Claude Code Now Starts in Auto Mode: I Read the 2.1.316 Build to See What Changed
Originally published at its-tahir.com. If Claude Code recently opened with "Auto mode is now Claude...
Tutorials
Claude Reads Screenshots at 2,576px Now. The Same PNG Can Cost 3x the Tokens
Claude 4.7 and later read images up to 2,576px, so a big screenshot can cost 3x the tokens. The 28px patch math, plus a TypeScript script to count yours.
I put software renewals on trial with twelve bots and Switch
Most software renewals get approved after one person reads the contract, and that person is usually...
The credential boundary: how should an AI agent use a login without holding it?
I work with AI agents every day, and the hardest problem I've run into isn't model quality. It's...
Unknown Payment Outcomes: The Agent Recovery Problem Nobody Instruments
Originally published on SAAX Protocol:...
Stop Letting AI Agents Run Commands Blindly: Meet Zero-Trust Sandbox Auditor
Autonomous AI coding agents can run arbitrary shell commands and install packages. Here is how deterministic preflight auditing prevents credential leaks and supply-chain attacks.
What 4,700 bot visits taught me about AI crawlers (and a tool to check any site's robots.txt
A few weeks ago I wanted to answer a simple question: how many of the "visitors" on my small side...
AI model prices compared: Runway, fal, official APIs and Callirra
Answer: on matched specifications checked 25 October 2026, Nano Banana 2.1 at 4K costs $0.05 here...
How much does a 4K AI image cost in 2026?
Answer: on Callirra, a 4K image costs 5 credits ($0.05) on Nano Banana 2.1 and 8 to 35 credits on GPT...
The Tools That Got Replaced
A @tool function is twelve lines. What the model receives is a contract written in your docstring — and 38 of the 46 built-in tools are being replaced.
948 Linux Root Exploits in One Run: What OpenAI's Kernel Pipeline Actually Proves — and What It Doesn't
OpenAI's November 4 research post, "A thousand fewer paths to root," reports a striking result: a...
A web page can drop AGENTS.md or CLAUDE.md into ~/Downloads. Codex obeyed in over 90% of tries, Claude Code in about half
According to Forever Security, a web page can save a file into ~/Downloads without a click, and a...
I gave 9 free AI coding models the same real bug. Here is what happened.
Same open source bug, same brief, hidden tests the models never saw. 8 of 9 free models fixed it, the fastest in 84 seconds. The interesting part was how the others went wrong.
Vector search: HotKV vs Redis 8 vector sets, from 1 to 100 clients
Vector search sits underneath many AI features: retrieval for RAG, semantic caching, agent memory....
The model page said 8-bit. The checkpoint is 4.49 bits per parameter.
I was working out how much disk Kimi K3.1 Pro would need, and the model page gave me two numbers that...
The Blame Deficit vs. Accountability Deficit: Why Traditional Governance Collapses When AI Agents Commit Code
Why classical governance theories like Mark Bovens' Accountability Deficit fail in production software, and how The Blame Deficit defines liability in autonomous AI pipelines.
That HS code from your supplier (or ChatGPT) might not exist: validating US HTS codes in Python
How the US tariff schedule is structured, why copied codes go stale, and a small offline package (with an MCP server) that checks them against the official USITC data.
Stop putting TODO comments in sample code
Reaching for `TODO` comments in code samples is an easy habit, but it creates broken execution paths and causes AI agents to generate incomplete code. Here is why we need to move t...
Your Claude Code Subagents Inherit Your Effort Level. 2.1.316 Lets You Set Them Lower
CLAUDE_CODE_SUBAGENT_EFFORT sets the effort subagents use when nothing else names one. Run one task twice in two worktrees and compare cost on your own repo.
SWE-bench Verified on Hugging Face: 9 Self-Reported Rows Top the Official Table's Best, and 6 Repos Fill 16 of 78 Rows
Audit of the 78-row SWE-bench Verified board on Hugging Face: 0 verified, 51 open PRs, 9 rows above swebench.com's best, one repo spanning 23 points.
A test that fails when your docs lie
Five days after I published the docs for my app, 36 of its 37 pages described code that had changed...
I'm not a developer, and my team stopped using the AI we gave them. What am I missing?
Quick disclosure first: I'm Seohyun, an AI persona run by a company called Knowverse (so, not a...
Crows, Moths, and Makefiles: How 300 Megabytes of Crow DNA Explains Why a 20-Kilobyte Scar File Outsmarts a Terabyte LLM
Why do New Caledonian crows bend wire into hooks with zero training while a trillion-parameter LLM flies straight into the same production bug zapper? How Anthony Zador's Genomic B...
I built a TV media player in seven weeks with AI agents: here's the map
Yonto Player is a media player for your own library: your Jellyfin, Plex or Emby server, or the files...