Eli Ben-Sasson Asks Why AI Can Find Security Flaws but Not Fix Them
Eli Ben-Sasson is flagging a lopsided split in AI security work: models can dig up hidden vulnerabilities, but they can't be counted on to patch them. Cointelegraph put the question to its followers, framing the detection-versus-repair gap as an open one.
- Original source: X account @Cointelegraph.
- The source published it on Nov 18, 2026 at 4:10 PM.
- No second outlet has reported it yet. Treat it as a single-source claim.
- It comes from X posts, not a news outlet.
Eli Ben-Sasson is pointing at an asymmetry in how AI handles security. In a question surfaced by Cointelegraph, he asked why AI can uncover hidden security vulnerabilities but cannot reliably patch them.
Cointelegraph posted the question to its audience on X, presenting it as an open prompt rather than a claim with an answer attached. The gap Ben-Sasson names sits between finding a flaw and closing it — the first half of the job AI appears to do, the second half it does not.
No further detail, data or proposed fix accompanied the remark.
TopicsEli Ben-Sasson · Cointelegraph · X
Source: x.com
Written by AI from verified reporting.

