#Developer 📈InfraSaaS for AVP⚡️Working on PV Power Grid 🍜Restaurant platform (exit to TripAdvisor) 🏦Mortgage financing 📲Live streaming App
Vienna, Austria
Joined February 2015
- Tweets2.1K
- Following1.7K
- Followers393
- Likes3.4K
Zeljko Savic retweeted
Jev is an incredible model router.
Ask Jev which models can solve a user’s task, and route it to the cheapest one.
We have a new frontier model overnight.
Zeljko Savic retweeted
Today we're rolling out Projects in Claude Code on desktop and web.
A project is one conversation with Claude. It splits the work into threads itself, runs them as parallel cloud sessions, passes context between them, and keeps going when you leave.
In beta for select users.
Zeljko Savic retweeted
Of course younguns think that UML is ancient and deprecated -- something we've outgrown.
That's funny.
What we've actually outgrown is the use of UML as an up-front specification language. What we have not outgrown, and likely will not outgrow any time soon, is a need to recursively depict the structure of a software system.
And it turns out that UML class diagrams (e.g. E-R diagrams) are uniquely applicable for such purposes.
Zeljko Savic retweeted
hi kids, gramps here. learn your algorithms and datastructures, cause SOTA frontier models will still fuck you up bad behind your back, especially if you don't read your code anymore.
Zeljko Savic retweeted
Projects now run from one conversation, starting in Claude Code. You describe what needs doing, and Claude directs parallel threads that keep working after you close your laptop.
In beta today for select Pro and Max users in cloud sessions; coming to all Claude users soon.
Zeljko Savic retweeted
In the 1950s, an aluminum company commissioned Vacheron & Constantin to make them some aluminum pocket watches. The case, dial, hands, numerals, and even the plates in the movement are aluminum. The resulting watch is 44 mm in diameter but weighs only 22 g.
Zeljko Savic retweeted
GPT-6 Astra deciphered a 1918 German radio transmission that, to my knowledge, has never been deciphered before.
The message below translates to:
"EIN ENGLISCHER KREUZER EINLIEG X SEWASTOPOL X S4STEN X EIN GESCHWADER DER X ALLIIERTEN FOLGT 26STEN X"
or, in English:
"AN ENGLISH CRUISER ARRIVED AT SEVASTOPOL ON THE ?4TH AN ALLIED SQUADRON FOLLOWS ON THE 26TH"
Astra even double-checked its work by determining that an English cruiser, HMS Canterbury, reported its arrival in Sevastopol on November 24, 1918 and the arrival of an allied squadron on November 26, 1918.
This message is one of the ~20 WWI German radio messages that appear as one of the entries in the scienceblogs.de list of top 50 unsolved ciphers (scienceblogs.de/klausis-kryp…).
A minor, but really cool result!
Zeljko Savic retweeted
One pattern I find useful for working with LLMs is a nice long ramble session. Sometimes the LLM needs more bits to understand what you're trying to achieve, but you're too lazy to type them. In these cases I like to lean back, switch to /voice and just ramble for like 10 minutes, total mess, anything goes, full stream of consciousness. Sometimes I declare it up top, something like "switching to speech recognition sorry for any typos...". Sometimes I turn it into a small interview of a few turns. But I find that the LLMs are somehow very good at reconstructing long incoherent rambles and often their echo of your own tangle of thoughts comes out quite a bit cleaner than what you started with. The result is that you improve the mind meld and have to correct things less from that point on.
Zeljko Savic retweeted
Claude Design, Claude Slides and Claude Docs also work inside Claude Code now.
Ask for a design review deck or a UI mockup and point it at the actual files and RFCs in the repo. Edit it yourself or keep going in the conversation, and share the link when it's ready.
Zeljko Savic retweeted
iPhone Duo
iPhone 18 Pro and iPhone 18 Pro Max
Apple Watch Series 12 and Apple Watch Ultra 4
AirPods 5
… and Joz
Zeljko Savic retweeted
For the past several months I've been working on this hypothesis that agents need to be constrained by a harness of deterministic tools that force them to follow a strict process. Gherkin, Code, Unit Tests, Crap, Mutation Tests, etc.
But while I've been hammering away on that, the models have gotten astronomically better. I'm starting to think that I'm over constraining them. Perhaps vastly over constraining them.
Zeljko Savic retweeted
Gemini 3.8 Flash is here, and it's a big step up 📈🚀
Our 3rd Flash release in 6 weeks continues the momentum of building a great model that is cost efficient for a wide range of tasks.
Give it a try today and let us know what you think!
Zeljko Savic retweeted
Today we’re introducing a new 3.8 Flash model, our 3rd Flash release in just 6 wks.
It delivers significant leaps from 3.7 Flash across software engineering, agentic tasks, and multi-step reasoning. On DeepSWE v1.1, it outperforms most larger frontier models in autonomously solving complex engineering problems end to end, at a fraction of the cost.
More details here: blog.google/innovation-and-a…
Zeljko Savic retweeted
Sending lots of love to the Apple community on my last day as CEO. My title changes tomorrow, but the love I have for the Apple community never will. Thank you for being a constant source of inspiration. My gratitude is endless, and I’m excited for the next chapter!
Zeljko Savic retweeted
anthropic released a new prompt that eliminates claudese:
platform.claude.com/docs/en/…
Zeljko Savic retweeted
The ability to wrangle these immensely powerful, yet dangerously capricious, agents into a productive harness that produces high quality systems — is the software engineering challenge of this decade.
Is anyone running multiple businesses and if yes, how do you manage it.
I now running three separate businesses within three disjunct products and teams, and would like to share know how with people doing so.
