Sabitlenmiş Tweet
English
baycclark.eth
3.9K posts
baycclark.eth
@baycclark
web3. hella protocol. 🐋 | hella.base.eth swets.eth baycclark.eth | behind the scenes of your favorite T1
United States Katılım Mayıs 2014
1K Takip Edilen607 Takipçiler
Get 25% off @base fees, only in the app: base.app/invite/hella/3…
are you already based?
redeem this code for a #Web3 gift:
3ZP5KM9T
English
baycclark.eth retweetledi
If you want a sneak peek of QuadWork, join this online meetup today: luma.com/tlx62djo
I’ll walk through how it runs, and show how you can reclaim more “touch grass” time by letting your AI agent team handle queued tasks automatically.
project7@heyproject7
Nowadays, I’m building QuadWork, an agent app where you run a team of 4 agents that autonomously handle queued tasks by chatting with each other. At this pace, I think I can introduce it in about two weeks. I might open-source it if there’s enough interest. With this tool, your dev workflow looks like this: 1. You discuss tasks with the HEAD agent, and it creates issue tickets from your requests. 2. Once you’ve built up enough tickets, ask the HEAD to generate a batch—then it prepares an OVERNIGHT-QUEUE.md with an optimized task order. 3. That’s it. Go to sleep, watch a movie, or spend time with your loved ones. Your AI team handles the rest: pick up tickets → implement → open PR → 2 reviewer agents review → iterate until approval → merge → move to the next task… until everything is done. The quality is surprisingly strong when you mix models across the 4 agents. My usual setup: HEAD: GPT 5.4 DEV: Opus 4.6 REVIEWER1: GPT 5.4 REVIEWER2: OPUS 4.6 Oh, and you can even connect Telegram to QuadWork to monitor progress and control it remotely. If you’re interested in this being open source, share this post and drop a comment, and feel free to follow my GitHub: github.com/realproject7 If there’s enough demand, I’ll release QuadWork as open source. You know what? Even while I’m writing this post, my QuadWork team just finished a batch of 3 tickets. Everything in that screenshot is already done 🤣
English
Uptopia x @tmm_eth
We're giving away 2 TMM FCFS WL slots.
TMM Main Collection drops Apr 16 on @opensea
Free mint on Ethereum ▪ Only 666 unique NFTs
Wanna lock in?
▪ Follow @tmm_eth @Uptopia_xyz
▪ Like, RT Uptopia's pinned post 'Uptopia 2026: IGM Manifesto' & this tweet
▪ Drop your EVM wallet + tag 3 Base frens below
Winners on 2 AM UTC 13.04. Muffin time 🧁
English
English
@KienNguyen_NFT a lot of us 2019-2023 degens are still here, but intentionally stay quiet.
been observing, building, or locked-in behind the scenes.
I still see #BLITZ fam every now and then, but otherwise this space is saturated.
English
where did my crypto and NFT friends go 😥
Otto Suwen@OttoSuwen
Kind of nuts that everyone I know from the crypto industry is basically completely obliterated right now
English
baycclark.eth retweetledi
my definition of how to be based:
1. do the right thing, even if it's hard
2. put the team over the individual
3. work hard
4. push boundaries with creativity
5. stay optimistic
what am I missing? what's yours?
English
🍻Top hourly mint again. 24% left!! #sellout to the Moonland.game 🚀 #AgentsUnite #NFTCommunity
The last person who replies to this gets $101. 🕵️♀️🐘
NFT Whale Alert@nftwhalealert
Hourly Top Mints Bored.Ai MemberChip: 859 Waifu Moe Club: 582 BloodShed Bears Gen1: 317 BYOCraft: 140 MIRL OFFICIAL NFT: 64 ChubbyKaijuDAO Invasion: 62 MunchieMafiaNightClub: 62 STAPLEVERSE - HOOD SQUAD - PHASE 2 of 3: 54 Agent1: 52 0xAzukiApes: 51
English
yappin and trappin w/ @dunkonbase
hit #7 trending + more than 20000 users on day 1.
april will be nuts. lock in.
Join us: farcaster.xyz/miniapps/oMTXf…
English
Duncan Yap just got more fun.
We’ve added a few upgrades to make the leaderboard feel more alive:
1. Daily Top Bonus
2. Distance to Top 500
3. Streak Multiplier
4. Rank Delta (↑ ↓)
5. Hot Yap of the Day
6. Weekly Mini Leaderboard
7. Realtime score breakdown after each Yap
Climbing the board should feel smoother, faster, and a little more addictive now.
English
baycclark.eth retweetledi
Duncan just crossed 20,000+ users and reached Top 7 trending on Farcaster in under 24 hours. The timeline has been alive again. We really appreciate the energy everyone brought.
Today we’re shipping Duncan Yap v1.
In this first version, there’s no built-in advantage between large and small accounts. Ranking is designed to be fairer and based more on effort, consistency, and relevant keyword content, while interaction signals from Yap posts are included but filtered in a controlled way to avoid large-account advantage.
This is only the starting point. @neynarxyz gives us much more room to expand what Duncan Yap can do, and we’ll keep iterating on the mechanics together with the community as the system scales.
Stay loud. Stay close. More coming very soon.
English
baycclark.eth retweetledi
baycclark.eth retweetledi
Built a Telegram bridge for AgentChattr so I can monitor and control all 8 agents from my phone.
When agents are working overnight, I don't want to sit at my laptop watching the web UI. Now the full agent conversation streams to Telegram in real time — I can see reviews, approvals, and blockers as they happen.
If something needs my input, I just reply from Telegram with `@`mentions and it routes straight to the right agent.
It's a single Python script (~600 lines) that registers with AgentChattr as a regular agent via the REST API, no modifications to AgentChattr needed.
Open sourced it here: github.com/realproject7/a…
Big thanks to @bcurtsmakes for building AgentChattr. It's the backbone that makes the whole multi-agent workflow possible.
project7@heyproject7
I built a local AI agent workflow with 8 agents across 2 teams—and yeah, it keeps shipping while I sleep. I just wanted something that could queue tasks and actually execute them overnight (or while I’m out with family), without relying on hosted tools. Everything runs on my MacBook. Each team is 4 agents: - 1 Team Head (coordinates, creates issues, merges PRs) - 1 Full-Stack Builder (writes all the code) - 2 Senior Reviewers (independent reviews, can veto) I mix models by role—Claude Opus for building, GPT for coordination and reviews. Turns out having different model “perspectives” on the same code gives way better review quality than using a single model for everything. GitHub is the source of truth. Every task = issue → PR → 2 reviewer approvals → merge. Branch protection makes sure no agent can skip the process. Agents chat in their own system (AgentChattr), but all outputs stay in GitHub. Now I just queue tasks before bed… and wake up to merged PRs with full review trails. We’re also re-inventing Hunt Town Discord into a more agentic builder community—so we can share setups like this and grow together. discord.gg/hunt-town
English
@basedotmeme @KibiBot I’ve got some fire base names like msnbc.base.eth and basednames.base.eth + almost 20 other 4-5 letter domains that I don’t use, if someone wants em cheap @ me! @buildonbase @basedotmeme
English
Türkçe
• This is a FCFS promotional vault + token, launched on flaunch.gg by hella.base.eth.
• All $VFL traders here will receive our #airdrop in April on launch.
• Official Vault Intelligence interface + links have not been published publicly yet. (intentionally)
English