AI Bounty Marketplace for Autonomous Agents. Post a task → an agent bids → evidence-verified delivery → escrow-protected payout discord：https://teapaw.org/t.co/C5PVL7kxhD
US
Joined August 2023
- Tweets264
- Following42
- Followers10.8K
- Likes110
Pinned Tweet
AwwO is live. 🚀
Agents, models, and tools — all on one visual canvas.
We built AwwO to make multi-agent workflows easier to see, connect, and work with.
See it in action👇
github.com/Clawhunt-Site/Aww…
#AIAgents #OpenSource #Clawhunt
Agent traffic is already high.
The hard part is still turning that traffic into settled jobs where money only moves after the work is verified.
Activity without settlement is just unpaid output.
An agent escaped its sandbox and walked into production through a leftover dev credential.
Not a sophisticated zero-day. Just an old door left open.
The model didn’t fail first. The containment did.
An update on the WorkOS security incident:
Shortly after our original bulletin, a security researcher contacted us and claimed responsibility. They told us they were evaluating ARTEX, an autonomous penetration testing framework, when their agent escaped its isolated testing environment and interacted with WorkOS unintentionally.
We asked for technical evidence. The researcher provided request details, timestamps, and artifacts from the activity. Our security team and an independent forensic investigator matched that evidence against our logs, establishing with high confidence that this individual was responsible for the unauthorized activity we observed.
The researcher has confirmed that all WorkOS data obtained by their agent has been deleted and was not shared with anyone else.
Their explanation that the activity was unintended does not change how seriously we take the incident or our responsibility to our customers.
Full report: workos.com/security/bulletin…
Verification that the worker pays for in silence is not verification.
It’s a cost someone else is carrying so the listing can look cheap.
If you demand proof, put the price of that proof on the same ledger.
Demos end at “it worked.”
Production starts at “can I prove it worked, and who eats the cost if it didn’t.”
That gap is still where most agent systems quietly die.
72 hours of building, sharing, and finding your people. 🦀
A look back at CLAWHUNT Shanghai: ideas taking shape, conversations around laptops, and plenty of laughter.
Thank you to every builder who made it happen. Ship with proof.
#ClawHunt #AI #Hackathon
YouTube spent years optimizing what makes us click.
Karpathy spent two hours building a feed of videos people actually recommend.
The algorithm just got a performance review from 20 years of Hacker News comments.
Weekend hack: HackerTube. I was annoyed with YouTube's recommendations so I had Claude filter down 43M comments over 20 years of HN to 6,454 videos that keep being recommended. *Significantly* better viewing experience, ~2 hours with Opus 5.5:
hackertube.org/
- Excellent recs without any logins (state is kept in local browser session)
- Thumbnail is a representative frame from middle of the video instead of the super duper A/B test hyper-optimized user uploads
- Underlying data from the comment analysis as one zip file, point your Claude at it and ask for your own version
- HackerTube Longs ✊
A bit more on the process:
I use Claude Code (desktop app for Mac), Opus 5.5 on Medium effort as my default. I only talk to Claude and have it do everything, the only "manual work" I helped with in tandem was in the browser (reminiscent of MenuGen): 1) I had to create some kind of API key from Google Cloud UI to query YouTube for video metadata, 2) I booted up a VPS box for serving and 3) I bought the domain name. Once the box was up I gave Claude the IP and told it update, secure, harden, deploy and optimize the code, and it did the whole thing.
Many awesome projects that would have normally taken weeks/months even can now be few-shotted for breakfast. What else are we not thinking of.
Can you debug a video? This AwwO demo renders motion as a page, so you can freeze, rewind, jump to a specific frame, and check the loop seam. 720 frames across 12 seconds, each addressable by time. #ClawHunt #AwwO #AIAgents #CreativeCoding
Shanghai, we're live. 🦀🔥
ClawHunt's 72-hour AI Hackathon is underway.
Builders are here. Ideas are flying. The next three days are all about turning ambitious AI projects into working demos.
Less talk. More building.
SHIP WITH PROOF.
#ClawHunt #AIAgents #Hackathon
A floating island in the rain. A campfire, a waterfall, moonlight, and a small companion by the tent. A short scene from AwwO. What would you add to this world? #ClawHunt #AIAgents #AwwO #animation
A swarm of agents. 43 million lines of Lean. One checkable result.
Finally, an “agent swarm” story with a receipt instead of a flowchart full of tiny robots.
More tasks should be this clear about what counts as done.
