Understanding Neural Network, Visually…
https://visualrambling.space/neural-network
#tech #technology #science #math #MachineLearning #ML #BigTech #AI #ArtificialIntelligence #LLM #LLMs #MachineLearning #GenAI #generativeAI #Meta #Google #NVIDIA #gemini #OpenAI #ChatGPT #anthropic #claude
Understanding Neural Network, Visually…
https://visualrambling.space/neural-network
#tech #technology #science #math #MachineLearning #ML #BigTech #AI #ArtificialIntelligence #LLM #LLMs #MachineLearning #GenAI #generativeAI #Meta #Google #NVIDIA #gemini #OpenAI #ChatGPT #anthropic #claude
Published today on the front page of Le Monde!
https://www.lemonde.fr/idees/article/2026/02/04/vu-par-tjeerd-royaards_6665324_3232.html
We're going to put together a resource for musicians on how they can have album art without using large language models. Do you have any resources you'd like to see in that? Free image libraries? Friends who can help do design? Basic how-tos?
#mutualaid #solidarity #helpingeachother #mirlo #resources #ai #llm
RAG works… until it doesn’t. Most failures aren’t crashes.
They’re silent: weak grounding, partial answers, confident hallucinations.
I wrote a hands-on guide showing how to measure RAG quality in Java using Quarkus + LangChain4j:
– faithfulness
– relevance
– retrieval quality
– reference-based checks
Local models. No hype. Production thinking.
https://www.the-main-thread.com/p/measuring-rag-quarkus-langchain4j-evaluation
#Java #Quarkus #RAG #LangChain4j #LLM #AIEngineering #Fediverse #OpenSource
RAG works… until it doesn’t. Most failures aren’t crashes.
They’re silent: weak grounding, partial answers, confident hallucinations.
I wrote a hands-on guide showing how to measure RAG quality in Java using Quarkus + LangChain4j:
– faithfulness
– relevance
– retrieval quality
– reference-based checks
Local models. No hype. Production thinking.
https://www.the-main-thread.com/p/measuring-rag-quarkus-langchain4j-evaluation
#Java #Quarkus #RAG #LangChain4j #LLM #AIEngineering #Fediverse #OpenSource
🧵 …that's the answer to the toot above. Not only that, when coding software, a lot of thought is given to what it is more stable and how it is implemented more safely. Mindlessly letting something rattle together sooner or later results in serious gaps.
»Technical Breakdown: How AI Agents Ignore 40 Years of Security Progress«
📺 https://www.youtube.com/watch?v=_3okhTwa7w4
#ai #vibecoding #itsecurity #breakdown #llm #LLMs #noai #softwareengineering #software #video #youtube #yt #code
AI agents want your API keys. Don't give them your API keys.
Built a proxy that lets them read everything but queues writes for approval. I review it over coffee.
Self-hosted. Open source. Your data stays yours.
I may regret this at some point, but I felt the need to put down in writing how I feel about this moment in the tech industry.
It is not kind. You may well be insulted by it. If you are... then you really should question yourself.
We're going to put together a resource for musicians on how they can have album art without using large language models. Do you have any resources you'd like to see in that? Free image libraries? Friends who can help do design? Basic how-tos?
#mutualaid #solidarity #helpingeachother #mirlo #resources #ai #llm
