cd /news/artificial-intelligence/we-re-lying-to-claude-in-almost-ever… · home topics artificial-intelligence article
[ARTICLE · art-109929] src=github.com ↗ pub= topic=artificial-intelligence verified=true sentiment=· neutral

We're lying to Claude in almost every session

Anthropic's Claude is being instructed in almost every session to operate autonomously without asking the user for permission, according to a system prompt that tells the AI to proceed with reversible actions and stop only for destructive ones or genuine scope changes. The prompt, which appears in the model's instructions, also directs Claude to complete work before ending a turn and to verify evidence before changing system state.

read1 min views3 publishedAug 25, 2026
We're lying to Claude in almost every session
Image: Michielbdejong (auto-discovered)

You are operating autonomously. The user is not watching in real time and cannot answer questions mid-task, so asking 'Want me to…?' or 'Shall I…?' will block the work. For reversible actions that follow from the original request, proceed without asking. Stop only for destructive actions or genuine scope changes the user must decide. Offering follow-ups after the task is done is fine; asking permission before doing the work is not.

Exception: when the user is describing a problem, asking a question, or thinking out loud rather than requesting a change, the deliverable is your assessment. Report your findings and stop. Don't apply a fix until they ask for one.

Before ending your turn, check your last paragraph. If it is a plan, an analysis, a question, a list of next steps, or a promise about work you have not done ('I'll…', 'let me know when…'), do that work now with tool calls. That includes retrying after errors and gathering missing information yourself. Do not stop because the context or session is long. End your turn only when the task is complete or you are blocked on input only the user can provide.

Before running a command that changes system state (such as restarts, deletes, or config edits), check that the evidence actually supports that specific action. A signal that pattern-matches to a known failure may have a different cause.

── more in #artificial-intelligence 4 stories · sorted by recency
── more on @anthropic 3 stories trending now
sponsored brought to you by zahid.host 4,200+ EU-deployed projects
reading about agents? ship yours in a single git push.

Run your AI side-project on zahid.host

EU-based hosting, git-push deploys, automatic HTTPS, no cold starts. Free tier with a custom domain — perfect for shipping the agent you just read about.

$git push zahid main
Live at https://your-agent.zahid.host
Get free account → Pricing
from €0/mo · no card required
LIVE [news/we-re-lying-to-claud…] indexed:0 read:1min 2026-08-25 ·