Building agent-box.sh, shopninja.ai, chatdomain.ai, former SW Manager @ Upwork, 2 times Founder, father of 2

Lisbon
Marco D'Alia retweeted
I came to realize people liked the french #slopcore without having the lyrics 😅 sorry! So here is a version with english subtitles!
255
583
5,727
1,040,055
OIDC is a blessing, demand to have it supported by any Saas you are using!
It's time to retire long-lived static credentials. We surveyed 1,000+ SaaS vendors and found only 8.4% support secure auth. This is our call to action and how we're doing our part. vercel.com/blog/death-to-lon…
1
4
192
😂
Breaking, Europe announced their new innovation project to show Tesla who is boss.
87
Marco D'Alia retweeted
Real life, baby
19,274
96,567
777,245
98,342,510
Marco D'Alia retweeted
AI is getting out of hand
Tomás C.
18
128
844
88,823
With AgentBox you can coordinate multiple tasks all at once, without juggling windows or terminals: ask a coordinator session (either codex, claude, pi, opencode etc.) to work on each task in a dedicated sandbox. Since each sandbox is used only for one task, you avoid side effects, and you don't need to manage branches, schema changes, system updates, temporary folders cleanup etc. Also sandbox costs is minimal, a few $ per month, since each box is used only for the time of a task: if a dedicated hetzner VM is around 8$/mo, using ~100 sandboxes a month for a few hours each is around ~5$/mo (billed by the minute)
1
4
306
Oh my! This is so cool, coming soon to AgentBox!
You can now mod Claude Code: - Change how it behaves - Customize the UI - Swap in your own features Write one with a few lines of TypeScript, or have Claude build it for you. Mods ship inside plugins, so you install them with /plugin in the CLI or desktop app. A few examples:
1
149
Damn so tempted! Who tried ultrafast from @OpenAI? How's it like to work with Astra at speed of Luna??
1
120
And just 15 days later 500 ✨ stars! With this trend AgentBox will have more stars than atoms in the universe in a year 😂
✨ 400 stars now for AgentBox, and my first Show HN submission! What works for you and what don't? Let me know in the comments 👇 news.ycombinator.com/item?id…
1
175
If you’re still running a pile of Hetzner dev boxes for your agents, you’re a year behind. @steipete shipped that playbook a year ago with OpenClaw. The next step is Agent Orchestration: you talk to Claude/Codex, and it spins up multiple VMs per task. I regularly run 10–20 VMs in parallel, each for 1–2 hours max. The orchestrator tears them down automatically when the work is done. Total cost: ~ $5/mo. - No dev/linux maintenance - No git branches mangling or when switching projects - Lower costs compared to a few dedicated always on boxes Try now with: $ npm -g i @madarco/agentbox $ agentbox install
2
1
199
I'll save you some time: "Over time, ... makes sense for most to buy usage as needed without ... a subscription..."
Hi, Tomorrow we are re-opening the Pro $200 subscriptions to new subscribers, but together with it we are also changing how we calculate the usage for it. In effect, if you do the math, it will net out at half the dollar in API spend compared to the old Pro $200 plan. Now that it's said, let me explain why this is happening and why you will still get more work done than if you were on the Pro $200 subscription one month ago. (a) We didn't want to compromise in other ways and are committing to not reintroducing the 5h limit, so that you can fully use the weekly usage when you want. (b) On the subscription, we guarantee that over time you always get more work done and with an increasing level of quality. This means that you will continue to get more value per dollar spent as a result of models getting more efficient and us passing down the improvements in the form of API price reductions. (c) We don't want to put an incentive on ourselves to artificially inflate the API list prices to make it look like you are getting a lot (and workaround it through discounts, etc). Instead we want to continue to both rapidly reduce prices and increase capabilities of models on the API. This week we introduced GPT-6 Sol and GPT-6 Luna at 50% of their previous price. Over time, we see prices go low enough that it makes sense for most to buy usage as needed without there being a significant gap between what you get in a subscription and what you get in the API for a dollar spent. (d) Tomorrow, we are adding more things to the subscription that won't draw on the usage, I won't reveal what that is yet. I wanted to be transparent before all the big announcements tomorrow. Lots of new exciting things are coming to the subscriptions that will make it super compelling, but I wanted to make sure to share this change ahead of time so you can all understand it before we shower you with good news. Codexingly, Tibo
1
138
Look at all the code I’m not writing! This is a pivotal moment explained perfectly by DHH here, worth watching by everybody. A LOT of the industry is not aware yet that writing code is a lost art. Like taking portraits of people. And yet look at the wave of creativity we got when painters had to reinvent themselves after the invention of the camera, impressionism, cubism etc And now we al know 10x developers do exists, imagine what these can do with AI, 100x?? piped.video/vDjW_dRyKXY?is=OgWY…
2
167
Taste is knowing what’s worth building. @aayushkapoor_ at @lisbonai_
5
89
The view at LisbonAI
1
16
233
Great talk by @duarteocarmo about european portuguese large language models and how he collected the biggest dataset of high quality PT language content for training, pretty cool to learn how these datasets are collected and groomed!
3
109
Great talks so far at LisbonAI from @Prince_Canuma from @Nativ_AI and Jean Rodriguez from @QuiverAI
4
119
is it me or @cursor_ai bugbot just 200% it's cost? very opaque pricing, you just pay tokens but you don't have visibility on how they are used 🤔 Any good alternatives for reviews?
87
Marco D'Alia retweeted
Jev was adopted faster than any other model in AI Gateway history. In the first day, @typesafeai reached ~13% of teams, 2x the GPT-5.6 family and 6x Fable 5.1.
145
186
2,432
1,013,238