something that I'm curious, and may want to try is implementing "Dynamic" state flows for LLMs... I can see a process where it could create new states (teaching it), and then asking to evaluate which state to slide into, to then change the prompts for that state... I wonder... #ai #llm #learning

AI isn’t just for chatbots. 🚫🤖 In my latest post, I share how LLMs can actually simplify real work—from classifying requests to summarizing reports. www.linkedin.com/pulse/unlear...

Unlearning and Relearning: How to Apply AI in Everyday Workflows

When engineers get a new tool in their toolbox, there’s always a learning curve. Some tools are easy to pick up (like new language versions), others are challenging (Docker, Kubernetes), and some are ...

linkedin.com

Ok question @tychobrahe.bsky.social. If I were to start reading warhammer novels where to start?

Just posted a new article on what does it mean to be an engineer in the era of LLM/AI #ai #leadership #llm #developer www.linkedin.com/pulse/throug...

Through the Looking Glass: How Engineers Should Approach AI, Its Tools, and Adapt

AI Is Here — And It’s Reshaping How We Work Artificial Intelligence isn’t a sudden arrival—it’s been quietly evolving for decades. The field traces its roots to the mid-20th century and saw an explosi...

linkedin.com

#offheap 91! We dive into OpenAI’s $3B Windsurf deal, the launch of the CVE Foundation, and big OSS updates: Spring AI 1.0.0, Jakarta EE 11 and major license shifts from Redis, Hibernate & OpenRewrite. Plus, RTO trends & more! 🎙️ #Java #OSS #AI #DevNews www.pubhouse.net/podcast/offh...

🎙️ New Stackd Podcast Ep. 77 — “I Haven’t Been Fired Yet” w/ @starbuxman! We talk AI debugging, Java 24, Spring AI, WebAssembly, UK’s crime prediction tool, clean energy, dev tools & more! ☕💻 www.pubhouse.net/podcast/stac... #Java

Interesting question. Say you have a request/response. Do you Process(req):res Process(pair):pair Process(req):res(contains req as property)

Hey blueskysphere. Has anyone worked with captnproto in java? Worth taking a look? Or is just in memory proto for c++?

@danvega.dev how about a tutorial for #springai and #llamaguard3? That would be amazing! (Hint hint 😉)

So my weekend project (ok multiple weekends) was to create an email classifier that help me organize more than 100k emails on my inbox. It's open sourced, use LLM for email classification and runs in your computer (no need to ship emails outside to anyone). Give it a spin! github.com/windust/mail...

GitHub - windust/mail-organizer: Mail Organizer for spam, etc.

Mail Organizer for spam, etc. Contribute to windust/mail-organizer development by creating an account on GitHub.

github.com

I will proudly die on this hill. Steak fries are the best fries🍟. www.nytimes.com/2025/03/31/d...

Steak Fries: Deservedly Reviled or Underappreciated Edible Spoons? (Gift Article)

They may be America’s least popular fry, but some chefs are still devoted to them.

nytimes.com

An interesting question. Bytearrayoutputstream…should it be guarded by a try-with-resources? Or just let it be?

💘 Open source is looking for love! In our latest #OffHeap episode, @apache.org #eclipsefoundation, and @commonhaus.org battle it out to win over a new open-source project. Who will be the perfect match? 🌹✨ www.pubhouse.net/podcast/offh...

Attend @fguime.bsky.social's session at Arc of AI Conference, and learn how to build an email filter and classifier that runs locally using Java and Ollama ✉️ www.arcofai.com/speaker/1d91... Use code JOIN-FREDDY-50OFF for a discount 📅March 31-April 3 🎟️ arcofai.com

Really outstanding explanation of stream gatherers

Todd Ginsberg@todd.ginsberg.com · last yr.

Java 24 just introduced Stream Gatherers — custom intermediate operations for Java Streams. I've written a blog post explaining what they are, why they matter, and how you can write your own. todd.ginsberg.com/post/java/ga...

And…IT’S A WRAP! #JavaOne 2025 is over! Thanks for making the return of “the conference that started it all” a huge success! The #Java community spirit is alive and well! See you next year!

⭐⭐⭐⭐⭐ "When your systems are designed to be used by normal engineers, all that excess brilliance they have can get poured into the product itself, instead of wasting it on navigating the system."

Charity Majors@charity.wtf · last yr.

The IEEE republished a lightly edited version of my recent essay, "In Praise of 'Normal' Engineers". 🙌 spectrum.ieee.org/10x-engineer The greatest engineering orgs in the world are not the most pedigreed or top heavy, but the ones where normal engineers can move the business forward, day by day.

Had a nice evening at the #SeaJUG with @jonatan-ivanov.bsky.social and @fguime.bsky.social #java #community

New JavaPubHouse Episode! (Spring AI and Ollama!). Learn how to run these fancy LLMs in your own computer, and best of all, interact with them using Java and Spring (it's a breeze!) www.javapubhouse.com/2025/02/epis...

Another rotation around the sun. What a great way to spend it with amazing friends and a tower of beer while grilling meats!

let's crowdsource (maybe someone ran into this)... have a kotlin project running in WSL, when using gradle works fine... BUT if using maven, it breaks (by ways of not finding the JDK and for example saying can't find Superclass Object). @intellijidea.com uses gradle for build in Kotlin WSL,

The world is in a quantum superstate

gosh, this is fun (and a little scary).. keep working on my household assistant, and I just added the ability to make notes (ie. a tool to record things of importance you tell it)..so now I can say that I like latin food, or when my birthday is, and it'll write it down.

so the project for this winter break is to create an AI Agent that can help with the household (someone who can keep track of lists, remind you of things, summarize your emails... let's see how far we can push SpringAI, Ollama, OpenAI, and Speechify :D

maybe a question for #springai folks @michaelminella.com .. I noticed that Spring AI + Ollama + Tools works well if doing non-blocking (chat), but when switching to stream it hangs. I did check the tips on and do have ollama 0.51.. bug? (docs.spring.io/spring-ai/re...)

When using #springai with @ollama.bsky.social the order of the System and User messages is important! Having it out-of-order mangles the prompt formation in the Ollama back-end and you get a bunch of hit stop token" pending=[<|start_header_id|>] stop=<|start_header_id|> FYI @danvega.dev :P

ok, maybe a question for @danvega.dev (or anyone that works with #springai). I am using it with Ollama, and while looking at the ollama server logs, it calls /api/chat for a OllamaChatModel.call, but I would rather call the /api/generate (as it's a one-shot generation)...how to do that?

Interesting... been working on using Ollama and Llama3 to classify all the emails in my inbox (100,000 emails)... and so far is going great! This could be a fun open source project :D