iiinova — where your digital self keeps evolving

Freddy Guime @fguime.bsky.social · 04/10/2025

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

010

Freddy Guime @fguime.bsky.social · 17/08/2025

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

000

Reposted by Freddy Guime

pubhouse.net @pubhouse.net · 15/07/2025

#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...

pubhouse.net

OffHeap 91. It’s monday, but I don’t wanna drive to work! (RTO!) – Pub House Network

062

Reposted by Freddy Guime

pubhouse.net @pubhouse.net · 15/07/2025

🎙️ 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

pubhouse.net

Stackd 77: “I Haven’t Been Fired Yet” – Pub House Network

022

Freddy Guime @fguime.bsky.social · 21/05/2025

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

000

Freddy Guime @fguime.bsky.social · 19/05/2025

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

000

Freddy Guime @fguime.bsky.social · 13/05/2025

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

010

Freddy Guime @fguime.bsky.social · 06/04/2025

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.com

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.

141

Freddy Guime @fguime.bsky.social · 27/03/2025

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

121

Reposted by Freddy Guime

pubhouse.net @pubhouse.net · 27/03/2025

💘 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...

pubhouse.net

OffHeap 90. The Dating Game at Devnexus 2025 – Pub House Network

022

Reposted by Freddy Guime

Arc of AI Conference @arcofai.bsky.social · 26/03/2025

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

022

Reposted by Freddy Guime

Ken Kousen @kousenit.com · 22/03/2025

Really outstanding explanation of stream gatherers

152

Reposted by Freddy Guime

Sharat (Shar) Chander - 🟦🌊 @sharatchander.bsky.social · 21/03/2025

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!

45313

Reposted by Freddy Guime

Abbey Perini @abbeyperini.dev · 13/03/2025

⭐⭐⭐⭐⭐ "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."

0365

Reposted by Freddy Guime

pubhouse.net @pubhouse.net · 26/02/2025

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...

javapubhouse.com

Episode 106. Spring AI and Ollama – Java Pub House

054

Freddy Guime @fguime.bsky.social · 23/02/2025

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

010

Freddy Guime @fguime.bsky.social · 12/02/2025

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,

100

Freddy Guime @fguime.bsky.social · 10/02/2025

The world is in a quantum superstate

010

Freddy Guime @fguime.bsky.social · 22/01/2025

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.

100

Freddy Guime @fguime.bsky.social · 20/12/2024

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

010

Freddy Guime @fguime.bsky.social · 12/12/2024

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...)

230

Freddy Guime @fguime.bsky.social · 12/12/2024

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

000

Freddy Guime @fguime.bsky.social · 03/12/2024

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?

ollamachatmodel.call

210

Freddy Guime @fguime.bsky.social · 01/12/2024

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

110