Marco Pesani (@marcopesani) header
Marco Pesani (@marcopesani) profile picture

CPO @bitrefill. Serial gamer and food junkie. Mostly #ux and #bitcoin

Italia
Joined May 2010
Photo by Marco Pesani (@marcopesani)Photo by Marco Pesani (@marcopesani)Photo by Marco Pesani (@marcopesani)Photo by Marco Pesani (@marcopesani)Photo by Marco Pesani (@marcopesani)Photo by Marco Pesani (@marcopesani)Photo by Marco Pesani (@marcopesani)Photo by Marco Pesani (@marcopesani)Photo by Marco Pesani (@marcopesani)Photo by Marco Pesani (@marcopesani)
Gasless USDC payments over Base, Polygon and Arbitrum. Gas is the single most annoying thing when paying with stablecoins. If you want to shop on @bitrefill, you don’t have to care about it.
1
2
3
87
Marco Pesani retweeted
this game fucking sucks
1
117
5
2,333
44,928
true
Gift vouchers are the most underrated way for agents to pay. I have a Grok Bot buys vouchers via @bitrefill MCP and pays in crypto via @ottopusxyz, so it feels just like a crypto checkout. It can even drive agentic checkout without intervention. Bought a movie ticket with one prompt.
5
96
Marco Pesani retweeted
Gift vouchers are the most underrated way for agents to pay. I have a Grok Bot buys vouchers via @bitrefill MCP and pays in crypto via @ottopusxyz, so it feels just like a crypto checkout. It can even drive agentic checkout without intervention. Bought a movie ticket with one prompt.
1
2
1
13
476
Best explaination of AI I ever seen
Deception needs a motive, and a motive needs a soul
83
Hackers are now using LLMs to continuously scan software updates, spot newly fixed bugs, and build attacks before teams can apply the fix — all without human involvement. That’s according to the latest report from the Google Threat Intelligence Group. We're helping defenders counter automated threats with Google AI Threat Defense, which combines Gemini and other frontier models to find and fix flaws before attackers can exploit them.
3
124
Turns out that switching to MCP is also effective for security
BREAKING: Google says “the era of autonomous attacks has arrived.” Hackers are now using AI to scan software updates, figure out which security flaw each patch fixes and build an attack before companies can install the fix, all without a human involved, according to a new report from the Google Threat Intelligence Group. “Defending against machine-speed threats at human speed isn’t feasible,” Google said.
58
Given everyone is speaking of agent swarms, here's a Claude Code / Codex skill to bring them to us plebs at acceptable costs. Have Fable 5.2 orchestrate swarms of cheap agents like DeepSeek 4.1 Flash: the big model plans and judges, the cheap ones grind
3
3
154
How: your agent becomes the lead. It splits the task, spawns pi workers on OpenRouter, each in its own git worktree, synced via SQLite. It audits what they ran and only merges what passes tests. npx skills add marcopesani/swarm-skill github.com/marcopesani/swarm…
1
2
88
Works in Claude Code, Codex, pi and 75+ agents via skills.sh. MIT-licensed, and it won't start with less than $5 left on your @OpenRouter key. Run it on a throwaway VM, the bees have shell access. Built something with a swarm? Show me plis
1
52
for privacy-conscious people: if you want to shop on @bitrefill with any coin via x402, without even opening a browser, just ask @bot or any harness. they’ll find a way
1
2
83
about agentic commerce
2
129
agents paying in shielded zec and buying real stuff on bitrefill. not a demo-day mockup, actual checkout. many such cases soon
At Free Society Hack in Mumbai, builders shipped AI agents that pay in shielded $ZEC and buy through @bitrefill, with $2,500 in Bitrefill gift cards on the line. Meet the Agentic Commerce winners 👇
1
2
11
433
ok now give me opus 5.6 because fable is back at burning precious tokens like crazy
3
201
ofc we’re teaching the ai overlords how to improve living beings taste just in case they develop one
we have a winner for the most absurd AI startup ever this Peter Thiel backed company uses AI robots to stab fish in the brain so they taste better and last up to 3x longer it's called Shinkei and it modernizes a centuries-old Japanese technique dozens of Michelin-star restaurants are already lining up to buy the fish here's how it works: > the problem is when a fish gets caught, it usually just suffocates on the boat > that stress floods the meat with hormones and lactic acid, which hurts the flavor and texture > the old Japanese fix for this was spiking the fish through the brain right after the catch, which stops all that > but doing it by hand is impractical for most American fishing crews > so Shinkei built a fridge-sized robot that sits right on the boat's deck > the crew feeds in a fish and AI identifies the exact species, so it knows exactly where the brain and gills are > the robot then drives the spike through the brain and cuts near the gills in about 7 seconds > the fish goes into an ice slurry so the blood drains out > so the fish doesn't sit there stressing out, and that tasty flavor and texture is preserved example number 5,392,417 of how AI can be applied to literally anything
1
1
122
Marco Pesani retweeted
🚨 We are receiving reports of hot wallets on BTCPay Servers being swept by unauthorized attackers. If you're running an instance, please shut it down (./btcpay-down.sh) until we complete the investigation.
279
1,086
457
3,151
902,526
Small plays - Roman Forum, AD 210 An afternoon under Septimius Severus: about 300 people, a vote in the Senate, a trial in the Basilica Julia, a dentist working inside the Temple of Castor. 11 buildings you can enter, each one researched from ancient sources. Built with Claude on @AmirMushich's open-source pixel-plays engine. Explore it: distant-rapids-j68a.here.now… Inspo: @awwbhi2 / @zzzzshawn
4
7
3
118
17,555
Grok make a flying car make no mistakes
3
180
Marco Pesani retweeted
What if you could shop on Bitrefill just by asking?
27
13
6
133
13,335