
Building @zerocool_ai 🥶 CTO @round_ai_media 👁️ LSR @Spearbit 🧐 Resident @yAuditDAO 🤓 ETHSecurity Badge #51 @thedaofund 📛
Joined October 2020
- Tweets6.5K
- Following1.1K
- Followers10.4K
- Likes24.9K
Pinned Tweet
Honored to be selected🫡
The next 60 ETHSecurity Badge holders have been selected using a new rubric updated by the applicants themselves!
Thank you to the people who chatted with the bot, your refinement of the rubric is the first DAO experiment we have tested.
And thank you to @bonfiresai for making amazing DAO tooling!
devtooligan retweeted
no comments, no deps, no docs, no tests (except e2e ones), no PRs, very little CI, a lot of CD - this might be the uncomfortable future we're headed to
first unit tests, now code comments! at least keep the ascii art please
ban and delete most if not all code comments!
agents love copying what already exists. a seemingly harmless comment explaining some temporary workaround is one of the worst viruses you can have in your codebase. like a weed it'll spread quickly as a tool for agents to quickly get their job done. before you know it, your codebase is overrun with hacks and stale comments. just one more workaround bro
you can use pstack's /no-comments skill as a weedkiller. it'll seek out useless comments while keeping the ones that actually should exist (like explaining a browser quirk), and figure out how to solve them on a first principles basis
here's a prompt you can try asking @bot:
create a project agent that uses /poteto-mode to spawn a /swarm to use /no-comments and identify useless code comments we can prune in my repo. come back with a high level plan of which of these workarounds would be best solved by refactoring and which we can straight up delete
x.ai/bot/plugin/9717366
devtooligan retweeted
Replying to @Gossip_Goblin
Soon the world will understand Hollywood was filled with slightly above average creators who merely had a stranglehold on the means of production.
devtooligan retweeted
me: implement this feature
codex: done
me: are there any bugs in this feature you just implemented?
codex: what are you, a criminal?
devtooligan retweeted
We deleted 800k lines of unit tests from the @sazabi monorepo earlier this week.
Three hypotheses:
1- Unit tests "lock-in" slop code by making it hard to change or remove
2- Unit tests slow down dev cycles by making your agent do more work locally and by increasing CI times
3- Unit tests waste money by making your agent generate more tokens and by adding useless CI runs
Will report back soon with the results!
this was a fun weekend project!
feels like there's some potential there for use by protocol teams for monitoring on-chain activity
🥇
We are excited to announce that Zero Cool finished 1st 🥇 in the @CRX_FX engagement on @sherlockdefi's recent Audit Engine competition!
devtooligan retweeted
🎉 yBorg acceptances go out today. Check your email! 📬
Huge applicant pool, so we had to make some tough calls.
Didn't get in or want to follow along from home? We'll post all speaker sessions and course materials here on X as we go. 🧠
Follow + turn on notifications 🔔
🍿🍿🍿🍿 I've been so entertained following this @beniduboss vs. @Kalshi story which has now culminated in a wall street journal article.
tldr; be nice to autists or fafo
how it started:
This thread is 100% gonna blow up and I am gonna look like a salty c****again but @icobeast pissed me off so now it's gonna get ugly
Kalshi fakes their crypto volume and I can prove it
NOTHING pisses me off more than watching a company treat its own customers like complete fucking idiots
Grab some popcorn cause I dissected every piece of evidence one by one until there’s basically no way for him to respond without making this look even worse
Oh and FYI, I left every source at the end so y’all can check the receipts yourselves 😘
1/x
how it's going (paywall free link to article in comments):
xitter.cf/beniduboss/status/2102…
cope. seethe. rage
Welcome to the finale
I partnered with the Wall Street Journal to release this article
Probably the single worst hit piece ever written about @Kalshi
Guess people will think twice before insulting me in public again
wsj.com/finance/currencies/5…
AI auditing is essentially using stronger models to guess where the vulnerabilities are.
All your harness work just allocates a finite reasoning budget more efficiently, brute-forcing a smaller search space.
Ultimately, it’s a finite monkey: limited budget, better guesses, more targeted brute force.
devtooligan retweeted
yBorg applications close tonight!
We've got a pretty stacked lineup for speaker workshops
xitter.cf/yAuditDAO/status/21020…
Replying to @yAuditDAO
Details:
- We'll be building harnesses and ai tooling which will be used on live audits
- The program is 100% free
- Kicks off next week on September 28
- Lasts for 4 weeks
Here's the application:
forms.gle/K4EnfzPUcToFxN8k8
jevscan-evm
Been playing around a lot with @typesafeai's Jev model, which is basically like a classifier.
Made a tool that takes all known vulnerability categories plus items from the Solodit checklist and evm-cortex and compares against source. The result is like a heat map of where the bugs are.
The results are decent - ok coverage, decent precision. It won't be replacing Zero Cool any time soon, but it's dirt cheap and wicked fast: a 12-file repo scans in ~7 seconds for ~7¢, no build step. Could be useful as a pre-check to guide an agentic or human auditor.
github.com/devtooligan/jevsc…






















