AI Tools & Frameworks Directory

In this tutorial, we explore how to apply post-training quantization to an instruction-tuned language model using llmcompressor. We start with an FP16 baseline and then compare multiple compression strategies, including FP8 dynamic quantization, GPTQ W4A16, and SmoothQuant with GPTQ W8A8. Along the ...

A collection of science tools and experiments to expand the scale and precision of scientific exploration.

Most LLM evaluation systems rely on vague scoring and human judgment disguised as metrics. I built a lightweight evaluation layer in pure Python that turns LLM outputs into reproducible decisions by separating attribution, specificity, and relevance—so hallucinations are caught before they reach pro...

Vercel Labs has released Zero, an experimental systems programming language designed so AI agents can read, repair, and ship native programs without requiring human interpretation of compiler output. The language emits JSON diagnostics with stable codes and typed repair metadata, enforces capability...

ArXiv is doing more to crack down on the careless use of large language models in scientific papers.

Running AI agents in a local script is straightforward. Running them reliably in production across teams, across restarts, with isolated environments per context is a different problem entirely. BerriAI, the company behind the LiteLLM AI Gateway, is now open-sourcing a purpose-built answer to that p...

Exactly how does it differ from ReAct, CodeAct, Self-Loops, and Subagents? The post Recursive Language Models: An All-in-One Deep Dive appeared first on Towards Data Science.

Researchers from NVIDIA introduce SANA-WM, an open-source camera-controlled world model that generates 60-second, 720p videos with precise 6-DoF camera control — trained on 64 H100 GPUs and deployable on a single RTX 5090. The post NVIDIA Introduces SANA-WM: A 2.6B-Parameter Open-Source World Model ...

arXiv:2605.13848v1 Announce Type: new Abstract: Agentic LLM frameworks that rely on prompted orchestration, where the model itself determines workflow transitions, often suffer from hallucinated routing, infinite loops, and non-reproducible execution. We introduce GraphBit, an engine-orchestrated f...

arXiv:2605.13849v1 Announce Type: new Abstract: Determining what to eat to satisfy nutritional requirements is one of the oldest optimization problems in operations research, yet existing formulations have two persistent limitations: continuous variables produce impractical fractional servings (1.7...

arXiv:2605.13850v1 Announce Type: new Abstract: Existing frameworks for LLM-based agent architectures describe systems from a single perspective: industry guides (Anthropic, Google, LangChain) focus on execution topology -- how data flows -- while cognitive science surveys focus on cognitive functi...

arXiv:2605.13851v1 Announce Type: new Abstract: Multi-agent orchestration -- in which a hidden coordinator manages specialized worker agents -- is becoming the default architecture for enterprise AI deployment, yet the safety implications of orchestrator invisibility have never been empirically tes...

arXiv:2605.13880v1 Announce Type: new Abstract: Agent memory is typically constructed either offline from curated demonstrations or online from post-deployment interactions. However, regardless of how it is built, an agent faces a cold-start gap when first introduced to a new environment without an...

OpenAI and Malta partner to expand AI access, offering ChatGPT Plus and training to help citizens build practical AI skills and use AI responsibly.

The Musk v. Altman trial came to a close this week, and the final arguments kept circling back to one question: can we trust the people in charge of AI? All of this is playing out as SpaceX charges toward what could be one of the largest IPOs in American history, with a whole generation of founders ...

Our recent paper, “LLMs Corrupt Your Documents When You Delegate”, has generated discussion about the reliability of AI systems in delegated workflows. We appreciate the interest in this work and want to clarify several important points about what the paper does—and does not—claim. The research aims...

A practical guide to categorization in credit scoring The post From Raw Data to Risk Classes appeared first on Towards Data Science.

A powerful illustrated allegory charting humanity's journey from raw physical labor to cognitive dependency on AI. This triptych explores the irony of strengthening our machines while weakening our own minds and bodies. There is nothing better for the body and the mind than to exercise and use both....

AI video generation startup Runway is betting that video generation is the path to world models. And that being an AI outsider is an advantage, not a liability.

Osaurus combines local and cloud AI models in a Mac app that keeps users’ memory, files, and tools on their own hardware.

In this article, we will explore five fundamental concepts that every Python developer should have in their toolkit.

How to build a decision-grade scorecard for AI agents The post Stop Evaluating LLMs with “Vibe Checks” appeared first on Towards Data Science.

This article was originally published on Addy Osmani’s blog. It’s being reposted here with the author’s permission. Roughly: Anytime you find an agent makes a mistake, you take the time to engineer a solution such that the agent never makes that mistake again. We’ve spent the last two years arguing ...

The Seoul-based speech AI company ships its third generation of its on-device TTS engine, adding expressive tags, improved reading stability, and a 6× increase in language coverage — all while keeping the inference contract unchanged for existing integrations. The post Supertone Releases Supertonic ...