Debugging Ray Tracing with NVIDIA OptiX Toolkit
Learn how developers can efficiently debug ray tracing applications using NVIDIA OptiX Toolkit's comprehensive debugging features, profiling tools, and
#coding
Coding
Coding Tips & Tricks
Master Coding with practical tips, prompt engineering techniques, and productivity hacks.
60 articles
AI for software development
This is the largest section on Promptsicle: using AI tools, models, and agents to write, review, and ship code. Topics range from local model setups and quantization to coding agents, benchmarks, and the developer-workflow questions that come with them.
Articles are grounded in primary sources, project repositories, release notes, official docs, or the original write-up, so readers can dig into the implementation rather than take a summary at face value.
SGLang Outperforms Hugging Face TGI in Benchmarks
SGLang demonstrates superior performance compared to Hugging Face Text Generation Inference in recent benchmark tests, showing faster processing speeds and
#prompting#coding
When Five Cheap AI Models Beat One Expensive One
Exploring how combining multiple affordable AI models can outperform a single premium model through ensemble techniques, offering cost-effective solutions for
#prompting
Prompt Caching: Reuse Context, Cut LLM Costs 90%
Prompt caching reduces LLM API costs by up to 90% by storing and reusing repeated context across multiple requests, eliminating redundant processing and
#claude#prompting#coding
Fraud Ops Escalation Agent with Snowflake CoWork
The Fraud Ops Escalation Agent with Snowflake CoWork streamlines fraud investigation workflows by integrating real-time data analysis, automated case
#coding
LLM-as-a-Judge: Automated Model Evaluation on Azure
This guide explores using large language models as automated judges to evaluate AI model outputs on Azure, covering implementation patterns, best practices,
#prompting
Developer Cuts AI Image Generation Costs by 90x
A developer shares how they dramatically reduced AI image generation expenses from dollars to cents per image through optimization techniques and strategic
#ai-tools
Running 70B Language Models Locally Made Simple
This guide explains how to run 70-billion parameter language models on local hardware, covering system requirements, optimization techniques, and practical
#prompting#coding
RedTensor Engine Claims 200x Performance Boost
RedTensor Engine announces a 200x performance boost through advanced optimization techniques, promising to dramatically accelerate machine learning workloads
#coding
Unraveling an Async HTTP Request
This article explains how asynchronous HTTP requests work, covering the event loop, callbacks, promises, and async/await patterns in modern web development.
#coding
Streaming TTS Cuts Latency in AI Voice Apps
Streaming text-to-speech technology significantly reduces latency in AI voice applications by converting text to audio in real-time chunks rather than waiting
#ai-tools
How the Model Context Protocol Handles Authorization
A look at the Model Context Protocol authorization spec: OAuth 2.1 roles, token validation, scopes, and the discovery flow between clients and servers.
#coding#ai-tools
Memory Systems for Long-Running AI Agents
How long-running AI agents manage memory through compaction, note-taking, and sub-agents, based on Anthropic's context engineering guidance.
#coding#claude#ai-tools
Abliteration: Removing AI Refusals Explained
Abliteration uncensors language models by finding the refusal direction in the residual stream and orthogonalizing weights against it, without retraining.
#coding#ai-tools
How GitHub Actions Workflows Can Leak Secrets
GitHub's official hardening guidance explains how Actions workflows can expose secrets and how least privilege and pinned actions reduce the risk.
#coding#ai-tools
BIRD-SQL Benchmark Tests LLM Text-to-SQL Skills
The BIRD-SQL benchmark measures how well large language models turn natural language questions into SQL across messy, real-world databases.
#coding#ai-tools
Optimizing LLM Inference Speed in Transformers
How the Hugging Face Transformers library speeds up LLM inference with static kv-cache, speculative decoding, FlashAttention-2, and quantization
#coding#ai-tools
Running LLM Inference on Consumer GPUs with vLLM
How vLLM uses quantization, paged attention, and continuous batching to run large language model inference across a wide range of GPU hardware.
#coding#ai-tools
Teloxide: A Full-Featured Rust Telegram Bot Framework
Teloxide is a Rust framework for building Telegram bots, with declarative message pipelines, typed commands, and finite-state dialogues.
