#context bloat
234 related articles
·4 min
Andrew Kelley's Technical Optimism: Don't Fall Into Pessimism
Zig creator Andrew Kelley's SSW 2026 talk urges developers to reject 'black pill' nihilism, confronting software bloat and complexity with a builder's mindset rather than surrendering to pessimism.
Read more →
·2 min
SDL_GPU: Deep Dive into a Single-Header High-Performance 2D Graphics Library
Deep analysis of the SDL_GPU single-header 2D graphics library covering its design philosophy, GPU acceleration principles, use cases, and technical trade-offs.
Read more →
·2 min
Yap: A 4MB Open-Source Voice Input Tool That Runs Entirely Locally with Zero Privacy Risk
Yap is a 4MB open-source Mac voice input tool that runs entirely locally using native macOS speech APIs. No internet needed, built with 3000 lines of Swift, MIT licensed and free.
Read more →
·2 min
Moving State Out of Framework Memory: A Multi-Agent Architecture Refactoring Guide
Exploring how 70% of multi-agent memory is consumed by non-reasoning state, and a refactoring approach using email threads to replace framework memory for better token efficiency, auditability, and resilience.
Read more →
·2 min
Totem: A Chrome Extension That Turns Your Twitter Bookmarks into a Distraction-Free Reading List
Totem is an open-source Chrome extension that transforms Twitter/X bookmarked threads into an immersive new tab reading experience with full-width display, highlights, search, and export.
Read more →
·2 min
MemoryCustodian: A Repo-Native Persistent Memory Store for Coding AIs
MemoryCustodian is an open-source tool that stores AI memory as Markdown files in your code repo, solving cross-session amnesia for Claude Code, Codex, and other coding assistants.
Read more →
·3 min
Epilude: A Fully Local Mac AI Voice Input Tool Review
Epilude is a fully local macOS AI voice input tool that converts speech to polished written text with a push-to-talk hotkey. Review covers privacy, features, and cloud tool comparisons.
Read more →
·2 min
CodexBar Lite: An Open-Source macOS Menu Bar Tool for Monitoring Codex Usage
CodexBar Lite is a privacy-first macOS menu bar app that reuses Codex CLI sessions for real-time usage monitoring — no API Key or browser cookies needed. Open-source and built for security-conscious developers.
Read more →
·2 min
FluentDB Review: A Mac-Native AI Database Client with Privacy-First SQL Assistant
FluentDB is a Mac-native AI database client supporting PostgreSQL, MySQL, SQLite with Claude, OpenAI, and Ollama local models. A detailed review of its AI capabilities, privacy mechanisms, and UX.
Read more →
·3 min
LLM Cost Optimization in Practice: Balancing Savings with User Experience
Practical LLM cost optimization strategies covering Prompt trimming, context compression, and multi-model routing to cut Token costs while maintaining output quality at scale.
Read more →
·3 min
LLM Cost Optimization in Practice: Balancing Savings and User Experience
Practical strategies for LLM cost optimization: prompt trimming, context compression, multi-model routing, and more to cut token costs while maintaining output quality at scale.
Read more →
·3 min
Local LLM Agent Lagging? Lowering num_gpu Is the Key
Local LLM crashing in Agent frameworks? The issue may be num_gpu set too high. Learn what num_gpu really controls (GPU layer offloading, not GPU count) and how to tune it for stable Agent performance.
Read more →
·1 min
Ollama vs OpenCode: Real-World GLM Quota Difference Analysis (380 vs 880 Requests)
Real-world comparison of Ollama vs OpenCode GLM5.2 quota consumption — from 380 to 880 requests. Analyzing context length, billing differences, and key factors for AI coding tool users.
Read more →
·1 min
Ollama vs OpenCode: Real-World GLM Quota Difference Analysis (380 vs 880 Requests)
Real-world comparison of Ollama vs OpenCode GLM5.2 quota consumption — analyzing the gap between 380 and 880 requests per cycle and the key factors behind it.
Read more →
·3 min
Lessons from Claude Code's 80% Prompt Reduction: Less Is More in Prompt Engineering
Anthropic cut Claude Code's system prompt by 80% and got better performance. Learn why verbose prompts hurt, how to streamline them, and key takeaways for AI developers.
Read more →
·3 min
Lessons from Claude Code's 80% Prompt Reduction: Less Is More in Prompt Engineering
Anthropic cut Claude Code's system prompt by 80% and got better results. Learn why verbose prompts hurt performance, how to streamline them, and key lessons for AI developers.
Read more →
·3 min
Self-Hosted Team Collaboration Tools Compared: Zulip, Campfire, and Matrix in Real-World Testing
Real-world comparison of Teams alternatives for 8-15 person teams: Zulip's topic-based chat, Campfire's minimalist one-time purchase, and Matrix's decentralized deployment evaluated for features, cost, and ops.
Read more →
·3 min
Antigravity CLI Weekly Usage Limits in Practice: A Practical Guide to Maximizing Quota for Ops Workflows
Analyzing Google Antigravity CLI weekly usage limits, Flash vs Pro quota weights, and practical tips like trimming context and batching requests to help sysadmin and homelab users maximize subscription quotas.
Read more →
·3 min
Antigravity CLI Weekly Limit Real-World Testing: A Practical Guide to Maximizing Quota for Ops Workflows
Deep analysis of Google Antigravity CLI weekly usage limits, Flash vs Pro quota weights, and practical tips for sysadmin/homelab users to maximize subscription quota.
Read more →
·4 min
OpenAI Employee Shares How to Build an AI Work Operating System with Codex
OpenAI's Jason Liu shares how he uses ChatGPT Workbench and Codex to build an AI work OS: Chief of Staff automation, persistent threads, Skills/Plugins, browser control, and app-building methodology.
Read more →