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 2/4 feed RSS
07:00
2026-09-27
dotnetperls.com
large-language-models

Experimented with Claude Opus 5.5

A developer reported that Claude Opus 5.5 generated correct Rust code from a spec for $0.09 per final generation, improving the code by switching lookup table values from u32 to u8 for slightly faster…

07:00
2026-09-26
dotnetperls.com
large-language-models

Costs of Online LLM Usage

Spec-driven development on OpenRouter cut the cost of evaluating a Markdown prompt of up to 180 lines and generating a function to between 1 and 7 cents, according to the author's experiments, far bel…

07:00
2026-09-25
dotnetperls.com
large-language-models

Evaluated MiMo-V2.6 for Code Rewriting

Xiaomi's MiMo-V2.6 Flash, a scaled-down version of the Pro model, rewrote a Rust codebase to replace lookup tables with direct match statements in 17 seconds at a cost of $0.0005 via OpenRouter, produ…

07:00
2026-09-24
dotnetperls.com
large-language-models

Used GLM 5.3 Flash for Code

A developer used OpenRouter to run GLM 5.3 Flash on two Rust functions generated from written specs, paying about $0.03 total for the work. The developer reported the model coded the functions well, w…

07:00
2026-09-23
dotnetperls.com
large-language-models

Generated Code with GPT-6-Sol

GPT-6-Sol generated correct Rust code from two Markdown specifications in under a minute for about $0.07, according to a developer's first-person account of spec-driven development. The same two code …

07:00
2026-09-22
dotnetperls.com
ai-agents

Specification Files for Agents

A developer reports that writing detailed Markdown specification files and having an LLM generate code from them produces reliable output, using the Qwen 3.8 27B model (Bonsai Ternary 2) for functions…

07:00
2026-09-21
dotnetperls.com
ai-tools

Maintaining Prompts Instead of Code

A developer reported that a local model, Ternary Bonsai 2, generated the parse_prompt function returning ParsedPromptInfo from a 180-line Markdown specification in about 30 minutes, producing 300-400 …

07:00
2026-09-20
dotnetperls.com
ai-agents

Doubts About Usefulness of MCP Servers

A developer who implemented a simple MCP server for file creation, deletion, and viewing reported that the LLM added little value, since calling the program executable directly was easier. Using Bonsa…

07:00
2026-09-19
dotnetperls.com
large-language-models

Ternary Bonsai 2 Usage Tips

A user improved the agentic coding performance of Ternary Bonsai 2, a Qwen 3.8 27B-based model, when run locally through llama-cpp by switching its thinking setting from "xhigh" to medium via the chat…

07:00
2026-09-18
dotnetperls.com
large-language-models

Tested Bonsai 2 27B Locally (Ternary Model)

A tester ran Bonsai 2 27B, a ternary model that stores each weight as one of three values (1, 0, -1), locally on a 12GB Nvidia GPU using a special build of llama-cpp from PrismML's GitHub. The 7.2 GB …

07:00
2026-09-17
dotnetperls.com
large-language-models

Compared Gemini 3.8 Flash and Gemma 4

A developer's side-by-side test found that Google's Gemini 3.8 Flash cloud model produced a faster Rust parsing function than the local Gemma 4 model (gemma-4-26B_q4_0-it.gguf), cutting starts_with ca…

07:00
2026-09-14
dotnetperls.com
ai-products

Qwen 3.5 0.8B

A user tested Qwen 3.5 0.8B (Qwen3.5-0.8B-Q4_K_M.gguf) locally and found it works on their MCP server, with a temperature of 0 giving the most consistent results for agentic function calling despite d…

07:00
2026-09-13
dotnetperls.com
ai-agents

Is Agentic Coding Worthwhile

A developer expressed doubts about agentic AI coding tools such as OpenCode and Pi, saying they have had "mixed results at best" and get "better results" from chatbot-style development. The developer …

07:00
2026-09-11
dotnetperls.com
large-language-models

Generating Functions with Prompts

A developer reports that prompting a chat LLM for individual functions and pasting the output into code can work better than agentic harnesses for some situations, and that a local model such as Gemma…

07:00
2026-09-10
dotnetperls.com
large-language-models

Small LFM Models and Quantization

A developer got the 230M-parameter LiquidAI LFM2.5-230M-Q5_K_M.gguf model working with a local MCP server after switching from 4-bit to 5-bit quantization, following an earlier setup that ran the 350M…

07:00
2026-09-09
dotnetperls.com
ai-tools

Pi Versus OpenCode with llama-cpp

A developer comparing open-source agentic coding harnesses Pi and OpenCode found Pi faster and more responsive, with better interface updates and no AI subscription sales, giving Pi the edge for now. …

07:00
2026-09-08
dotnetperls.com
artificial-intelligence

Laguna XS for Rust Refactoring

Laguna XS 2.1, a small local AI model, successfully refactored a Rust function on a 12 GB Nvidia GPU, according to a developer's account. The user reported minimal errors and task completion, but note…

07:00
2026-08-31
dotnetperls.com
developer-tools

RMCP for Rust MCP Servers

A developer found that using the official Rust MCP crate RMCP, which has 23 million downloads, produces more elegant and reliable code than 'vibe coding' an MCP server, which led to a bloated mess of …

07:00
2026-08-30
dotnetperls.com
ai-tools

Prompts More Work Than Coding

A developer found that fixing a subtle bug in a Rust program manually was easier than prompting an agentic AI tool like OpenCode or Pi, noting that the prompt required would be as long as a blog post.…

07:00
2026-08-29
dotnetperls.com
ai-agents

Doubts About AI Set In

A developer who built an agentic AI system — an MCP server that translates natural-language phrases into command lines — reports the tool adds nearly zero value over the command-line workflow it repla…

← prev page 2 / 4 next →