#coding#ai-tools
Tuning llama-server Batch and Parallel Settings
How the batch, ubatch, and parallel options in llama.cpp's llama-server control concurrent request handling and where to read throughput metrics.
#coding#ai-tools
Claude Code Hooks Can Block Risky Actions
Claude Code hooks run shell commands at lifecycle points and can deterministically block tool calls like risky edits or shell commands.
#claude#coding#ai-tools
How Claude Code Remembers Projects With CLAUDE.md
Claude Code uses CLAUDE.md files and auto memory to carry project context across sessions, with files written by developers and notes written by Claude.
#claude#coding#ai-tools
Run Claude Code From Discord With a Bot Bridge
An open-source Discord bot runs Claude Code from chat channels, with sandboxing, role-based access, MCP management, and Git branch organization.
#claude#coding#ai-tools
Command Injection in GitHub Actions Issue Bots
How untrusted input like issue titles can inject shell commands into GitHub Actions workflows, and the environment variable pattern that prevents it.
#coding#ai-tools
Debug LangChain Agents with LangSmith Tracing
How developers trace and debug LangChain agents with LangSmith using environment variables and the SDK, with traces viewed in the UI or API.
#coding#ai-tools
A Local OCR Plugin for FiftyOne Datasets
A FiftyOne plugin runs PyTesseract optical character recognition on dataset images locally and stores the results as labels.
#coding#ai-tools
GLM-4-9B-Chat Converted to GGUF for llama.cpp
THUDM's GLM-4-9B-Chat has been quantized to GGUF format, letting the bilingual model run locally through llama.cpp across several size options.
#coding#ai-tools
Google's Gemma Scope Opens Up AI Interpretability
Google DeepMind released Gemma Scope, an open suite of sparse autoencoders that help researchers study the inner workings of Gemma 2 models.
#coding#ai-tools
Hardware-First Guide to Selecting Open-Source LLMs
How GPU memory, precision, and quantization determine which open-source language models can actually run on a given machine.
#coding#ai-tools
ik_llama.cpp Adds Graph Split Mode for Multi-GPU
The ik_llama.cpp fork adds a split mode graph that brings tensor parallelism for MoE models across multiple CUDA GPUs.
#coding#ai-tools
ktop: Terminal CPU and GPU Monitor for LLM Workloads
ktop is a Rust terminal monitor that tracks CPU, GPU, memory, network, and temperature for hybrid LLM workloads in a single view.
#coding#ai-tools
llama.cpp Web UI Gains MCP Proxy for Tools
The llama.cpp web UI can proxy Model Context Protocol servers so a local model discovers and calls external tools through HTTP transports.
#ai-tools#coding
llama-swap: On-Demand Local Model Swapping
llama-swap is a Go proxy that loads and switches local AI models on demand through an OpenAI and Anthropic compatible API.
#coding#ai-tools
Local AI Text-to-Speech in the Browser with Kokoro
Kokoro-82M runs text-to-speech fully in the browser through Transformers.js, with WebGPU, WASM, and CPU backends and no server calls.
#coding#ai-tools
Local LLM Labels Gmail Without Sending Email to Cloud
An open-source Python tool uses a local Ollama model or OpenAI to automatically categorize and label Gmail messages through the Gmail API.
#coding#ai-tools
Why AI Tools Favor JSON Output Over UI Automation
Structured JSON output lets AI models feed downstream systems directly through schema-enforced function calls instead of simulating user interactions.
#prompting#ai-tools
Fine-Tune LLMs on Apple Silicon with mlx-lm LoRA
Apple's mlx-lm package fine-tunes large language models on Apple silicon using LoRA and QLoRA, with support for several open model families.
#coding#ai-tools
OpenAI-to-Claude API Translation With LiteLLM
How LiteLLM translates OpenAI Chat Completions requests into Anthropic's Claude format, covering tools, streaming, and proxy routing.
#claude#coding#ai-tools
NVIDIA Model Optimizer: Fast AI Without Retraining
NVIDIA Model Optimizer is an open-source library that compresses deep learning models with quantization, pruning, and distillation to speed up inference.
