Pasero

• Pasero 8 Mar 2024 19:38 UTC

  6 points

  6

  in reply to: Shmi’s comment on: Claude 3 claims it’s con­scious, doesn’t want to die or be modified

  Consciousness might not matter for alignment, but it certainly matters for moral patienthood.

• Pasero 26 Jul 2023 23:44 UTC

  1 point

  0

  on: Llama We Do­ing This Again?

  Presumably many people are already hard at work trying to undo what safety precautions were instilled into Llama-2, and to use various techniques to have it do everything you are imagining not wanting it to do

  There are now easily available “uncensored” versions of Llama-2. I imagine the high false refusal rate is going to increase the use of these among non-malicious users. It seems highly likely that, in the context of open source LLMs, overly strict safety measures could actually decrease overall safety.

• Pasero 28 Mar 2023 1:18 UTC

  2 points

  0

  on: GPT-4 Plugs In

  One last thing I didn’t consider at all until I saw it is that you can use the plug-ins with other LLMs? As in you can do it with Claude or Llama (code link for Claude, discussion for Llama)

  
  A growing number of open source tools to fine-tune LLaMA and integrate LLMs with other software make this an increasingly viable option.

• Pasero 10 Sep 2021 21:30 UTC

  1 point

  in reply to: Quintin Pope’s comment on: How do you de­cide when to change N95/​FFP-2 masks?

  I’d recommend using a mask with an exhalation valve, if you can.

  Excellent write-up. Though, I think it’s important to note that, if unfiltered, exhalation values can potentially spread disease.

• Pasero 7 Sep 2021 23:26 UTC

  2 points

  on: All Pos­si­ble Views About Hu­man­ity’s Fu­ture Are Wild

  I found the last bit very compelling. David Deutsch’s The Beginning of Infinity is the only place where I have seen a similar sort of anthropocentrism regarding the future discussed. Could anyone point me in the right direction to more on the topic (or keywords I should be searching for)?