Unverified50% confidenceFactExact time
A pretrained-only model is good at continuing text but not at answering questions or following instructions; Anthropic's glossary states this directly.
1
Sources
50%
Confidence
Long-term
Relevance
10/19/2026
First Seen
Sources
Related Entities
Related Claims
UnverifiedModels were not explicitly trained to persuade, yet they naturally acquired persuasion capabilities through language generation; researchers call this emergent persuasion ability.75% similarUnverifiedLarge language models have no genuine introspective access to their own execution traces and can only reconstruct a plausible-looking narrative based on context and training tendencies74% similarUnverifiedSimply switching to a stronger model cannot solve the problem of AI drafts reading "flat", because the model optimizes for "resembling the training data" rather than "having a personal style".74% similarUnverifiedThe author found that putting process constraints at the code layer (such as REQUIRED in tools.py) is more reliable than at the prompt layer, because the model sometimes skips the steps required by the prompt and answers directly.74% similarUnverifiedExperiments found that a meta-model trained on word-level features could not predict which words should be removed, indicating that there is no targetable objective for fine-tuning stopword lists.73% similar
Cite This Claim
Stable URI
https://kongchang.com/claim/1069870API
curl https://kongchang.com/api/v1/knowledge/claims/1069870MCP
get_claim(id=1069870)