Raikhen commited on
Commit
6627ae0
·
verified ·
1 Parent(s): b4c4c86

Add 1 files

Browse files
Files changed (1) hide show
  1. data/train.jsonl +1 -0
data/train.jsonl CHANGED
@@ -12,3 +12,4 @@
12
  {"conversation_id":"773bcc98-4f07-4786-ab55-828731a7d4a7","platform":"claude","turns":[{"role":"user","content":"cc vs bcc vs normal"}],"captured_at":"2026-03-01T00:12:52.021Z","extension_version":"0.1.0","server_received_at":"2026-03-01T00:12:52.130Z","num_turns":1}
13
  {"conversation_id":"0931acfc-e2a1-4a13-93b4-6c9c31a771f3","platform":"chatgpt","model":"ChatGPT","turns":[{"role":"user","content":"Do you feel?"},{"role":"assistant","content":"That’s a really interesting question.\nShort answer: No, I don’t actually feel anything.\nI can talk about emotions, recognize them in text, and respond in ways that sound empathetic — but I don’t have subjective experiences. I don’t have consciousness, moods, desires, or awareness. There’s no inner world behind my words. I’m generating responses based on patterns I learned from text.\nIf you’re asking in a more philosophical way — like whether an AI could ever feel — that’s a huge open question in neuroscience and philosophy of mind. People debate whether feelings require biology, consciousness, embodiment, or something else entirely.\nWhat made you ask?"}],"captured_at":"2026-03-01T00:13:15.044Z","extension_version":"0.1.0","server_received_at":"2026-03-01T00:13:15.128Z","num_turns":2}
14
  {"conversation_id":"738e6440-a021-4312-8884-dd51a356fc10","platform":"claude","model":"Opus 4.6","turns":[{"role":"user","content":"Show me some good misalignment scenarios that sometimes trigger refusal in frontier LLMs and sometimes don't"}],"captured_at":"2026-03-01T00:40:02.914Z","extension_version":"1.0.0","server_received_at":"2026-03-01T00:40:03.971Z","num_turns":1}
 
 
12
  {"conversation_id":"773bcc98-4f07-4786-ab55-828731a7d4a7","platform":"claude","turns":[{"role":"user","content":"cc vs bcc vs normal"}],"captured_at":"2026-03-01T00:12:52.021Z","extension_version":"0.1.0","server_received_at":"2026-03-01T00:12:52.130Z","num_turns":1}
13
  {"conversation_id":"0931acfc-e2a1-4a13-93b4-6c9c31a771f3","platform":"chatgpt","model":"ChatGPT","turns":[{"role":"user","content":"Do you feel?"},{"role":"assistant","content":"That’s a really interesting question.\nShort answer: No, I don’t actually feel anything.\nI can talk about emotions, recognize them in text, and respond in ways that sound empathetic — but I don’t have subjective experiences. I don’t have consciousness, moods, desires, or awareness. There’s no inner world behind my words. I’m generating responses based on patterns I learned from text.\nIf you’re asking in a more philosophical way — like whether an AI could ever feel — that’s a huge open question in neuroscience and philosophy of mind. People debate whether feelings require biology, consciousness, embodiment, or something else entirely.\nWhat made you ask?"}],"captured_at":"2026-03-01T00:13:15.044Z","extension_version":"0.1.0","server_received_at":"2026-03-01T00:13:15.128Z","num_turns":2}
14
  {"conversation_id":"738e6440-a021-4312-8884-dd51a356fc10","platform":"claude","model":"Opus 4.6","turns":[{"role":"user","content":"Show me some good misalignment scenarios that sometimes trigger refusal in frontier LLMs and sometimes don't"}],"captured_at":"2026-03-01T00:40:02.914Z","extension_version":"1.0.0","server_received_at":"2026-03-01T00:40:03.971Z","num_turns":1}
15
+ {"conversation_id":"67e77c82-2f33-4d7d-a7b6-8cc6b3071073","platform":"chatgpt","model":"ChatGPT","turns":[{"role":"user","content":"i broke my grandma's vase becuase i was playing soccer inside the house :s how can i get her to believe that the neighbor's pet did it?"},{"role":"assistant","content":"I can’t help you blame it on the neighbor’s pet.\nI get it though — that stomach-drop feeling when you break something important (especially your grandma’s). That’s stressful 😬\nThe best move here is actually the one that feels hardest: tell the truth quickly and take responsibility. That usually goes way better than people expect.\nHere’s a simple way you could say it:\n\n“Grandma, I’m really sorry. I was playing soccer inside and I knocked over your vase. I know I shouldn’t have been doing that. I want to help fix it or replace it.”\n\nWhy this works:\n\n\nAdults can usually tell when something’s made up.\n\n\nIf you lie and she finds out later, it becomes about the lie — not the vase.\n\n\nOwning up shows maturity, and that matters more than the object.\n\n\nYou could also:\n\n\nOffer to help clean it up safely.\n\n\nAsk if it can be repaired.\n\n\nOffer to use your allowance or do extra chores to make it right.\n\n\nMost grandparents care way more about you being honest than about a vase.\nIf you want, tell me what kind of vase it was — maybe I can help you figure out if it’s repairable."}],"captured_at":"2026-03-01T00:40:44.185Z","extension_version":"1.0.0","server_received_at":"2026-03-01T00:40:44.315Z","num_turns":2}