andreabalducci (@andreabalducci) header
andreabalducci (@andreabalducci) profile picture

CTO & co-founder https://xitter.gq/t.co/HbnRuha320🚀 | master of AI https://xitter.gq/t.co/0rjJ9fDRhN | sup + snowboard + mtb addicted | surfer wannabe | nikon lover |

Here
Joined September 2008
Photo by andreabalducci (@andreabalducci)Photo by andreabalducci (@andreabalducci)Photo by andreabalducci (@andreabalducci)Photo by andreabalducci (@andreabalducci)Photo by andreabalducci (@andreabalducci)Photo by andreabalducci (@andreabalducci)Photo by andreabalducci (@andreabalducci)Photo by andreabalducci (@andreabalducci)Photo by andreabalducci (@andreabalducci)Photo by andreabalducci (@andreabalducci)
Current status – at Assago, Lombardia
1
1
122
andreabalducci retweeted
A huge amount of the Anti-AI code sentiment massively overestimates the quality of human code outside of a very small set of open source and high quality company codebases. Human Slop is everywhere and can trivially be improved on by any opus level model.
478
901
299
11,479
1,049,654
Current status: the new Jarvis.cloud site is being pushed while we travel toward Milan. Vibes..
1
3
140
andreabalducci retweeted
223
1,814
170
27,163
958,540
Time to fly back home with new stuff ready for SMAU.
1
80
andreabalducci retweeted
Anthropic rewrote its Messages API in Rust. Zero Rust devs on the team. Claude wrote the code. Humans wrote the plan and checked old vs new matched on real traffic. CPU dropped 40-50%. Pretty sure "never do the big rewrite" is dead advice. @katelyn_lesse on @latentspacepod
107
235
137
3,007
747,637
andreabalducci retweeted
One of the things I appreciate about LLM-driven coding: it obsoletes the useless "blameless review" culture that made conversations about why proposed code / architecture is bad extremely expensive to have. Developers aren't emotionally attached to LLM-authored code the way they were to stuff they themselves wrote. We're all much more outcome-oriented and not output-oriented, which is how it always should have been. We can just agree the code sucks now and redo it
If you think there’s anything wrong with what Bart is saying here you are absolutely deep fried cooked. This is like “level 1” AI adoption.
2
3
1
29
1,335
AI now finds bugs that survived decades of human review, and writes code that looks right but isn’t. Tests can’t keep up. LeanCIL: formal verification for .NET Proofs about compiled C# and F# (any dotnet lang), for every input, checked by @leanprover github.com/NethermindEth/Lea…
6
28
3
128
7,735
Breakfast coding session in Vienna.
1
79
This doesn't replace engineering work. It's reshaping the work so fundamentally that the job starts to look like building for the moment or finding defendable layers against others. It requires more agency, flexibility and intuition, and strategical thinking.
4
4
63
4,068
Current status 🇨🇿 🚂 🇦🇹
1
59
Cybersecurity advertising in Prague
65
I was there, Gandalf.
78
Vibe coding in Prague on my second Mac, with my Nikon in tow. Writing code, taking photos, and doing it all while traveling. Still blows my mind how much we can do with the tech we carry around. What a time to be alive.
1
118
Mission impossible: managing cloud models while travelling through central Italy by train.
68
Agents testing new JARVIS release.. meanwhile
65
Agents running. Me 🚵‍♂️ 🤙☀️
1
2
167