Mihai retweeted
I really enjoy @AmpCode and have recommended it to plenty of people.
Every time I get blocked because of an outage makes me want to use it less and less.
Mihai retweeted
Presidente @NicusorDanRO, grazie per le congratulazioni e le belle parole rivolte all’Italia e al suo governo.
Le nostre Nazioni sono unite da legami profondi tra i nostri popoli e da interessi comuni. L’Anno Culturale Romania-Italia sta rappresentando un’ulteriore importante occasione per valorizzare questa vicinanza e il patrimonio che condividiamo. Sono certa che continueremo a lavorare insieme con concretezza, rafforzando una collaborazione che offre grandi opportunità alle nostre Nazioni 🇮🇹🇷🇴
Congratulations @GiorgiaMeloni as your government becomes today the longest-serving in the history of the Italian Republic. It is a milestone that reflects the institutional continuity which gives policy the horizon it requires to deliver.
Romania and Italy are bound by a Strategic Partnership that rests on strong foundations. More than a million Romanians live and work in Italy, the largest foreign community in the country, and our economies are closely tied. Italy is Romania's second trade partner and the leading source of foreign-capital companies here. We are marking those ties this year through the Romania–Italy Cultural Year.
I look forward to continuing our work together, co-chairing the Friends of Cohesion in the negotiations on the 2028–2034 multiannual financial framework, where Romania and Italy make the common case for an ambitious EU budget with adequate resources for cohesion and agriculture, and standing side by side on the security of NATO's eastern flank and the Black Sea.
Mihai retweeted
Astra's understanding of 3D assets and spacial awareness is beyond anything else.
Astra (GPT-6) is here!!!
I've had early access and tested it like crazy with things like games, code, writing, browser control, presentations and general knowledge work.
This is the best model I've ever used. Period.
(Incredible demos below in this thread ⬇️)
Here's my take on Astra:
> It's insanely capable. This feels like a massive improvement, not just an incremental change. This is especially true with zero-shot prompts.
> It's all about knowledge work. Slide creation, analysis, writing, and browser control. And oh my...it's so good at browser control. GPT-5.6 was already fantastic at doing things in the browser, Astra is another level and significantly faster.
> We're closer than ever (arrived?) at prompt-to-playable game. And I don't just mean only playable, these are actually fun games. I bet if someone with a great eye for games used Astra, they could create a viral game within 1-2 weeks.
> Astra is better at writing but not perfect. It removes much of the "AI Smell" we're all familiar with but some stink still survived.
> It has a tendency to use the same design colors and look/feel as GPT-5.6 (forrest green anyone?) but it is more steerable in design than previous models.
> It's highly steerable in general. A little nudge goes a long way. When I first started using Astra, almost every task I gave it would go for ~30 minutes. I wanted it to keep working. Adding more specifics to a prompt helped greatly with it's ability to work for a long time.
> Astra's 3D understanding is unmatched. 3D asset creation was consistent and easy and its spacial awareness while building complex 3D worlds blew me away.
I'm still getting familiar with Astra but this will now be my go-to model for any difficult work I have.
Check out the demos below: 👇
Mihai retweeted
After a week with @cursor_ai cloud (with poteto poteto poteto) and @AmpCode's orbs, I'm ashamed to admit that I was wrong.
Cloud agents are amazing, I'm spawning more VMs than I can count, but I can come back to them anytime, or check on them during my commute.
Orbs have the best implementation, Cursor comes close (but way more expensive).
To prove I'm serious, I'll work off an iPad next week, and make a supaterm.com iPad app that can connect to any host. I've put off this work for awhile since it's not my workflow, but now there is no excuse.
I rarely see the need for cloud agents or for running agents inside VMs.
With a modern MacBook and a proper codebase that's worktree and agent-friendly, I can spawn basically 50 instances of the app, and the computer barely sweats.
Taco Bell programming please widgetsandshit.com/teddziuba…
Mihai retweeted
will be speaking at frontiers by @paradigm in SF oct 12 about the crazy things you have to do to build an agent that people want to use - apply at paradigm.xyz/frontiers-2026 if you want to join
Excited to share Wave 2 of Frontiers by @paradigm Speakers! Frontiers is our intense annual conference & hackathon for those beyond the edge in SF, Oct 12-14th 2026.
- @johannes_hage of Prime Intellect
- @_patrickogrady of Commonware
- Sam Herring of Nous Research
Apply to attend in the link below!
Logistics:
- Wave 1 of acceptances goes out today.
- 2 weeks left for any new applications.
- Merch and more sick videos to be announced.
- 1 more super special speaker to be announced!
Mihai retweeted
We just shipped live video chat for your orbs and threads in @AmpCode.
Go to the new 'space' tab and you'll enter a shared space where you can chat with your team!
Mihai retweeted
ampcode.com/settings/dial?lo…
Perfect combination
Raising an Agent, S2E3: When Tokens Flow Like Electricity.
@sqs and @thorstenball on what happens when intelligence gets cheap: build vs. buy flips, why everyone building software to build software to do X is probably incorrect, and when software starts to feel like owning a house instead of renting one.
00:00 Intro: Cheap intelligence & doing X instead of building software to do X
01:06 Back home after Munich & what's changed in how we build
02:06 Predictions: the price of intelligence drops, tokens flow like electricity
05:54 Everyone is building dev tools & why that's the wrong bet
06:57 Pet theory: engineers can't believe it's this easy
10:33 Orbs vs. EC2, a VPN & tmux
17:18 Build vs. buy when the models keep changing
20:14 If Amp is worth buying, why isn't an issue tracker?
27:34 Killing features & vibe coding the 2% of a SaaS product you need
30:03 Build on a solid core: glue code is the worst part
33:19 The two Amps: jellyware, homeowners & renters
37:01 Exporting the Amp way to more teams
43:42 Opinionated software from people you trust
Mihai retweeted
For everyone who:
• doesn't want to commit .agents/setup OR
• needs to run tailscale up before repo cloning
Amp's now for you, too.
Now you can set up orbs without committing files. If you have repos on private networks, or other more advanced setups you might need setup prior to cloning, or maybe you just don't want to commit your setup scripts. We have you covered.
Happy orbing.
ampcode.com/news/setup-witho…
Mihai retweeted
Anyone want to contribute a cool demo video of Amp's experimental Desktop tab for native development, browser automation, or anything else where it does stuff portals alone can't do?
It'll be in the Amp news post about this, will credit you. Must be high-res no-audio video or screenshot. Email sqs at ampcode dot com or reply here. Going out in the next ~24h probably.
ampcode.com/settings/experim…
Mihai retweeted
Now anyone at @tryramp who can help? Similar issue. @AmpCode purchases are shown in Ramp as being from Sourcegraph, despite the statement descriptor being "AMP CODE". And they are misclassified as "Consultants and other Professional Services".




































