korrents

On the map

Tap a claim on the ring to put it at the centre.

← Prompt injection is an extremely hard attack to defend against, and…

8 connected korrents · 7 moments on record from 22 Mar 2025 to 4 Sept 2026.

Same subjectSame subjectSame subjectSame subjectSame subjectSame subjectSame subjectSame subject Read this korrent: Prompt injection is an extremely hard attack to defend against, and hardly anyone integrating AI is talking about it. Prompt injection is an extremelyhard attack to defend against, andhardly anyone integrating AI istalking about it. TH ThePrimeagen — holds since 2025-03-22 — tap for who they are Same subject: Auto-mode does not yet convincingly fix prompt-injection risk for coding agents. — tap to centre the map on it Auto-mode does not yetconvincingly fixprompt-injection risk forcoding agents. SW Simon Willison — holds since 2026-08-08 — tap for who they are Same subject: Prompt injection can be caught by watching the neurons that fire when it happens, so a defence no longer depends on the model reporting the attack. — tap to centre the map on it Prompt injection can be caughtby watching the neurons thatfire when it happens, so adefence no longer depends on… BC Boris Cherny — holds since 2026-07-27 — tap for who they are Same subject: Prompt injection has no equivalent of parameterized queries: there is no reliable way to tell a language model which text is data and which is instructions. — tap to centre the map on it Prompt injection has noequivalent of parameterizedqueries: there is no reliableway to tell a language model… SW Simon Willison — holds since 2026-03-19 — tap for who they are Same subject: Prompt injection is no longer a live attack on the frontier model: it simply does not follow instructions it reads on the internet any more. — tap to centre the map on it Prompt injection is no longera live attack on the frontiermodel: it simply does notfollow instructions it reads… BC Boris Cherny — holds since 2026-07-27 — tap for who they are Same subject: Prompt injection is unsolved, but the latest models are post-trained to resist it, so it takes far more than 'ignore all previous instructions' now. — tap to centre the map on it Prompt injection is unsolved,but the latest models arepost-trained to resist it, soit takes far more than 'ignore… PS Peter Steinberger — holds since 2026-02-12 — tap for who they are Same subject: Current prompt-injection defenses for AI agents (such as auto mode) are now reliable enough that agents can practically be assumed safe from successful injection attacks. — tap to centre the map on it Current prompt-injectiondefenses for AI agents (suchas auto mode) are now reliableenough that agents can… ZM Zvi Mowshowitz — holds since 2026-09-04 — tap for who they are Same subject: The only guaranteed defence against a prompt-injection attack is to remove one of its three legs — private data, exposure to untrusted content, or a way to send data out. — tap to centre the map on it The only guaranteed defenceagainst a prompt-injectionattack is to remove one of itsthree legs — private data… SW Simon Willison — holds since 2026-03-19 — tap for who they are Same subject: Letting the public see a powerful AI does something no essay about AI can do, and that is a real reason not to straight-shot superintelligence. — tap to centre the map on it Letting the public see apowerful AI does something noessay about AI can do, andthat is a real reason not to… IS Ilya Sutskever — holds since 2025-11-25 — tap for who they are
same subject or similar wording

At the centre Prompt injection is an extremely hard attack to defend against, and hardly anyone integrating AI is talking about it. Holds ThePrimeagen Read this korrent →