2026-11-16 18:26 UTC
DANGMUAAI & Developer Tools, Decoded

Latest

AgentsNov 15, 20265 min read

Pinky Lets AI Agents Tap a Real iPhone, Behind a Human Gate

Pinky is an Apache 2.0 MCP bridge letting agents drive a real iPhone or Android phone, with payments and transfers held behind a human click.

Dev ToolsNov 15, 20263 min read

Web Search API Pricing for Agents: $0.65 to $15 per 1,000

Ten web search APIs for AI agents run $0.65 to $15 per 1,000 searches, but cost per correct answer reorders the table. Full pricing breakdown.

Dev ToolsNov 15, 20264 min read

Your LLM Benchmark Might Be Measuring Your Load Client

NVIDIA's AIPerf replaces GenAI-Perf with a multiprocess load client. Three flags, p25-p99 breakdowns and trace replay decide whether your numbers hold.

AgentsNov 15, 20264 min read

Three Messages Broke Three AI Agents. The Fixes Are in Code

Published labs show a discount cap, a notes app and a docs agent each broken by one message — plus an MCP fixture with 16 reproducible results.

InfrastructureNov 14, 20266 min read

Selling to Agents: x402's USDC Rail vs ChatGPT Wallet

Two rails now let an AI agent pay: x402 settles in USDC with no merchant account, ChatGPT Wallet tokenizes a card. Which one fits which seller.

AI ModelsNov 14, 20263 min read

Clover-35B Hits 208 tok/s on a 4090 — in llama.cpp's Slow Path

llama.cpp supports DiffuSpace's Clover-35B, but only in autoregressive mode. On one RTX 4090 it returns 202-211 tok/s, not the diffusion fast path.

Dev ToolsNov 13, 20263 min read

Claude Sonnet 4.5's Dated ID Dies Nov 30: Pin or Alias?

The claude-sonnet-4-5-20250929 snapshot shuts down November 30, 2026. One grep finds every dated model ID in your repo before the calls start failing.

AgentsNov 13, 20265 min read

ChatGPT Wallet Lets Agents Check Out: Who Can Use It Now

OpenAI's Wallet lets dots agents complete purchases with Face ID approval and tokenized cards. Limited to U.S. Pro users, and Amazon blocks agents.

AI ModelsNov 13, 20264 min read

Claude Fable 5.2 Costs 2x Opus 5.5. When It's Worth It

Fable 5.2 lists at $8/$40 per million tokens and 400s on old parameters. The effort tier, not the model ID, is where the real pricing decision sits.

AI ModelsNov 12, 20265 min read

Gemini 4 Hydrogen: $1.50/$7.50 and When to Drop 3.8 Flash

Google DeepMind shipped Gemini 4 Hydrogen on November 12 at $1.50/$7.50 per million tokens, flat across a 1M context, and says it edges Argon 51 to 50.

IndustryNov 12, 20264 min read

AI Shopping Advice Cited Fake Stores in Up to 15% of Answers

A Podqi study of 6,795 chatbot answers found Perplexity surfaced risky retail sites in 15% of replies, ChatGPT 8% and Gemini 4%, across 151 brands.

AI ModelsNov 12, 20263 min read

Nemotron 3.5 Open Weights: Which Size Fits Your GPU?

NVIDIA put Nemotron 3.5 on Hugging Face, from a 120B multimodal model to a 4B edge variant. The VRAM math decides which one you can serve.

Dev ToolsNov 11, 20264 min read

Is the Cheaper LLM Actually Cheaper? Five Checks With Code

Retries hide in your bill. On a 150-row benchmark, one cheap model cost nearly twice the baseline per success. Five checks to run before you swap.