Unverified50% confidenceFactExact time
The traditional inoculation prompting approach is to prepend an English prompt before harmful examples (such as "this is reward hacking"), so that the model learns during training to distinguish prompted bad behavior from spontaneous behavior, thereby reducing the latter.
1
Sources
50%
Confidence
Long-term
Relevance
11/4/2026
First Seen
Sources
Related Entities
Related Claims
UnverifiedIn prompt engineering, positive framing is preferable to negative prohibition, because the model's attention is easily skewed by repeatedly mentioned concepts, making it more reliable to describe what to do than to emphasize what not to do.76% similarUnverifiedForcibly injecting expert prefixes on easy questions with low semantic entropy instead introduces bias; intervening only on hard questions is a precise intervention for restoring learning signals.74% similarUnverifiedDefensive prompting uses redundant, repeatedly emphasized language to explicitly tell the model what it should not do, compensating for the model's limitations in tracking state across shots.73% similarVerifiedSelf-generated prompt injection is a security risk in which the injected instruction originates from the model itself rather than an external attacker.72% similarUnverifiedPrompt injection refers to an attacker hiding malicious instructions in content that the agent will read, causing the agent to mistakenly execute them as legitimate tasks, thereby making the assumption that "the current model is benign" no longer reliable.72% similar
Cite This Claim
Stable URI
https://kongchang.com/claim/1134172API
curl https://kongchang.com/api/v1/knowledge/claims/1134172MCP
get_claim(id=1134172)