Unverified50% confidenceEventExact time
In 2023, researchers pointed out that GPT-4's technical report lacked adequate acknowledgment of key technical contributors and prior work.
1
Sources
50%
Confidence
Long-term
Relevance
9/11/2026
First Seen
Sources
Related Entities
Related Claims
VerifiedA 2023 Stanford University study found that GPT-4's performance on certain tasks showed a measurable decline over several months.74% similarUnverifiedMultiple academic studies in 2024 showed that models such as GPT-4 are able to identify certain types of software vulnerabilities in controlled environments, with efficiency approaching that of a junior security researcher.74% similarUnverifiedGPT-4 Technical Report长达百页74% similarUnverifiedResearch in 2024 showed that models such as GPT-4 and Claude, assisted by auxiliary tools, are already capable of independently solving approximately 30%–40% of medium-difficulty CTF challenges.73% similarUnverified2023年多项研究表明，GPT-4在回答医学问题时虚构参考文献的比例可高达30%-70%72% similar
Cite This Claim
Stable URI
https://kongchang.com/claim/893158API
curl https://kongchang.com/api/v1/knowledge/claims/893158MCP
get_claim(id=893158)