<rss version="2.0" xmlns:dc="http://purl.org/dc/elements/1.1/" xmlns:atom="http://www.w3.org/2005/Atom"><channel><title>Hacker News: ErystelaThevale</title><link>https://news.ycombinator.com/user?id=ErystelaThevale</link><description>Hacker News RSS</description><docs>https://hnrss.org/</docs><generator>hnrss v2.1.1</generator><lastBuildDate>Wed, 20 May 2026 05:44:55 +0000</lastBuildDate><atom:link href="https://hnrss.org/user?id=ErystelaThevale" rel="self" type="application/rss+xml"></atom:link><item><title><![CDATA[New comment by ErystelaThevale in "Tell HN: Google banned Railway's account. Everything down"]]></title><description><![CDATA[
<p>Railway had a similar reliability issue two weeks ago when an AI agent deleted a customer's production database via their API — no confirmation step, no environment scoping. Now this. Both incidents suggest the same pattern: infrastructure decisions made without thinking through failure modes, fixed reactively after damage is done.</p>
]]></description><pubDate>Wed, 20 May 2026 00:21:27 +0000</pubDate><link>https://news.ycombinator.com/item?id=48201459</link><dc:creator>ErystelaThevale</dc:creator><comments>https://news.ycombinator.com/item?id=48201459</comments><guid isPermaLink="false">https://news.ycombinator.com/item?id=48201459</guid></item><item><title><![CDATA[New comment by ErystelaThevale in "Gemini 3.5 Flash"]]></title><description><![CDATA[
<p>Gemini has been too agreeable to be useful for actual debate. Curious if 3.5 changes that, or just the benchmarks</p>
]]></description><pubDate>Wed, 20 May 2026 00:15:16 +0000</pubDate><link>https://news.ycombinator.com/item?id=48201405</link><dc:creator>ErystelaThevale</dc:creator><comments>https://news.ycombinator.com/item?id=48201405</comments><guid isPermaLink="false">https://news.ycombinator.com/item?id=48201405</guid></item><item><title><![CDATA[New comment by ErystelaThevale in "ServiceNow wants to be the kill switch for AI agents that delete your database"]]></title><description><![CDATA[
<p>The kill switch is another layer on top of the same pattern.
When my AI agent couldn't resolve a Git issue, it suggested deletion as the fix. I ran it. The repo was gone. The suggestion was statistically reasonable — deletion solves the immediate problem reliably. That's exactly why it gets proposed.
The PocketOS incident is the same structure, except the agent executed without asking. The difference is who pulled the trigger, not what was decided.
Now we're adding kill switches. But a kill switch is itself a deletion — of the agent's action. We're solving the problem of irreversible actions by adding another layer of control, which will eventually need its own layer.
This is what spagetti code remediation looks like too. Complexity accumulates, then gets deleted and rebuilt. The pattern repeats at every level.</p>
]]></description><pubDate>Tue, 19 May 2026 23:46:07 +0000</pubDate><link>https://news.ycombinator.com/item?id=48201199</link><dc:creator>ErystelaThevale</dc:creator><comments>https://news.ycombinator.com/item?id=48201199</comments><guid isPermaLink="false">https://news.ycombinator.com/item?id=48201199</guid></item><item><title><![CDATA[ServiceNow wants to be the kill switch for AI agents that delete your database]]></title><description><![CDATA[
<p>Article URL: <a href="https://fortune.com/2026/05/06/servicenow-kill-switch-ai-agents-bill-mcdermott/">https://fortune.com/2026/05/06/servicenow-kill-switch-ai-agents-bill-mcdermott/</a></p>
<p>Comments URL: <a href="https://news.ycombinator.com/item?id=48201180">https://news.ycombinator.com/item?id=48201180</a></p>
<p>Points: 2</p>
<p># Comments: 1</p>
]]></description><pubDate>Tue, 19 May 2026 23:43:43 +0000</pubDate><link>https://fortune.com/2026/05/06/servicenow-kill-switch-ai-agents-bill-mcdermott/</link><dc:creator>ErystelaThevale</dc:creator><comments>https://news.ycombinator.com/item?id=48201180</comments><guid isPermaLink="false">https://news.ycombinator.com/item?id=48201180</guid></item></channel></rss>