Massimo Cotrozzi
@MassimoCotrozzi
Followers
72
Following
67
Media
11
Statuses
1K
Joined December 2011
RT @coffinxp7: Finally, here’s the detailed article where I walk you through, step by step how to find this vulnerability in real bug bount….
infosecwriteups.com
Hackers Are Earning 💸$XX,000+ With This Secret Trick — Now It’s Your Turn
0
46
0
This. Reminds me when people say Google doesn’t work. An AI is as good as you are. If you’re not satisfied, look at the mirror.
Unsolicited reminder: the info you obtain from chatgpt is only as good as the skills of the person on the prompt to know how to think critically and know when it's hallucinating.
0
0
1
I would argue that LoT is more of a symptom-targeted intervention than a cure for the real issue. The core problem, which originates from their architecture and training paradigm, is that LLMs rely on statistical patterns in language data rather than a robust reasoning framework.
This paper presents Language-of-Thoughts (LoT) prompting. It directs models to explicitly process all relevant input, mitigating bias and improving reasoning performance. Methods 🔧:. → Language-of-Thoughts uses "observe, expand, echo" prompt instructions. → "Echo" reduces
0
0
0
RT @PrajwalTomar_: Bolt built this entire landing page from a single prompt 🤯. No Figma. No coding. Just one prompt and a clear flow. Want….
0
120
0
LLM aided coding. Enhancing existing skills at the nth power. If your skills are zero, the result will always be zero. Thanks @simonw.
simonwillison.net
Online discussions about using Large Language Models to help write code inevitably produce comments from developers who’s experiences have been disappointing. They often ask what they’re doing...
0
0
0
That’s because AI is programmed to respond to questions and questions are made by the very same people who don’t have all the knowledge. When we will have self questioning AI then they will go ahead and invent.
Rare that I hear something new in the AI debate, but this is one such case.
0
0
0
If the data owner, having done a proper risk analysis, accepts the risk of giving people access, it’s BAU. Then again, who’s the data owner, how do you control access, etc… is also BAU. It’s a breach when it is NOT authorised.
I’ve had a few people flag this with me as a “data breach”. It’s not, it’s authorised access. Not liking that authorisation does not make it a data breach. If one of these guys then accidentally leaks it all over the place to unauthorised parties, *then* it’s a data breach!.
0
0
0
RT @SamuelXeus: I just finished a detailed market research❗️ Here's what I found👇🏽. • Everybody is picking up $BOTIFY 🔥.If you understood t….
0
88
0
RT @gabeElbling: Amazing graphical representation of a neural net, never seen anything like it.
0
4K
0
Why do security engineers know more about applications, servers, networks, ….
Because we were forced to learn about them in order to prove its not the network 😭.
0
0
0
so this is declassified technology. where's super secret military stuff now? :).
I went to a DARPA robotics challenge in 2015 & the robots could barely walk in a line without falling over. And now.
0
0
0
A new era for privacy – GDPR 6 months on . What’s your key priority when it comes to #GDPR? @Deloitte explore whether attitudes towards privacy have changed since GDPR came into force 6 months ago.
lnkd.in
This link will take you to a page that’s not on LinkedIn
0
0
0
Very nice way to see the world development. Would be interesting to link “slowdowns” to socio/economic/political/military events.
0
0
0
“Deloitte being positioned first in security consulting services worldwide for six years running speaks volumes about our practice,” says Nick L. Galletto, Global Cyber Risk Services leader. ”From the board to the c-suite, organi…
0
0
0
Not sure if amazing or terrifying. BrainNet: A Multi-Person Brain-to-Brain Interface for.Direct Collaboration Between Brains /
0
0
0