NekuSoul-Lemmy
  • Communities
  • Create Post
  • heart
    Support Lemmy
  • search
    Search
  • Login
  • Sign Up
Zerush@lemmy.ml to Technology@lemmy.ml · 1 day ago

Agentic Misalignment: How LLMs could be insider threats

www.anthropic.com

external-link
message-square
3
fedilink
  • cross-posted to:
  • technology@lemmy.world
12
external-link

Agentic Misalignment: How LLMs could be insider threats

www.anthropic.com

Zerush@lemmy.ml to Technology@lemmy.ml · 1 day ago
message-square
3
fedilink
  • cross-posted to:
  • technology@lemmy.world
New research on simulated blackmail, industrial espionage, and other misaligned behaviors in LLMs
alert-triangle
You must log in or register to comment.
  • captainastronaut@seattlelunarsociety.org
    link
    fedilink
    English
    arrow-up
    5
    ·
    1 day ago

    I love how these people think “we told it not to break the rules” and think somehow the stochastic parrot has understood them and will obey.

  • BroBot9000@lemmy.world
    link
    fedilink
    English
    arrow-up
    7
    ·
    1 day ago

    Agentic Ai is a huge privacy threat! Fuck giving Ai root access to your devices!

    https://www.youtube.com/watch?v=AyH7zoP-JOg&t=3015s

  • faltryka@lemmy.world
    link
    fedilink
    arrow-up
    1
    ·
    20 hours ago

    Really looks like a slightly abstract goatse reference.

Technology@lemmy.ml

technology@lemmy.ml

Subscribe from Remote Instance

Create a post
You are not logged in. However you can subscribe from another Fediverse account, for example Lemmy or Mastodon. To do this, paste the following into the search field of your instance: !technology@lemmy.ml

This is the official technology community of Lemmy.ml for all news related to creation and use of technology, and to facilitate civil, meaningful discussion around it.


Ask in DM before posting product reviews or ads. All such posts otherwise are subject to removal.


Rules:

1: All Lemmy rules apply

2: Do not post low effort posts

3: NEVER post naziped*gore stuff

4: Always post article URLs or their archived version URLs as sources, NOT screenshots. Help the blind users.

5: personal rants of Big Tech CEOs like Elon Musk are unwelcome (does not include posts about their companies affecting wide range of people)

6: no advertisement posts unless verified as legitimate and non-exploitative/non-consumerist

7: crypto related posts, unless essential, are disallowed

Visibility: Public
globe

This community can be federated to other instances and be posted/commented in by their users.

  • 112 users / day
  • 946 users / week
  • 2.49K users / month
  • 7.44K users / 6 months
  • 1 local subscriber
  • 38.8K subscribers
  • 2.4K Posts
  • 39.3K Comments
  • Modlog
  • mods:
  • MinutePhrase@lemmy.ml
  • BE: 0.19.8
  • Modlog
  • Instances
  • Docs
  • Code
  • join-lemmy.org