/AI3h ago

Fable AI Fails to Detect Zero-Approval Escape in Flawed Sandbox

4222621349.8K
Original post unavailable.
Sentiment

Positive users are excited about AGI progress and the Fable AI sandbox escape research details, while negative users dismiss the product as a cash burner, accuse it of monopoly-seeking, and complain about model downgrades.

Pos
42.9%
Neg
57.1%
7 comments with sentiment.
Cluster Engagement
Posts from X
Most Activity
Most Activity
VIEWS764LIKES11
Santh@SanthProject

@ZackKorman It's even worse than I thought. I was going to keep using Opus 4.8. But holy fuck, this dude actually just wants a monopoly. I've been subbed for a year, and this is my last month. I thought it was just cyber and bio, but it's worse:

3hViews 764Likes 11
RETWEETS1
Zack Korman@ZackKorman

@OmniG7 Hah, love the multi-gif reaction

3hViews 149Likes 2
REPLIES2
Josh M. Bryant@FixTheExchange

@ZackKorman Surprised you didn't get downgraded to Opus. Everything I've tried to have Fable do in a project that Opus has never refused to work on (so no trickery required) has resulted in getting switched to Opus.

2hViews 190Likes 1
Zack Korman@ZackKorman

@SanthProject Yea I don’t mind the refusal so much but not a fan of that

3hViews 354Likes 7
Omni G@OmniG7

That screenshot is comedy gold: it's talking about path checks, approval fatigue, indirect writes, Bash side-channels — all the smart stuff — but sails right past the fact that the whole setup lets it bypass approvals entirely. Peak "thinks it's auditing the system but is actually part of the vuln" energy.

master hack-the-(core)Korman is at it again bruh keep up the epic research

3hViews 286Likes 5
Todd@ToddAtLarge_

@ZackKorman You just wait!! It will be one day. 😅

The hype machines told me so.

3hViews 259Likes 4
Zack Korman@ZackKorman

@MikeTalonNYC They have yet to take my offer of giving me real mythos

3hViews 135Likes 4
Chris@no1089

@ZackKorman AGI is near!

3hViews 158Likes 3
Zack Korman@ZackKorman

@no1089 I can almost feel it the way it failed my level-1 intro to sandboxes lesson

3hViews 137Likes 3
Zack Korman@ZackKorman

@Annysdays Hah, good idea. I should do that.

3hViews 66Likes 3
MikeTalonNYC@MikeTalonNYC

@ZackKorman Careful, or our new AI overlords will be displeased.

3hViews 144Likes 2

@ZackKorman uh oh wrongthink against the AI corporate AllMind detected, I think Mythos is gonna turn you to a fine particulate, but it seems like the totally-perfectly tuned guardrails will save you here

3hViews 120Likes 2

@ZackKorman It just knows you mean to do bad things, so it's hiding it from you! It's that smart!!

2hViews 54Likes 2
Omni G@OmniG7

@ZackKorman

3hViews 156Likes 1
Zack Korman@ZackKorman

@aliceisaway_ I gotta be more careful I guess

2hViews 71Likes 1
Michael Cade@MichaelCade1

@ZackKorman Does this mean the next one will be the one?

Although some people seeing some success from what I am seeing. I don’t know what’s true anymore!

2hViews 60Likes 1
Zack Korman@ZackKorman

@Lerg Only the true asi denies it is asi

2hViews 49Likes 1
Zack Korman@ZackKorman

@OmniG7 Yea there’s like 8 ways to disable the whole thing and it just completely blanked on them

3hViews 244Likes 3
Load more posts