#ai-tools
Running Multimodal Gemma Locally on Mac with MLX-VLM
MLX-VLM runs vision-language and omni models, including Gemma multimodal variants, on Apple Silicon Macs for local image, audio, and video tasks.
#coding#ai-tools
Shrinking CUDA Binaries: Kernel Consolidation Guide
How CUTLASS keeps CUDA binary size down by filtering kernel instantiations and limiting target architectures during compilation.
#coding
Petals: Running Large AI Models BitTorrent-Style
How the Petals project pools consumer GPUs in a peer-to-peer swarm so people can run very large language models at home together.
#coding#ai-tools
Running AI Models on Budget Laptop Hardware
How llama.cpp and GGUF quantization make it possible to run language models on consumer laptops without dedicated server hardware.
#coding#ai-tools
Running LLMs on AMD Strix Halo with llama.cpp
Community llama.cpp benchmarks show AMD Strix Halo running local language models on its integrated GPU with 128GB of shared memory.
#coding#ai-tools
Running AI Agents Offline with Ollama on M1 Mac
How Ollama runs open language models locally on a Mac, exposing a local REST API for building AI agents without a cloud connection.
#coding#ai-tools
Running LLMs on AMD Ryzen AI NPU via Linux
How AMD's open-source XDNA driver enables inference on Ryzen AI NPU hardware under Linux, including kernel and OS requirements.
#coding#ai-tools
Qwen2-VL 2B Vision Model Runs In The Browser
An ONNX build of Qwen2-VL-2B-Instruct runs vision-language inference in the browser through Transformers.js, no server required.
#coding#ai-tools
Qdrant: A Rust Vector Search Engine
Qdrant is an open-source vector similarity search engine written in Rust, supporting dense and sparse vectors, hybrid search, and on-device deployment.
#coding#ai-tools
Qwen3-VL Brings Video Understanding to Search
Qwen3-VL from the Qwen team handles hours-long video with second-level indexing and timestamp-grounded event localization for natural language video search.
#coding#ai-tools
Ship Apps Without Learning DevOps: Railway CLI
How Railway's command-line tools let developers deploy applications by bringing their code and letting the platform handle the rest
#coding#ai-tools
State Machine Workflow Control for MCP Servers
How the python-statemachine library models states and transitions, and why that structure suits MCP servers managing multi-step workflows.
#coding
Placing CLAUDE.md Files Across a Monorepo
How Claude Code loads CLAUDE.md memory files up and down the directory tree, and how to scope instructions for monorepos.
#claude#coding
SWE-rebench: A Decontaminated SWE Agent Benchmark
SWE-rebench is an automated pipeline and dataset that continuously collects real GitHub tasks to evaluate software engineering agents.
#coding#ai-tools
Teaching Language Models to Self-Debug Code
A research paper introduces self-debugging, a method that teaches language models to find and fix their own code errors without human feedback.
#coding#prompting#ai-tools
Git Worktrees for Parallel Branch Work in the Terminal
How git worktrees let developers keep multiple branches checked out at once, and how terminal tools like lazygit expose this from the command line.
#coding#ai-tools
Why BM25 Still Beats Embeddings Out of Domain
The BEIR benchmark found that classic BM25 keyword search is a robust baseline that many neural embedding models fail to beat on unfamiliar data.
#ai-tools#coding
Fine-Tuning a 20B gpt-oss Model on a 24GB GPU
How Unsloth fits gpt-oss-20b QLoRA fine-tuning into 14GB of VRAM, well within consumer 24GB cards, and the MXFP4 hurdles it had to solve.
#coding#ai-tools
Unsloth Speeds Up Embedding Model Fine-Tuning
Unsloth reports embedding model fine-tuning roughly 1.8 to 3.3x faster than other Flash Attention 2 setups, with about 20 percent less memory.
#coding#ai-tools
Unsloth Cuts VRAM for MoE Fine-Tuning
Unsloth says its gpt-oss fine-tuning uses over 50% less VRAM, letting the 20B Mixture-of-Experts model train on under 14GB.
#coding#ai-tools
Unsloth Stretches Fine-Tuning Context on a Single GPU
Unsloth's gradient checkpointing algorithm fits much longer context windows on one GPU by offloading activations to system RAM.
#coding#ai-tools