devtooligan @devtooligan

Building @zerocool_ai 🥶 CTO @round_ai_media 👁️ LSR @Spearbit 🧐 Resident @yAuditDAO 🤓 ETHSecurity Badge #51 @thedaofund 📛 Joined October 2020

Tweets

6K
Followers

10K
Following

1K
Likes

25K

Round AI @Round_AI_Media

23 hours ago

𝗧𝗵𝗲 𝗜𝗻𝘁𝗲𝗿𝘀𝘁𝗲𝗹𝗹𝗮𝗿 𝘁𝗿𝗮𝗶𝗹𝗲𝗿, 𝗯𝘂𝘁 𝗶𝗻𝘀𝘁𝗲𝗮𝗱 𝗶𝘁'𝘀 𝗮 𝗳𝗮𝗸𝗲 𝗮𝗱 𝗳𝗼𝗿 𝘁𝗵𝗲 𝗻𝗲𝘄 Tᴇꜱʟᴀ Rᴏᴀᴅꜱᴛᴇʀ. @elonmusk @Tesla

0 1 5 263 1

View Details

devtooligan @devtooligan

2 days ago

@leekt216

0 1 3 263 0

View Details

Georgios Konstantopoulos @gakonst

3 days ago

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

34 12 203 18K 61

View Details

devtooligan @devtooligan

3 days ago

@BowTiedDravee @yAuditDAO great talk king!

0 0 3 131 0

View Details

devtooligan @devtooligan

4 days ago

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

313 209 5K 481K 5K

1 0 7 697 2

View Details

Andrew Anderson @mochacortado

a week ago

@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.

3 3 26 1K 0

View Details

ncitron.eth @NoahCitron

2 weeks ago

me: implement this feature codex: done me: are there any bugs in this feature you just implemented? codex: what are you, a criminal?

1 3 37 2K 1

View Details

devtooligan @devtooligan

2 weeks ago

@josepchetrit haters will say this is ai

0 0 0 44 0

View Details

devtooligan @devtooligan

2 weeks ago

@hrkrshnn @p_misirov lfg

0 0 4 457 0

View Details

Sherwood @shcallaway

2 weeks ago

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!

375 78 3K 629K 2K

View Details

devtooligan @devtooligan

2 weeks ago

@Mudit__Gupta This started like a clickbait announcement of your new durable agent framework cloud services

0 0 10 272 0

View Details

devtooligan @devtooligan

2 weeks ago

@JubeAIKibagamAI just rewatched this -- so good

0 0 0 25 0

View Details

devtooligan @devtooligan

2 weeks ago

@DevDacian @cyfrin congrats!! well-deserved, they're lucky to have you.

0 0 1 85 0

View Details

devtooligan @devtooligan

3 weeks ago

@Simo1028 🤝

0 0 0 19 0

View Details

devtooligan @devtooligan

3 weeks ago

this was a fun weekend project! feels like there's some potential there for use by protocol teams for monitoring on-chain activity

Zero Cool @ZeroCool_AI

3 weeks ago

x.com/i/article/2104…

6 3 49 7K 48

2 0 21 3K 14

View Details

devtooligan @devtooligan

3 weeks ago

Thanks Jack. 20 of the blocks had "false positives" although we didn't research those 20 too much, we just assumed they are benign > Or do you have a sense for how low false positives would need to be to make this a no-brainer for protocol teams The results seem promising to me, although there's still plenty of room for optimization, calibrating the questions, etc. Adding protocol context such as invariants and permissions, and limiting alerts to activity involving the protocol’s addresses, would reduce the noise further. You could also add an agentic triage layer to investigate flagged transactions.

1 0 6 149 0

View Details

devtooligan @devtooligan

3 weeks ago

@c4lvin nice! I've got like 3 half-written trading bots lol

0 0 1 20 0

View Details

devtooligan @devtooligan

3 weeks ago

@blockrotator @aviggiano it's a bleeding edge agentic swarm intelligent anime reference to the "yAcademy fellowships" that i believe were originally inspired by your suggestion 5 years ago