@pr0cf51

Generating AI slop @QED_Audit ex. @TeamAtlanta24, @osec_io, @georgiatech

 /proc
Joined April 2019
  • Tweets1.8K
  • Following877
  • Followers1.9K
29Media
Pinned Tweet
pr0cf5
@pr0cf51Jun 5
claude is chinamaxxing
1
1
27
4,636
Can’t believe SF rent is more expensive than colo need to reincarnate as B300 SXM
4
347
I am now a competitive bitch.
3
288
Pasta à la vodka maxxing
1
171
Founder led sales?
the tiny corp
@__tinygrad__Oct 7
Compilers for Machine Learning Carnegie Mellon University Spring 2027 Semester In person, Pittsburgh 10-411/711, MWF 10-10:50 139-seat classroom reserved Lectures not posted online Don't miss registration!
1
2
752
pr0cf5 retweeted
s1r1us
@S1r1u5_Sep 18
On July 25, we hacked OpenAI. Two bugs let us take over ChatGPT/Codex accounts of OpenAI employees (+some unaffiliated users) and reach connected services: Outlook, Slack, GitHub, etc. We proved it with a PR in OpenAI’s internal codebase . It took us <72h. 🧵
353
1,388
548
11,825
2,820,521
Poor Poseidon...
QED Audit
@QED_AuditSep 17
1/ We found a full collision for the Poseidon1 Collision Prize instance and submitted it on July 31. Two different messages, identical 16-word output after all 28 rounds, verified on the Initiative's official implementation. The technical breakdown and full story ⬇️
7
1,169
Dig is the king of all slop bowls. Period.
1
1
526
pr0cf5 retweeted
Xion@0x10nSep 6
During my time at @QED_Audit I circled back and took another quick look at browser/JSE vulnerability research. AI agents flying high, seemingly finding & exploiting bugs everywhere, and there's this: a **constant integer overflow** in V8, alive for over 3.5 years. (1/5)
QED Audit
@QED_AuditSep 6
Replying to @QED_Audit
@QED_Audit found CVE-2026-19174, an integer overflow in V8 that gives you arbitrary code execution in Chrome. The bug is one line of constant arithmetic. It survived 3.5 years of fuzzing, manual audit, and LLM-driven review. (1/n)
2
25
2
147
17,200
pr0cf5 retweeted
QED Audit
@QED_AuditSep 6
@QED_Audit found CVE-2026-19174, an integer overflow in V8 that gives you arbitrary code execution in Chrome. The bug is one line of constant arithmetic. It survived 3.5 years of fuzzing, manual audit, and LLM-driven review. (1/n)
3
14
2
111
26,986
I want to do slack huddles with my coding agent does this exist?
1
1
3
540
In some ways, LLM pessimists are even more bullish on AI than the slop startup bros. It's just buried so deep in their unconscious mind that it materializes as denial and complete logical fallacies like this.
LiveOverflow 🔴 hextree.io
@LiveOverflowAug 21
Some people saw the "count Rs in strawberry" example and dismissed the capabilities. But I saw it and thought I cannot spell strawberry either, and I still can be productive.
2
537
Some people saw the "count Rs in strawberry" example and dismissed the capabilities. But I saw it and thought I cannot spell strawberry either, and I still can be productive.
4
6
1
95
9,644
Anyone can write a patch-gap exploit in a few minutes using Claude Code. Uncoordinated patch releases are criminal.
KiiChain
@KiiChainioAug 24

KiiChain Security Incident

Article · @KiiChainio
3
641
Recently I uploaded two new videos! But I have been pretty inactive the past 2-3 years and a lot has happened. Let me share an update about my life, AI and the future of LiveOverflow.
46
36
4
631
51,758
pr0cf5 retweeted
ainta
@kaizero_aintaAug 15
LLM-driven security isn't just about finding implementation bugs in code. it's breaking cryptographic protocols at the logic level. AI agents are necessary to secure every layer of a project, from theoretical foundations to the frontend.
QED Audit
@QED_AuditAug 15
We found a key-recovery attack on TALUS v4, a PQ threshold signature scheme in NIST’s Threshold Call, using @QED_Audit’s bug finder. Huge thanks to the authors for the quick response and fix in v5. 📄 Attack: eprint.iacr.org/2026/1668 🛠️ TALUS v5: arxiv.org/abs/2603.22109v5
2
15
1,416
Load more