korrents

← Do not run a personal agent on a cheap or local model: weak models are gullible and easy to prompt-inject.

On the map

8 connected korrents · 8 moments on record from 31 Dec 2025 to 4 Sept 2026.

Same subjectSame subjectSame subjectSame subjectSame subjectSame subjectSame subjectSame subject Do not run a personal agenton a cheap or local model:weak models are gullible… PS Peter Steinberger — holds since 2026-02-12 Good documentation is produced by effort, not by tooling that keeps code and docs together Good documentation isproduced by effort, not… HH Hamel Husain — holds since 2026-01-18 When two expert users argue over whether documentation is clear, that debate is unproductive — the way to actually find unclear documentation is to test it on real readers, not to have experts argue about wording. When two expert usersargue over whether… JE Julia Evans — holds since 2026-01-08 Auto-mode does not yet convincingly fix prompt-injection risk for coding agents. Auto-mode does not yetconvincingly fix… SW Simon Willison — holds since 2026-08-08 In an agent-written codebase the agent-written tests are equally untrustworthy; manually using the product is the only reliable measure of whether it works. In an agent-writtencodebase the… MZ Mario Zechner — holds since 2026-03-25 This is the year of personal agents, and the fastest way to get one to everyone is to team up with a lab, on condition the project stays open source. This is the year ofpersonal agents, and… PS Peter Steinberger — holds since 2026-02-12 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. Currentprompt-injection… ZM Zvi Mowshowitz — holds since 2026-09-04 AI agents and AI coding will run on servers and from the cloud first, not on your laptop. AI agents and AI codingwill run on servers and… PL Pieter Levels — holds since 2026-06-28 Running coding agents without approval prompts is a normalization-of-deviance risk: the fact that it has not caused a disaster yet is itself the problem. Running coding agentswithout approval… SW Simon Willison — holds since 2025-12-31
same subject