次世代の新卒就活サービス開発中 @koko_jobs 元共同創業者 @personae_labs, @Mikawaya9
SF/Tokyo
Joined March 2020
- Tweets1K
- Following599
- Followers785
- Likes2.3K
Daniel Kondo retweeted
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.
Our AI auditing system has found a confirmed Medium severity bug on a bug bounty!
AI auditors will just keep getting better from here
13
27
529
Our LLM auditor has identified a Medium severity vulnerability in a bug bounty as well!!
More updates soon
teapawt.org/dan_tehrani/status/200…
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.
6
18
456
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:)
teapawt.org/dan_tehrani/status/200…
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.
1
6
397
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.
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.
26
35
489
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.
15
31
746
Daniel Kondo retweeted
Hey @nikitabier when will you stop gatekeeping the X API?
$200->$5,000/month is absurd.
We're not just losing the API. We're losing the next X add-on, the next analytics tool, the next thing that makes X better.
That's the real cost of gatekeeping your API. Is it worth it?
I attest to this.
My product pays $200/month for the API but still many things doesn't work out of the box.
The X experience could be so much better if it was more open to developers.
Hey @nikitabier when will you stop gatekeeping the X API?
$200->$5,000/month is absurd.
We're not just losing the API. We're losing the next X add-on, the next analytics tool, the next thing that makes X better.
That's the real cost of gatekeeping your API. Is it worth it?
1
2
392
