See you all soon! ๐Ÿ˜Ž #SafeTravels
Safe travels to all Devoxxians. See you soon! #Devoxx
1
1
10
532
๐ŸŽฎโญ๏ธ๐Ÿ˜… #Devoxx #RobotGames
The games are in. Itโ€™s your turn to play!ย ๐ŸŽฎ ๐Ÿ•น๏ธ The #Devoxx Robot Games community has been busy building. Now we need your reviews and ratings: try the games, pick your favourites and give them 1โ€“3 stars. Play & Rate: game.devoxx.be/vote.html
318
๐Ÿง ๐Ÿ”ฅ๐Ÿ‘€ #Gemini4 #Argon
Lots of discussion out there about our next model(!), so I wanted to give an early look as soon as possible. Introducing Gemini 4 Argon! It shows frontier performance in complex workflows, cyber defense and software engineering. Teams are using it extensively at Google, from coding to quantum computing, great feedback. Hereโ€™s a look at the benchmarks:
1
482
Wow... some amazing #Devoxx Games have arrived โค๏ธ๐Ÿคฉ Deadline is tonight... game.devoxx.be
2
314
Looks like @OpenAI is starting to connect the dots ๐Ÿซฃ๐Ÿ”ต๐ŸŸข
310
The final #Devoxx newsletter is out! ๐Ÿ“ฌ Everything you need to know before next week, including practical info to help you get ready for #Devoxx ๐Ÿ‡ง๐Ÿ‡ช๐Ÿš€ redirect.devoxx.be/nl3/63Kt_โ€ฆ
3
5
419
๐Ÿ‘‡๐Ÿ‘€๐Ÿ”ฅ
Planning your @Devoxx Belgium schedule? With 200+ talks across 8 parallel tracks, picking sessions takes time. I built a personalized agenda generator using @Micronautfw, @LangChain4j, and #Gemini 3.5 Flash-Lite on #Java 25 virtual threads! Here is how it works ๐Ÿงต๐Ÿ‘‡
1
3
614
Can't wait to get started... #Devoxx
NEXT WEEK ๐Ÿš€ #Devoxx Belgium 2026 is almost here! 5 days. ~200 speakers. 8 tracks. ~2700 devoxxians. ๐ŸŽŸ๏ธ eTickets have now been emailed to all attendees and speakers, check your inbox (and spam folder). See you in Antwerp! ๐Ÿงก
1
11
713
This is clearly the exciting and very promising part of AI ๐Ÿฉบ๐Ÿฅผ๐Ÿ‘‡๐Ÿ‘€
I've been a cardiologist for 25+ years. The last 90 days changed medicine more than the last decade, and almost nobody noticed. Here are the 10 biggest AI breakthroughs, and why you should be excited, not afraid ๐Ÿงต 1/ 37,000 AI agents. One "virtual biotech." It analyzed thousands of trials, figured out which drug targets actually work in humans, and independently proposed a lung cancer strategy that a major pharma company later pursued. AI isn't a search engine anymore. It's a co-scientist. 2/ The first drug discovered AND designed entirely by AI (Insilico's rentosertib) just entered Phase 3. In patients, it reversed biological age by 3โ€“6 years across six different aging clocks. Read that again! 3/ As a cardiologist, this one gives me chills. The FDA authorized "Queen of Hearts," an AI that reads a standard ECG and catches heart attacks, including the hidden ones doctors miss. 2x the sensitivity. Far fewer false alarms. It pages the cardiology team itself. In a heart attack, minutes are muscle. 4/ EchoNext spots 6 types of hidden structural heart disease from a cheap, 10-second ECG, and it does it better than cardiologists. It already flagged a patient who went on to get a heart transplant. Screening that used to need an echo lab now needs a test any clinic can run. 5/ UpDoc is the first FDA-cleared AI that talks directly to patients. It checks in between visits, adjusts insulin within limits the doctor sets, and documents everything in the chart. Chronic disease no longer has to wait for your next appointment. 6/ An autonomous AI agent called MIRA, with full access to medical records, went head-to-head with ER physicians on hundreds of real cases. AI: 87.8% correct Doctors: 78.1% It ordered the tests, read the results, and wrote the plan. 7/ Google released MedGemma 1.5 and MedASR, open medical AI for imaging and clinical speech that anyone can build on. Every hospital. Every researcher. Every country. Open models mean medicine moves at internet speed. 8/ The FDA authorized Aletta, the first robot that draws blood on its own. It gets the vein on the first stick 94โ€“95% of the time, even hard veins. One technician supervises three robots. The most common procedure in medicine just got automated. 9/ UCLA's SLIViT matches specialists on 3D MRI, CT, ultrasound, and retinal scans, and it's 5,000x faster. It isn't a new model for every organ. One architecture reads them all. 10/ The FDA has now authorized 1,600+ AI medical devices. They cover radiology, cardiology, and surgery, including real-time AI that checks breast cancer margins while the patient is still on the table. This isn't coming. It's here. What this means to you: โ†’ Drugs that took 10โ€“15 years are showing human results in a fraction of the time โ†’ Heart attacks get caught on a cheap ECG, not after a collapse โ†’ Doctors get hours back โ†’ Patients get answers between visits โ†’ Aging itself is becoming treatable This isn't "AI will replace your doctor." It's AI finally becoming good enough that medicine starts to compound. The next 18 months will feel different. Bookmark this. We're early. Stay positive!!!
2
681
Last weekend to work on your #Devoxx Robots game! Still polishing levels, squashing bugs, or adding that one last crazy feature? Nowโ€™s the time ๐Ÿ˜… ๐Ÿ‘‰ game.devoxx.be Iโ€™ll also share a short demo of my own game, just as a bit of inspiration/reference ๐ŸŽฎ๐Ÿ‘€
4
7
944
Looking forward to this #Devoxx Belgium keynote and hoping (by now) they also support local models ๐Ÿ‘€๐Ÿ”ฅ
One of the highly anticipated opening keynotes for Devoxx Belgium by Jean-Laurent from @Docker ๐Ÿคฉ Make sure to add it your favs ๐Ÿ‘‡๐Ÿผโญ๏ธ m.devoxx.com/events/dvbe26/tโ€ฆ
2
4
641
Parallel Constrained Decoders (PCD) as a possible solution for Agents Mis-alignment?! Love to hear your thoughts on this... linkedin.com/pulse/observabiโ€ฆ
2
6
684
I built a native PCD (Parallel Constrained Decoder) server that embeds llama.cpp and guarantees bounded JSON. Every field gets exactly one allowed value & the probability behind it ๐Ÿ”ฅ MIT, local GGUF, macOS binary, Linux compliant ๐Ÿ‘‡ github.com/stephanj/pcdServeโ€ฆ
1
5
10
1,148
I've tried using PCD (Parallel Contrained Decoder aka JEV) to decide which tools it should use during a @DevoxxGenie agentic loop. Results were not really different compared to what the LLM would decide. 1/2
3
1
6
1,465
However using a PCD calls for knowing when a bash tool command could be destructive is a more promising integration. When flagged as destructive we can ask the user to accept or decline the bash command ๐Ÿคฉ #HITL
1
2
210
Just released a Parallel Constrained Decoding service using java, llama.cpp with local models ๐Ÿคฉ๐Ÿ”ฅ๐Ÿš€ github.com/stephanj/parallelโ€ฆ #Enjoy #Jev #LookAlike
3
10
2,080
Now parts of the "LLM" are playing Tetris ๐Ÿคฉ Full code available in repo.
2
178