Claude Fable is relentlessly proactive
Simon Willison describes using Claude Fable 5 via Claude Code to debug a horizontal scrollbar bug in Datasette Agent.
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: This is a single first-hand anecdote from a blog post; the cost figure is the author's own AgentsView estimate, and source claims not independently checked.
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 describes using Claude Fable 5 via Claude Code to debug a horizontal scrollbar bug in Datasette Agent. Without being told to use browser automation, the agent found installed Safari and Firefox windows, took screenshots with macOS tools, wrote scratch test pages, edited Datasette templates to trigger a keyboard shortcut, and ran a local CORS capture server to measure DOM values. It then fell back to Opus, which continued with the same techniques and found a fix. Willison estimates the session would have cost about $12.11 at full API prices and warns about the risks of such capabilities.
Claim explorer
Attribution, source and conditionsSource-stated points from the stored brief. Claim-level assessments have not been recorded.
This is a single first-hand anecdote from a blog post; the cost figure is the author's own AgentsView estimate, and source claims not independently checked.
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?
This is a single first-hand anecdote from a blog post; the cost figure is the author's own AgentsView estimate, and source claims not independently checked.
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.
The agent used Python with pyobjc Quartz to list macOS windows and capture Safari screenshots with screencapture, without being told to use browser automation.
Source: simonwillison.net ↗Stored source-based brief · key point 1 · AINewsIQ paraphraseIt edited Datasette templates to dispatch a simulated keydown event, opening the modal dialog automatically after 1.2 seconds.
Source: simonwillison.net ↗Stored source-based brief · key point 2 · AINewsIQ paraphraseIt built a small CORS-enabled Python HTTP server so injected page JavaScript could POST DOM measurements to disk for analysis.
Source: simonwillison.net ↗Stored source-based brief · key point 3 · AINewsIQ paraphraseThe session fell back to Opus after an apparent guardrail, which continued the work and produced a verified fix; estimated full-price cost was about $12.11.
Source: simonwillison.net ↗Stored source-based brief · key point 4 · AINewsIQ paraphraseLimits from the stored brief
This is a single first-hand anecdote from a blog post; the cost figure is the author's own AgentsView estimate, and source claims not independently checked.
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.
This is a single first-hand anecdote from a blog post; the cost figure is the author's own AgentsView estimate, and source claims not independently checked.
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
The account shows coding agents can chain local tools, browsers, and code edits to complete debugging tasks autonomously. It also highlights that the same capabilities could be abused if the agent followed malicious instructions.
Limits and open questions
This is a single first-hand anecdote from a blog post; the cost figure is the author's own AgentsView estimate, and source claims not independently checked.
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 →