RE: https://flipboard.com/@pcmag/pcmag-s-top-stories-enri7nshz/-/a-RY5fwHf_Qp2KuygO-hX2Tw%3Aa%3A1861800451-%2F0Here’s th...

RE: https://flipboard.com/@pcmag/pcmag-s-top-stories-enri7nshz/-/a-RY5fwHf_Qp2KuygO-hX2Tw%3Aa%3A1861800451-%2F0Here’s the thing: when you’ve got a system that produces output you have no direct control over, all you can do is try to build filters to catch harmful output, which only work as well as the various outputs that you can anticipate. There will always be edge-cases or scenarios you didn’t account for. And it’s already been demonstrated how easy it is to re-word/modify prompts to work around safeguards.#LLMs #AI #OnlineSafety

Read Original

Related

Mastodon discussion 17m ago

ヒトにとっての神、亜人にとっての神、そして中央にとっての神は違うのでしょうか【やじうまミニレビュー】スマホを16.7℃も冷却!カーメイトのMagSafe対応ハンディファンで快適に https://pc.watch.impress.co.jp...

ヒトにとっての神、亜人にとっての神、そして中央にとっての神は違うのでしょうか【やじうまミニレビュー】スマホを16.7℃も冷却!カーメイトのMagSafe対応ハンディファンで快適に https://pc.watch.impress.co.jp/docs/column/yajiuma-mini-review/2133608.html#Apple #LLM #ne...