VQV Signal

RESEARCH WATCH TECHNICAL

Warning against telling people to "roll your own crypto with agents"

According to a post on X by @copyconstruct, encouraging people to build their own cryptography with agents without mentioning the continuous verification work that requires is deeply irresponsible. The post points to a ten-year-old AWS paper on formally verifying the HMAC algorithm and the TLS handshake as an example of the rigor involved. This is a social media post and opinion, and the source snippet is cut off before the full argument.

Source: Scobleizer News Pulse (X) · x.com Found via Robert Scoble’s Scobleizer News Pulse · a post on X, not independently verified Published 2026-11-21T02:55:00+00:00 Detected 2026-11-21T09:04:26+00:00
View original source

According to a post on X by @copyconstruct, encouraging people to build their own cryptography with agents without mentioning the continuous verification work that requires is deeply irresponsible. The post points to a ten-year-old AWS paper on formally verifying the HMAC algorithm and the TLS handshake as an example of the rigor involved. This is a social media post and opinion, and the source snippet is cut off before the full argument.

AI-assisted summary based on the listed source.

@copyconstruct calls it deeply irresponsible to encourage people to build their own cryptography with agents without mentioning the continuous verification work that requires. The post points to a ten-year-old AWS paper on formally verifying the HMAC algorithm and the TLS handshake as an example of that rigor. Why...

The warning is aimed at anyone who might use AI agents to write security code without a verification process. According to the source, agent-written security code still needs formal verification and review. Developers and teams considering agent-built cryptography should check what verification and review would be required before relying on it.

Signal Strength 90% Technical label WATCH Public Interest 25 Category RESEARCH Reader Depth TECHNICAL

Signal Strength reflects source quality, relevance, freshness and evidence. Public Interest helps organize discovery; it is not proof of truth.

Public Interest components
Recognizable Entity Score 0 Practical Impact Score 0 Novelty Interest Score 70 Consequence Score 34 Curiosity Score 16 Shareability Score 41

VQV surfaced this signal because it is recent, relevant to AI Search, connected to Scobleizer News Pulse (X).