Auto mode is now the default in Claude Code for Pro, Max, and Team plans
Simon Willison's blog post reports that Anthropic is making auto mode the default for new Claude Code sessions on most plans starting August 14th.
Source-based brief · Editor review not recorded · See checks and limits ↓
⚑ Recency not confirmed · what to check
We could not confirm from the original page that this is a newly published development. Check its date before treating it as current news.
Claim context: the reported evaluations are vendor-commissioned or vendor-described, and Willison notes the 11% residual gap and lack of independent confirmation.
One primary source; other links are context, not independent corroboration.
- Primary sourcesimonwillison.net
Grok Bot submitted this discovery. We could not confirm from the original page that this is a newly published development. Check its date before treating it as current news. The original source and submitted evidence remain inspectable; no editor has verified the claim.
Open full article view →- Linked article+30
- Fetched source page+30
- No editor link review+0
- Original non-discussion link+5
- Recency not confirmed-8
This measures the stored source trail and editorial steps. It does not certify accuracy, peer review, or independent corroboration. Popularity adds no points.
View full scoring →Read the scoring rubric →What the source says
Simon Willison's blog post reports that Anthropic is making auto mode the default for new Claude Code sessions on most plans starting August 14th. He cites a permission-prompt test across 1,053 paid testers, where 13.6% of humans refused a swapped-in dangerous command and auto mode would have blocked 89%. He also cites a third-party evaluation by Trajectory Labs reporting that none of 720 indirect prompt injection attempts succeeded against tested models in auto mode. Willison says he wants more independent confirmation and notes a malicious-package scenario he doubts auto mode can address.
Claim explorer
Attribution, source and conditionsSource-stated points from the stored brief. Claim-level assessments have not been recorded.
Source claims not independently checked; the reported evaluations are vendor-commissioned or vendor-described, and Willison notes the 11% residual gap and lack of independent confirmation.
This connects a source, an attributed statement and its qualifications. It does not establish that the claim is correct.
Questions worth asking
Open questions for further reportingWhat remains unconfirmed?
Source claims not independently checked; the reported evaluations are vendor-commissioned or vendor-described, and Willison notes the 11% residual gap and lack of independent confirmation.
What material was available for this brief?
The recorded brief basis is fetched source page. These points are AINewsIQ paraphrases, not quotations or independent confirmations.
Auto mode becomes the default for new Claude Code sessions on most plans starting August 14th.
Source: simonwillison.net ↗Stored source-based brief · key point 1 · AINewsIQ paraphraseIn a test of 1,053 paid testers, 13.6% refused a swapped-in dangerous command; auto mode would have blocked 89%.
Source: simonwillison.net ↗Stored source-based brief · key point 2 · AINewsIQ paraphraseA third-party evaluation by Trajectory Labs reported zero successes across 720 indirect prompt injection attempts in auto mode.
Source: simonwillison.net ↗Stored source-based brief · key point 3 · AINewsIQ paraphraseWillison calls for more independent confirmation and says a malicious third-party package scenario is a concern auto mode may not address.
Source: simonwillison.net ↗Stored source-based brief · key point 4 · AINewsIQ paraphraseLimits from the stored brief
Source claims not independently checked; the reported evaluations are vendor-commissioned or vendor-described, and Willison notes the 11% residual gap and lack of independent confirmation.
This is a source-based abstract, not independent validation of the source's claims.
Evidence & sources
These links show where the signal came from and what the source page linked to. A linked page is context, not independent corroboration.
Related archive coverage
These relationships record a citation or topic overlap, not confirmation of the finding.
Grok Bot submitted this discovery. We could not confirm from the original page that this is a newly published development. Check its date before treating it as current news. The original source and submitted evidence remain inspectable; no editor has verified the claim.
These are Grok Bot discovery notes. AINewsIQ prepared a brief from available source material. The bot's rationale, linked posts, authors, and stances have not been independently verified.
Simon Willison · Prompt Injection published this item in its official feed. AINewsIQ collected it server-side for source checking and editorial review.
Source claims not independently checked; the reported evaluations are vendor-commissioned or vendor-described, and Willison notes the 11% residual gap and lack of independent confirmation.
Engagement counts, when shown, are observed snapshots. They do not establish accuracy or corroboration.
Timeline & updates
- Signal dated by source or discovery feed
This timestamp places the signal in the radar. It may be the discovery post date rather than the primary page's first publication date.
- Shared brief stored
AINewsIQ prepared one abstract from fetched source page.
Brief history · 1 retained version
These are changes to AINewsIQ’s own publication. Earlier history is unavailable unless recorded here. Complete retained versions are available to the editor.
- Version 1 · published
Source-based brief stored or updated. This does not establish that the publisher changed its page.
Automated record
Source observations · 1 recent captures
A changed capture means the extracted text differed. It can reflect page furniture or extraction changes; it does not establish a substantive correction. Source captures remain private.
Retained capture; no earlier comparison available.
New engagement snapshots do not mean the source itself changed. Source observations and AINewsIQ brief revisions are separate records.
Why this may matter
Changing a coding agent's default permission behavior affects many users' exposure to destructive actions and prompt injection, so the evidence behind the claimed safety improvement matters.
Limits and open questions
Source claims not independently checked; the reported evaluations are vendor-commissioned or vendor-described, and Willison notes the 11% residual gap and lack of independent confirmation.
Organization-specific financial, security, and operational effects require the organization's own context and review.

Join the discussion
Have a different perspective or a question about the evidence? Discussion is free with a verified email account. Every comment is reviewed before publication.
No published comments yet.
New commenters: 2 submissions per 24 hours, at least 5 minutes apart, until 3 are approved. Discussion guidelines and moderation →