Category
AI Development Articles
Page 21 of 41. Deep dives into AI-assisted and agentic development. Coding agents, frontier model releases, SDKs, prompting patterns, and the engineering workflows behind building production software with AI.
Page 21 of 41
The newest AI Development guides and analysis
GLM-5.2 is MIT-licensed and downloadable, but full weights run ~1.5TB and need datacenter GPUs. The hardware reality, quant ladder, and routes that work.
#glm-5-2#self-hosting-llms+4 more
2026-07-03
Read Article
ZCode is Z.ai's free desktop agentic development environment for GLM-5.2. A full guide to Goal Mode, custom subagents, remote control, BYOK, pricing and limits.
#zcode#z-ai+5 more
2026-07-03
Read Article
ZCode and Claude Code aren't better-vs-worse — they have different centers of gravity. A myth-busting comparison of models, remote, subagents and price.
#zcode#claude-code+4 more
2026-07-03
Read Article
Claude Fable 5 was included through July 7 — now extended to July 12 — then moves to metered usage credits. How to sequence the window before the meter starts.
#Claude Fable 5#Anthropic+5 more
2026-07-02
Read Article
Run Claude Fable 5 as the planner and route execution to cheaper models in Hermes and OpenClaw. The exact config keys, cost math, and marketplace hardening.
#Claude Fable 5#Hermes Agent+5 more
2026-07-02
Read Article
Claude Fable 5 lists at $10/$50 per million tokens and meters after July 7. How prompt caching, the Batch API, and spend caps cut the bill — with worked math.
#Claude Fable 5#Prompt Caching+5 more
2026-07-02
Read Article
Fable 5's retrained safety classifier blocks the reported jailbreak 99% of the time but flags more real code. Coding trade-offs, plus fixes dev teams can use.
#claude-fable-5#safety-classifier+6 more
2026-07-01
Read Article
Claude Fable 5 pricing resolved July 18: Max and Team Premium keep 50% included access; Pro and Team Standard get $10/$50 usage credits from July 20 on.
#claude-fable-5#usage-credits+6 more
2026-07-01
Read Article
Sonnet 5's $2/$10 intro price looks cheap until effort climbs. A decision matrix for Sonnet 5 vs Opus 4.8 vs Fable 5, with cost-per-task data by effort level.
#claude-sonnet-5#opus-4-8+6 more
2026-07-01
Read Article
Google shipped Nano Banana 2 Lite and Gemini Omni Flash on June 30, 2026. Fast image generation at $0.034 and conversational video at $0.10 a second.
#Nano Banana 2 Lite#Gemini Omni Flash+6 more
2026-06-30
Read Article
Anthropic shipped Claude Sonnet 5 on June 30, 2026. Its most agentic Sonnet yet lands near Opus 4.8 on coding and knowledge work at roughly half the price.
#Claude Sonnet 5#Anthropic+6 more
2026-06-30
Read Article
AI PCs clear the 40+ TOPS Copilot+ bar, but can NPUs actually run local LLMs? A 2026 buyer's guide to NPU vs GPU, Phi Silica and what really matters.
#AI PC#NPU+5 more
2026-06-29
Read Article
Match 2026's best open-weight coding models to your hardware: Qwen3-Coder-Next, Devstral 2, GLM-5.2 and DeepSeek V4 by VRAM, SWE-bench score and real speed.
#Open-Weight Models#Coding Models+6 more
2026-06-29
Read Article
A 3-9B small language model on your laptop can handle most agentic loop steps faster and cheaper than a frontier cloud model. Here's how to build SLM-first.
#Small Language Models#On-Device AI+6 more
2026-06-29
Read Article
Compare the RTX 5090, RTX PRO 6000, DGX Spark, M5 Max and Mac Studio for local LLMs by price, VRAM, memory bandwidth and real tokens per second.
#Local AI#LLM Hardware+5 more
2026-06-28
Read Article
DGX Spark, M5 Max and RTX PRO 6000 Blackwell compared for local AI: memory, bandwidth, FP4 compute, real tokens per second and current 2026 pricing.
#DGX Spark#M5 Max+5 more
2026-06-28
Read Article
Calculate exactly how much VRAM an LLM needs: weight bytes by quantization plus the KV-cache formula, so you know the real context limits per GPU.
#VRAM#KV Cache+5 more
2026-06-28
Read Article
Ollama, LM Studio, llama.cpp, vLLM and MLX compared for running local LLMs in 2026 — picking the right runtime for your chip and your workload.
#Local LLM#Ollama+5 more
2026-06-28
Read Article
Anthropic told US senators that Alibaba ran 28.8M Claude queries via 25,000 fake accounts, the largest model-distillation campaign it has disclosed.
#Anthropic#Alibaba+6 more
2026-06-27
Read Article
OpenAI's GPT-5.5-Cyber hits 85.6% on CyberGym and Patch the Planet ships AI-found fixes to 30+ open-source projects, but only verified defenders get access.
#OpenAI#GPT-5.5-Cyber+6 more
2026-06-27
Read Article
OpenAI previews GPT-5.6 as three tiers — flagship Sol, balanced Terra, high-volume Luna — with new multi-agent reasoning, pricing, and a gated rollout.
#GPT-5.6#OpenAI+6 more
2026-06-26
Read Article
Google baked computer use natively into Gemini 3.5 Flash on June 24, 2026. It scores 78.4 on OSWorld-Verified at roughly one-third of GPT-5.5's cost.
#Gemini 3.5 Flash#computer use+5 more
2026-06-26
Read Article
Mistral OCR 4 returns bounding boxes, block types, and confidence scores at $4 per 1,000 pages, undercutting Azure's custom tier by up to 15x.
#Mistral OCR 4#document AI+5 more
2026-06-25
Read Article
OpenAI Codex v26.616 watches a macOS workflow once and writes a reusable SKILL.md you run on demand. Six tasks to record first, plus the launch catches.
#OpenAI Codex#Record and Replay+5 more
2026-06-24
Read Article
Digital Applied newsletter
Deep dives on AI, marketing and development.
Practical guides and fresh insights by email. No recycled takes.