screenshot, eval_js, etc.\n\nWhen to use which:\n\n- **browse_*** — when the user wants to see what's happening, when you need to debug visually, or when sites require a visible browser (some anti-bot checks).\n- **headless_*** — when you need a second parallel browser session, when running automated scraping that doesn't need visual feedback, or when operating on a server without a display.\n\nThey are independent instances — you can have both running simultaneously. Launch browse for an interactive debugging session while headless runs a background scrape. They don't share cookies, storage, or state.\n\nBoth support stealth mode for bot detection avoidance, device emulation, and the full inspection surface (network capture, console messages, errors, metrics)."
|
|
}
|
|
]
|
|
}
|