HNHacker News
TopNewBestAskShowJobs

oedemis

51 karma · joined July 4, 2014

Developer
submissionscomments
oedemis··on I have a theory that software drives people insane
It depends on the context, software that controls an airplane has very different requirements from an todo-app.
oedemis··on Beating GPT-5.6 Sol on retrieval with 100x cheaper open models
whats about self-consistency like in grpo with majority voiting?
oedemis··on Show HN: Autoretrieval – Autoresearch for RAG Pipelines
interesting approach can you share some insights of your experiments in different domains
oedemis··on Rich Sutton on AI creativity and discovery
why no one talks about claude shannon deep understanding of information theory and the consequences for compression and intelligence
oedemis··on 2025: The Year in LLMs
as architectures evolve, i think it can be that we learn more "side effects".. back in 2020 openai researchers said "GPT-3 is applied without any gradient updates or fine-tuning" the model emerges at a certain level of scale...
oedemis··on CUDA Tile Open Sourced
how mojo with max optimize the process?
oedemis··on The Illustrated Transformer
there is also very good explanation from Luis Serrano, https://youtu.be/fkO9T027an0
oedemis··on Donating the Model Context Protocol and establishing the Agentic AI Foundation
i thought skills are the new context resolver
oedemis··on IBM to acquire Confluent
Streaming, EDA can solve lot of data challenges for enterprise AI use cases
oedemis··on IBM CEO says there is 'no way' spending on AI data centers will pay off
https://huggingface.co/ibm here is very interesting research going https://huggingface.co/ibm-granite
oedemis··on IBM CEO says there is 'no way' spending on AI data centers will pay off
ibm developed SSMs/mamba models and also releasing trainings datasets i think, also quantum computing is strategic option..
oedemis··on No clicks, no content: The unsustainable future of AI search
the first thing when i open my browser is lookup at https://news.ycombinator.com/ :)
oedemis··on Simple Explanation of LLMs
Hello, tried to explain Large Language Models with some visualizations, especially the attention mechanism.
oedemis··on Ingesting PDFs and why Gemini 2.0 changes everything
there is also https://ds4sd.github.io/docling/ from ibm research which is mit license and track bounding boxes as rich json format
oedemis··on GitSynth – Explore Git Commits and Diffs with GenAI (Ollama) for Deeper Insights
mika6996, all set! Feel free to share any updates or thoughts on the idea
oedemis··on GitSynth – Explore Git Commits and Diffs with GenAI (Ollama) for Deeper Insights
GitSynth – A Git Commit Visualizer for Insightful Code Exploration diffs and commits with GenAI (ollama)

Hey HN!

I’m excited to share GitSynth, a tool designed to visualize Git repositories and generates commits and changelog.md file insightful and interactive way. here we go: https://github.com/oedemis/gitsynth

oedemis··on Show HN: FastGraphRAG – Better RAG using good old PageRank
but what about the chunk size, if we have a small chunks like 1 sentence and the hyde embeddings are most of the time larger, the results are not so good
oedemis··on The Cloud Computer
sustainability considerations?
oedemis··on Ask HN: What are your predictions for 2023?
invest in decarbonization movement
oedemis··on Ask HN: Event Driven Design/Discovery?
i also write recently something about this not eventstorming but more in architecture https://blog.oedemis.io/serverless-event-driven-architecture...