AI security research at attacks.ai · making things with AI since VQGAN, breaking them since before it was a job
Joined October 2021
- Tweets 15,553
- Following 1,288
- Followers 4,590
- Likes 20,652
2,368 Photos and videos
Who's making this locally ?
Jun 13
Introducing the Fusion API, the smartest compound model in the market.
Fusion achieves Fable-level intelligence at half the price.
How it works 👇
131
Good thing ! It also solve many security problem
Jun 13
Introducing the Fusion API, the smartest compound model in the market.
Fusion achieves Fable-level intelligence at half the price.
How it works 👇
153
Takyon∞ retweeted
Jun 13
Introducing the Fusion API, the smartest compound model in the market.
Fusion achieves Fable-level intelligence at half the price.
How it works 👇
688
1,750
14,736
5,883,699
Takyon∞ retweeted
Jun 13
IMPORTANT UPDATE:
18
144
1,996
83,656
Well... Check my blog post at blog.attacks.ai
Jun 13
The US government, citing national security authorities, has issued an export control directive to suspend all access to Fable 5 and Mythos 5 by any foreign national, whether inside or outside the United States, including foreign national Anthropic employees.
The net effect of this order is that we must abruptly disable Fable 5 and Mythos 5 for all our customers to ensure compliance.
Access to all other Claude models is not affected.
We apologize for this disruption to our customers. We believe this is a misunderstanding and are working to restore access as soon as possible.
Read our full statement: anthropic.com/news/fable-myt…
1
77
Got ~160 click for 10.67€
Jun 12
I tried this so you don’t have to.
At the end, I got:
- 10,000 impressions
- $600 spent
- 0-400 clicks (tracking isn’t very good)
- 0 conversions
I’m probably not going to spend more on this platform at the current stage because it’s a very heavily inflated CPM and the tracking is quite limited.
I think it’s a very interesting idea and I hope to continue seeing it evolve!
1
64
I think this N-day research is potentially the biggest story of AI, vulnerability finding, and exploit development.
red.anthropic.com/2026/n-day…
1/6
8
105
613
48,057
Hacking Google with A.I. for $500,000
brutecat.com/r/hacking-googl…
59
501
2,464
325,143
Got a x190 speed up boost with F5 on my scanner for sweep and dispatch and I got a speed from 140 seconds to 246 ms on deep path detection with the new changes
I can scan a codebase and get results in less than 5 minutes now if I use anthropic API. Now I'll improve my local path
Little blog post about something I built, I've managed to find vulns in many repo such as @NousResearch or @ComfyUI (And many others) by using this process and my good old 3090 24GB and an open source model.
Here you go : We got glasswing at home
blog.attacks.ai/we-got-glass…
2
2
106
Rememeber that you can use caching at the API level and a bunch of others things to /10 your API costs...
my experience so far: topped up claude with $50, fable ate through it in 10 mins and delivered nothing. anthropic has gotten much closer than other labs to building a slot machine.
70