🗣️ Large Language Models - inarcissuss

clickBrick prompt engineering: optimizing large language model performance in clinical psychiatry

Covers 3 stories including GitHub here . You can follow the build instructions below as well. Change -DGGML_CUDA=ON to -DGGML_CUDA=OFF if you don't have a GPU or just want CPU inferen...

⚙️LLM Fine-tuning mlx-lora-studio.netlify.app·

MLX LoRA Studio — Fine-tune LLMs on your Mac

Covers ml-explore/mlx

📄AI Papers arXiv·

LoRA: Low-Rank Adaptation of Large Language Models

Covered by 14 sources including Martin Fowler, Towards Data Science

🧠LLM Engineering GitHub·

ml-explore/mlx-swift-lm: LLMs and VLMs with MLX Swift

Covered by developer.apple.com, jan.ai

🤖AI Assistants medium.com

Prompt Engineering : AI Security Tryhackme Walkthrough

🧠LLM Research medium.com

Temperature and Sampling in Transformers: How LLMs Decide the Next Word

⚡Transformers colobu.com·

LLM 究竟是如何工作的？

🧠LLM Tooling blog.skypilot.co·

SkyPilot Endpoints: Production-Ready Inference on Every Cluster You Own

Discussed on Hacker News

🧠LLM Research medium.com

Large Language Models: Architectures, Pretraining, and Roadmaps

🤖AI Assistants klr-pattern.github.io·

Treat the Context Window as a Data Assembly Problem

Discussed on Hacker News

🧠LLM Reasoning research.google·

Thinking to recall: How reasoning unlocks parametric knowledge in LLMs

💬LLM Prompting agentx.so·

评估 AI 代理，精准定位问题，并一键修复。

🤖AI Assistants GitHub·

Show HN: Route LLM prompts to cheapest capable model – pydantic-AI and litellm

Covered by DEV Community

Discussed on Hacker News

🧠LLM Research IT之家·

富士通介绍 PHOTON 框架：1.2B 模型多查询性能 475 倍于 Transformer

🧠LLM Research Bloomberg

Tech Disruptors: Invisible Technologies on RLHF and LLM Training

🤖AI/ML medium.com

The Coming War Between Memory and Compute in AI Systems

🧠LLM Research medium.com

How LLMs Actually Work

🤖Agentic Engineering BestBlogs.dev

我们如何利用 DSPy 将 AI 评估转化为 Dash Chat 的更优回复

🤖AI Assistants m.okjike.com·

clickBrick prompt engineering: optimizing large language model performance in clinical psychiatry

MLX LoRA Studio — Fine-tune LLMs on your Mac

LoRA: Low-Rank Adaptation of Large Language Models

ml-explore/mlx-swift-lm: LLMs and VLMs with MLX Swift

Prompt Engineering : AI Security Tryhackme Walkthrough

Temperature and Sampling in Transformers: How LLMs Decide the Next Word

LLM 究竟是如何工作的？

SkyPilot Endpoints: Production-Ready Inference on Every Cluster You Own

Large Language Models: Architectures, Pretraining, and Roadmaps

Treat the Context Window as a Data Assembly Problem

Thinking to recall: How reasoning unlocks parametric knowledge in LLMs

评估 AI 代理，精准定位问题，并一键修复。

Show HN: Route LLM prompts to cheapest capable model – pydantic-AI and litellm

富士通介绍 PHOTON 框架：1.2B 模型多查询性能 475 倍于 Transformer

Tech Disruptors: Invisible Technologies on RLHF and LLM Training

The Coming War Between Memory and Compute in AI Systems

How LLMs Actually Work

我们如何利用 DSPy 将 AI 评估转化为 Dash Chat 的更优回复

推荐这篇文章，作者完整展示了怎么用 LLM 做一个真正好用的个人工具，重要的是，他展示了如何让 LLM 取代那些你之前觉得不好用的产品，服务，非常值得参考。作...

Clustering Unstructured Text with LLM Embeddings and HDBSCAN