Dan Tehrani

942 posts

Dan Tehrani banner
Dan Tehrani

Dan Tehrani

@dan_tehrani

security researcher prev co-founder @personae_labs, @Mikawaya9

SF/Tokyo Beigetreten Mart 2020
502 Folgt797 Follower
Angehefteter Tweet
Dan Tehrani
Dan Tehrani@dan_tehrani·
I'll be in SF from Aug 21st for about a month Let's grab coffee if you're there!
English
147
1
221
2.6K
Dan Tehrani retweetet
Davide
Davide@0xseiryu·
1/ The Ethereum protocol prices congestion correctly. Wallets don’t. • 25 days of data. • ~185k observations. • 3 wallets. One clear mismatch ↓
English
13
20
91
10.2K
Dan Tehrani retweetet
Davide
Davide@0xseiryu·
1/ “Who is the top JIT liquidity searcher in Ethereum?” → a question answer by our paper w/ @0xAlphaist (accepted to a FC workshop: fc26.ifca.ai/defi/) We mapped JIT activity in Uniswap v3 and linked searchers <-> builders from Jan 2024 to Sept 2025. One name dominates: jared accounts for >50% of all observed public JIT execution.
Davide tweet media
English
12
15
81
6.8K
Dan Loewenherz
Dan Loewenherz@dwlz·
Latest version of Prettier is broken on Cursor. This GitHub issue has the fix (just force downgrade to v11.0.2): #issuecomment-3761391774" target="_blank" rel="nofollow noopener">github.com/prettier/prett…
Dan Loewenherz tweet media
English
2
0
4
1.5K
Dan Tehrani
Dan Tehrani@dan_tehrani·
Our AI auditing system has found a confirmed Medium severity bug on a bug bounty! AI auditors will just keep getting better from here
Dan Tehrani tweet media
English
11
0
25
341
Dan Tehrani
Dan Tehrani@dan_tehrani·
Our LLM auditor has identified a Medium severity vulnerability in a bug bounty as well!! More updates soon x.com/dan_tehrani/st…
Dan Tehrani tweet media
Dan Tehrani@dan_tehrani

I’ve been building an AI agent for finding vulnerabilities in smart contracts. It has found several confirmed bugs in audit contests, including code4rena contests which codebases are pre-scanned with @zellic_io's v12 LLM auditor. Tuning the prompts of an AI agent to find vulnerabilities requires thousands of dollars in inference cost for the best reasoning models, and careful try-and-error prompt tuning across many real-world vulnerabilities. It still falls short compared to the best human auditors, but with the prompts and the base models improving, the gap will only get smaller.

English
3
0
15
251
Dan Tehrani
Dan Tehrani@dan_tehrani·
We're offering *free* audits with our LLM auditor. Please DM if you want to get an audit report now. Our system usually costs hundreds of dollars per audit for LLM inference. It has been competing in audit contests and has identified variaous high/medium severity vulnerabilities. We currently provide *free* audits for projects in exchange for permission to write a case study of auditing your project. Please DM if you are interested:) x.com/dan_tehrani/st…
Dan Tehrani tweet mediaDan Tehrani tweet media
English
1
0
6
299
Dan Tehrani
Dan Tehrani@dan_tehrani·
I’ve been building an AI agent for finding vulnerabilities in smart contracts. It has found several confirmed bugs in audit contests, including code4rena contests which codebases are pre-scanned with @zellic_io's v12 LLM auditor. Tuning the prompts of an AI agent to find vulnerabilities requires thousands of dollars in inference cost for the best reasoning models, and careful try-and-error prompt tuning across many real-world vulnerabilities. It still falls short compared to the best human auditors, but with the prompts and the base models improving, the gap will only get smaller.
Dan Tehrani tweet mediaDan Tehrani tweet mediaDan Tehrani tweet media
English
2
1
9
643
Dan Tehrani
Dan Tehrani@dan_tehrani·
In the last few months, I’ve been focusing on building an LLM-based smart contract auditing system with the question: Can an AI auditing system become more reliable than human auditors? I see a lot of sentiment that discards AI auditing. So I wanted to assess what AI actually can and cannot do in finding vulnerabilities. Here are all my learnings (post link in thread) With today’s models, LLMs aren’t capable of finding all vulnerabilities expert humans can find with just a few prompts. But with the base model improving and further research in promoting, it’s plausible that LLMs will become more reliable than humans. Further research is required, but as millions of dollars are at stake, we need to keep pushing the frontier of LLM auditing faster than the blackhats do.
English
25
0
32
421
Dan Tehrani
Dan Tehrani@dan_tehrani·
I need the new AirPods for the better noise cancellation
English
42
1
66
979
Dan Tehrani
Dan Tehrani@dan_tehrani·
Sent 30+ DMs to users who haven't come back to my product after the first use. Really want to understand how to make one want to come back and use it again.
English
15
0
31
699
Zazzy
Zazzy@zazzygfx·
Good morning ✨ Say it back
English
14
1
29
978
Praveen Kumar
Praveen Kumar@PraveenInPublic·
When you’re overwhelmed, break things down into smaller chunks and mindlessly execute it.
English
2
0
4
94
Marcus Enochs
Marcus Enochs@marcus_enochs·
Is Codex CLI better, worse, or equal to Claude Code?
English
1
0
0
110
Dan Tehrani
Dan Tehrani@dan_tehrani·
@robert_shaw don't know why but I have an urge not to click it whenever I see ✨
English
0
0
0
13
Robert Shaw 𝕏
Robert Shaw 𝕏@robert_shaw·
I found that there is still no icon that directly represents an AI Agent. Do we really still need to use ✨?
English
3
0
4
567
harish.rs
harish.rs@Harish_521·
Drop your best project below i ll rate it
English
129
3
172
21K
Jon Morehouse
Jon Morehouse@nuonjon·
What did you ship today?
English
3
0
2
252
Lars
Lars@larsbuilds·
What did you ship this weekend?
English
55
1
53
3.8K
Faizan Ali
Faizan Ali@devfaizanali·
So, what did you ship over the weekend?
English
2
1
2
195
Consulted Graphs
Consulted Graphs@consulted_graph·
What did you ship this week anon?
English
10
1
26
1K