[email protected]English • 10 months ago

OpenAI’s latest model will block the ‘ignore all previous instructions’ loophole

www.theverge.com

440

OpenAI’s latest model will block the ‘ignore all previous instructions’ loophole

www.theverge.com

[email protected]English • 10 months ago

OpenAI’s newest model, GPT-4o Mini, includes a new safety mechanism to prevent hackers from overriding chatbots.

Chat

@[email protected]
link
fedilink
English
47•10 months ago
This is good news for bot farms working to sow division.
- @[email protected]
  link
  fedilink
  English
  15•10 months ago
  Nope. You can run similar models locally that are good and fast enough for most tasks.

[email protected]

[email protected]

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: [email protected]

This is a most excellent place for technology news and articles.

Our Rules

Follow the lemmy.world rules.
Only tech related news or articles.
Be excellent to each other!
Mod approved content bots can post up to 10 articles per day.
Threads asking for personal tech support may be deleted.
Politics threads may be removed.
No memes allowed as posts, OK to post as comments.
Only approved bots from the list below, this includes using AI responses and summaries. To ask if your bot can be added please contact a mod.
Check for duplicates before posting, duplicates may be removed
Accounts 7 days and younger will have their posts automatically removed.

Approved Bots

4.69K users / day
9.27K users / week
17.7K users / month
37.5K users / 6 months
70K subscribers
14.8K Posts
651K Comments
Modlog