artale
/
agentic-ai-engineering
1
0
Fork 0
Code Issues Pull Requests Packages Projects Releases Wiki Activity

docs(tac): add antirez export-control corollary to insider-threat note 

Folds antirez's observation that LLM export controls are futile
(weights leak, proxies bypass, enforcement requires dismantling
encryption) into the existing insider-threat model note. Argues
the real safeguard is agent-level sandboxing (OpenShell pattern),
not model distribution control — assume any model can run on any
hardware.
This commit is contained in:
artale 2026-07-07 13:45:55 +02:00
parent fceab3c97c
commit 7d0e096d61
1 changed files with 2 additions and 0 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

2
plans/meta-prompts/loop_engineering.md
View File

@ -143,6 +143,8 @@ Do not trust an agent because it is helpful, local, or model-authored. Trust onl
Reference: Security Fest 2026, Dan Tentler, "Claude is your insider threat now" (YouTube `yvJYw2gR0cU`). Reference: Security Fest 2026, Dan Tentler, "Claude is your insider threat now" (YouTube `yvJYw2gR0cU`).
**Antirez corollary: model export controls are futile against the insider-threat model.** Model weights (few TB files) will inevitably leak; internet proxies render geographical blocks meaningless; enforcement would require dismantling encryption and global connectivity. The real question is not nationality-based restrictions but whether to distribute a powerful model to any general public at all — every large country has internal threats that could misuse leaked copies (antirez, July 2026). This strengthens the case for agent-level safeguards: if you cannot control which model an adversary runs, you must sandbox the agent, policy-gate every action with business impact, and assume any model could be running on any hardware. OpenShell's approach (secure agent runtime, secrets management outside sandbox, policy-based egress) is the correct architecture for this world.
## External research anchors ## External research anchors
Ground agent plans against external production guidance, not just video notes: Ground agent plans against external production guidance, not just video notes: