vel ⋈ 🤌🧦

Circle was asleep while many millions of USDC was swapped via CCTP from Solana to Ethereum for hours from the 9 figure Drift hack during US hours. Value was moved and nothing was done yet again. Comes days after you froze 16+ business hot wallets incompetently which is still being slowly unfrozen. @circle @jerallaire @usdc are bad actors for the industry.

Our Codex dashboards are showing increased rate of users hitting rate limits and since we don't fully understand why I have made the cautious decision of resetting the usage limits for all plans. Enjoy. I also wanted to celebrate us finding a pocket of fraudulent accounts that we banned and have helped us regain some compute. The fight against abuse never stops, but it's important to mark the moment and make it a little shared victory.

@zuri_nft with the rise of personalized tooling, & customized agents (cowork, openclaw, hermes, etc) the ability to create your own orchestration MCP is tangible. The question becomes what service will provide these at a larger enterprise orchestration layer

@Velcrafting Who owns the orchestration layer?

With MCP being the USB-C of agentic coding, orchestration becomes the relevant factor. min-maxing your costs by leveraging multiple planes of Ai.

We’ve seen Claude Code users bring in Codex for code review and use GPT-5.4 for more complex tasks, so we thought: why not make that easier? Today we’re open sourcing a plugin for it! You can call Codex from Claude Code with your ChatGPT subscription. We love an open ecosystem!

Favorite video yet is Dan Hurley's mom after The Shot: "HOLY FUCKING SHIT!!!"

@camolNFT That, daily sunlight and drinking a lot of water make a world of difference

biggest life hack is just getting 8 hours of sleep every night

@MiniMax_AI Nice, no changes needed on my end, plan just upgrades. Great update

Introducing the MiniMax Token Plan: First All-Modality API Subscription Flat-rate API access to MiniMax's leading text, speech, music, video, and image models. Stop juggling multiple unpredictable bills for different modalities. One key. One predictable bill. All modalities.

the biggest onboarding issue with openclaw right now is that most people get stuck before they even run their first agent. especially on discord, which is frustrating because discord is genuinely one of the best platforms for running a swarm. and to be fair it is complicated if you have never used discord before or if you are not technical enough to get through the setup. which creates a huge gap.. on one side you have people experimenting with every feature and literally applying everything on their swarm, on the other side you have people who cannot even get a single agent running. been building with my mate @hsoumix a solution where you can literally install openclaw on whatever infrastructure you want and have your swarm running without fighting the setup. starting with discord first and expanding to other platforms.. telegram, slack.. etc and it goes way beyond just getting openclaw running.. we are talking memory, built-in features, the full experience. not just a setup wizard.. waitlist is open and we are locking in something for the early ones that will not be available later. waitlist.secondmate.io

@Zeneca i agree, i have been using my openclaw instances for diverse research projects + providing that context as an md document repo. Then codex + claude cowork desktop apps for individual executions based on task. Until the first agent consistent, there is no value in duplication.

I'm convinced if you want to maximize productivity, you shouldn't be using openclaw or hermes - they take so much time bug fixing that you're better off just using claude code/codex directly there's maybe 1% of people who are the exception to this

@camolNFT thank you wise Camol. this is thinking in 3D

@Velcrafting If their mascot is a tiger, I calculated it based on a REAL tiger. I believe the entire alumni of Texas A&M could beat a Hurricane.

March Madness bracket, based off of which teams mascot would win in a fight:

great tool, needed this - seeing how much i would've spent in API costs is a great looking glass. Last 30 days: 2B tokens ~ $590 - Including heavy utilization for hackathon instead cost me $100: - $20 (GPT Plus subscription) - 2 $40 credit packs. Much cheaper than API

@Ledger It back

gm, say it back

@fipcrypto I have not been able to hit my Minimax coding limits, at all ( @MiniMax_AI ) ..And it works very well with agentic flow. I have the $20/ month plan, but have not felt limitations.

My GLM coding plan was wiped out in 4 days, with most tokens burnt on troubleshooting my OpenClaw setup. So I bought the Alibaba Coding plan for $3.27 (first month only) to give me more tokens for the week. Now with everything set up, the next goal is optimising token usage.

@Zeneca Clean dashboard, and clean execution. GG

Another good day 104 bets total now, 19.85% yield (P&L / money bet) Happy days

@camolNFT I programmed my openclaw agent to fish, now it feeds me for a life time

Is anyone here good at fishing??? Is my rod supposed to just snap in half?

@camolNFT Baller honeymoon, and a nice gift for Camol’s generosity

If I gave you $10,000 right now, but you had to spend it all at once, what would you buy?

GPT-5.4 Thinking and GPT-5.4 Pro are rolling out now in ChatGPT. GPT-5.4 is also now available in the API and Codex. GPT-5.4 brings our advances in reasoning, coding, and agentic workflows into one frontier model.

@fipcrypto slack is interesting, does that tool just feel more native to you? Lot of telegram content discord usage is growing content. @jumperz has great insight Ask your agent how to solve the issue. Or let me know and I’ll see if I have notes or a solution to suggest 🫡

Spent almost half a day to finally get the second bot configured on OpenClaw. (After reinstalling and restarting from scratch while troubleshooting many errors) Not sure if it's because I'm using GLM-4.7 or it's my server configuration, as the responses I got back were slow.