cd/sources/dotnetperls-auto-discovered· home› sources› Dotnetperls (auto-discovered)
cat /sources/dotnetperls-auto-discovered.feed | wc -l → 79

Dotnetperls (auto-discovered)

articles 79 domain dotnetperls.com → page 4/4 feed RSS
07:00
2026-08-01
dotnetperls.com
artificial-intelligence

Reducing Tool Calls in Agentic AI

A developer experimenting with local-LLM agentic AI workflows found that combining tool calls—such as having a single `read_blog_post` MCP tool internally perform `find_blog_date`—reduces the number o…

07:00
2026-07-31
dotnetperls.com
artificial-intelligence

Using AI Agents for Disliked Tasks

A developer reports greater success and enjoyment using agentic AI with small local models, such as Gemma 4 E4B via llama-cpp and an MCP server, for disliked tasks like website management, compared to…

07:00
2026-07-30
dotnetperls.com
ai-agents

Benefits of Local MCP Servers

A developer created a local MCP server in Rust to run commonly-needed commands via an AI agent, arguing that the approach offers error correction, command chaining, and an improved browser-based UI ov…

07:00
2026-07-29
dotnetperls.com
artificial-intelligence

LFM 2.5 Agentic Model for Tool Calling

Liquid AI released LFM 2.5, an 8-billion-parameter agentic model with 1 billion active parameters focused exclusively on tool calling, achieving nearly 200 tokens per second on a GPU. The model excels…

07:00
2026-07-28
dotnetperls.com
large-language-models

Nanbeige 3 Billion Parameter Model

A developer testing Nanbeige 4.2, a 3-billion-parameter looped-transformer model from a Chinese company, found it well-suited for tool calling with a Rust MCP server, outperforming Gemma 4 12B in that…

07:00
2026-07-27
dotnetperls.com
developer-tools

Stdio and HTTP for MCP Servers

The developer rewrote their MCP server to use Stdio input and output instead of HTTP, reducing code from 300 lines to about 60 lines using the Rust crate RMcp. The Stdio MCP server functions as a cons…

07:00
2026-07-26
dotnetperls.com
developer-tools

Using ui-mcp-proxy in Llama-cpp

A developer created a simple MCP server for local LLMs to call Rust-coded tools, but encountered CORS errors. The llama-cpp feature ui-mcp-proxy, passed as an argument to llama-server, sets up a proxy…

07:00
2026-07-25
dotnetperls.com
artificial-intelligence

Wrote a Local MCP Server

A developer created a local MCP server to extend llama-cpp's tool capabilities, finding that models like Gemma 4 12B reliably call MCP-provided tools. The server, written first in Python then Rust, of…

07:00
2026-07-23
dotnetperls.com
ai-agents

Writing Tests in Rust with Laguna

Laguna XS 2.1, used with OpenCode, helped a developer replace narrowly-focused unit tests in a Rust project with a single, more general test that covers multiple functions at once, resulting in fewer …

07:00
2026-07-22
dotnetperls.com
large-language-models

Laguna XS Model in OpenCode

Poolside AI's Laguna XS model, a small local LLM, performed well in refactoring Rust code via OpenCode, making relatively few errors and handling tool calls correctly except for escaped quotes. The 20…

07:00
2026-07-21
dotnetperls.com
artificial-intelligence

Replacing Scripts with AI Markdown Files

A developer proposes replacing traditional Bash scripts with Markdown files processed by local AI agents, arguing that code is a maintenance burden. Using llama-cpp's tool-use feature, an AI agent lik…

14:01
2026-07-20
dotnetperls.com
artificial-intelligence

Tested Kimi K3 for Coding (2026)

Kimi K3, a new AI model released this week and claimed to be near-frontier quality similar to Fable and GPT, successfully optimized a Rust program by implementing a SWAR (SIMD Within a Register) optim…

07:00
2026-07-13
dotnetperls.com
large-language-models

Rewriting Code With AI

A developer used AI agents Gemma 4 12B and Qwen 3.6 35B to rewrite Rust code without doc-comments, but found direct rewriting unreliable. Instead, the developer had Qwen 3.6 generate a Python script t…

07:00
2026-07-08
dotnetperls.com
large-language-models

Llama-cpp Tools

A developer is using llama-cpp's tool-calling feature to let large language models execute system commands such as reading files and editing code, comparing the approach to bash scripting but easier t…

07:00
2026-07-07
dotnetperls.com
large-language-models

Notes on MTP, EAGLE-3 and DFlash

A developer reports that speculative decoding techniques MTP, EAGLE-3, and DFlash can significantly speed up local inference of large language models in llama-cpp. Testing on an NVidia 3060 RTX 12 GB …

07:00
2026-07-02
dotnetperls.com
large-language-models

DFlash for Local LLM Inference

Z-Lab's DFlash technique uses diffusion models to accelerate LLM token generation through speculative decoding, achieving up to 123 tokens per second for code generation in tests with Qwen 3 8B on lla…

07:00
2026-06-27
dotnetperls.com
large-language-models

Why Local LLMs Are Necessary

Local LLMs are necessary for privacy and freedom, as data center subscriptions risk data misuse and account lockouts. Smaller models are becoming more capable, making local AI viable for software deve…

07:00
2026-06-24
dotnetperls.com
large-language-models

Agentic Coding Outperforms Human

A developer spent an hour trying to optimize a Rust function but failed, then used a local LLM agent (Qwen 3.6 35B) in OpenCode to suggest and implement a faster, clearer solution. The LLM's alternati…

07:00
2026-06-23
dotnetperls.com
large-language-models

AutoRound Quantization for LLMs

Intel's AutoRound quantization algorithm for large language models claims state-of-the-art performance, enabling LLMs like Qwen 3.6 to run on consumer GPUs. In testing, AutoRound produced consistent o…

← prev page 4 / 4