milliondreams
Re:Why Workflows Fail: The Indeterministic Business Problem
on Wednesday November 05, 2025 @01:13AM (#45819821)
What does the HN community feel about workflows?
Re:Show HN: CodePrism – an AI-generated code analysis engine as MCP
on Monday June 23, 2025 @06:09PM (#44360717)
And now it has a LinkedIn page too. All content (and images) IS AI Generated.
https://www.linkedin.com/company/codeprism-ai/
Show HN: CodePrism – an AI-generated code analysis engine as MCP
https://rustic-ai.github.io/codeprism/
I wanted to see how far I could push the idea of autonomous software development. So I ran a (slightly reckless) experiment: Could an AI build a real, working code intelligence tool entirely on its own — without any human code?Over the span of a week — mostly while I was doing my day job — I let a custom AI agent (built with Dragonscale) design, write, and document a full static analysis engine...
VILA: On Pre-Training for Visual Language Models
Flame: Factuality-Aware Alignment for Large Language Models
LoRA Land: 310 Fine-Tuned LLMs That Rival GPT-4, a Technical Report
Toward Self-Improvement of LLMs via Imagination, Searching, and Criticizing
Toward Self-Improvement of LLMs via Imagination, Searching, and Criticizing
ResearchAgent: Iterative Research Idea Generation Using LLMs
CodecLM: Aligning Language Models with Tailored Synthetic Data
Viking – a family of models for the Nordic languages
Mixtral-8x22B on HuggingFace
Implementation of Google's Griffin Architecture – RNN LLM
Griffin: RNN for Efficient Language Models
Categorical Deep Learning: An Algebraic Theory of Architectures
Training LLMs over Neurally Compressed Text
TinyTimeMixer: Open-source time series LLM by IBM
Re:White House Announces Open Science Recognition Challenge Winners
on Sunday April 07, 2024 @04:14PM (#39963499)
Proud to see Jupyter in the list
White House Announces Open Science Recognition Challenge Winners
Mixture-of-Depths: Dynamically allocating compute in transformers
Arizona State University – Can Large Language Models Reason and Plan?
Can LLMs Every Reason?
Re:Berkeley Function-Calling Leaderboard
on Saturday April 06, 2024 @01:46AM (#39950297)
1. The leaderboard offers a unique benchmark for function calling abilities in language models.
2. It covers a wide range of programming languages and scenarios, enhancing its comprehensiveness.
3. The dataset's diversity, with 2,000 pairs across various domains, stands out for testing model versatility.
4. Comparative analysis of models like GPT-4 on metrics such as cost and latency is highlighted.
5. This resource serves as a valuable tool for understanding and improving language model interactions with code.
Berkeley Function-Calling Leaderboard
Language models as compilers: Simulating pseudocode execution
GLM: Genome Language Model – Deep learning to predict gene function
Re:Lumos: Learning Agents with Unified Data, Modular Design, and Open-...
on Tuesday April 02, 2024 @11:02AM (#39906546)
Guess you are looking for this - https://github.com/allenai/lumos/blob/main/README.md
Evolution of RAG
Re:Lumos: Learning Agents with Unified Data, Modular Design, and Open-...
on Monday April 01, 2024 @11:34PM (#39902131)
Looks promising approach to Agentic AI systems.