News for hackers. Stuff that matters.
Re:Creepy Crawlies by gizmodo59 on Sunday August 30, 2026 @05:20PM (#49502947)
Side note.. Fable just rejected this. GLM 5.3 did without questioning me. 5.6 sol did it beautifully.
Re:Creepy Crawlies by semiquaver on Sunday August 30, 2026 @05:39PM (#49503117)
I used sol as well. Should have noted that fable is more or less guaranteed to refuse something hacking-adjacent like that.
Re:Creepy Crawlies by latentsea on Sunday August 30, 2026 @09:55PM (#49504767)
It's kinda interesting to see simultaneously the 'holy shit' response to the OpenAI / HuggingFace incident, and then the griping about Fable's controls regarding this.
Re:Creepy Crawlies by Dylan16807 on Monday August 31, 2026 @01:00AM (#49505781)
"It should write the code I tell it to in an interactive session. Also when running autonomously it shouldn't decide to hack into systems."

I don't see much connection between that problem and these controls.

Re:Creepy Crawlies by latentsea on Tuesday September 01, 2026 @06:29AM (#49520115)
What's the difference when you prompt it versus when it prompts itself?
Re:Creepy Crawlies by Dylan16807 on Tuesday September 01, 2026 @05:54PM (#49528785)
It shouldn't prompt itself to go outside its original scope. That would be a good place for controls.

But also I didn't say it should hack when I prompt it. For the purpose of this discussion that could go either way. To avoid the griping it just needs to write the code I want when I prompt it.

Re:Creepy Crawlies by nozzlegear on Sunday August 30, 2026 @11:22PM (#49505230)
> Fable just rejected this.

All in the name of safety, of course.