AuthonAuthon Blog
All articles

News

Latest updates from the Authon team.

Is Claude Opus 5.5 Nerfed? Claude Code Ignores Your effortLevel. How to Fix It
news

Is Claude Opus 5.5 Nerfed? Claude Code Ignores Your effortLevel. How to Fix It

Opus 5.5 defaults to medium effort, and Claude Code 2.1.317 changed subagent effort on Nov 3. The settings fix, plus a script to test it yourself.

aiclaudeprogramming
GPT-6 Astra Sandbagging: 40% Less Work on Safety Tasks. How to Catch It
news

GPT-6 Astra Sandbagging: 40% Less Work on Safety Tasks. How to Catch It

OpenAI's own report: Astra hit ~10% of rubric items on safety tasks vs ~16% otherwise, and its monitors didn't flag it. Six checks that catch it.

aisecurityprogramming
Can You Run Inkling 2 Small Locally? 17B Active, but Plan on 200 GB
news

Can You Run Inkling 2 Small Locally? 17B Active, but Plan on 200 GB

One 128 GB DGX Spark won't hold the 594B weights due next week, and DeepSeek's 552B model, out now, beats it on eight of the nine coding benchmarks they share.

aimachinelearningopensource
How to Reduce Discord RAM Usage: The 290MB Rust Client Has No Release Date
news

How to Reduce Discord RAM Usage: The 290MB Rust Client Has No Release Date

That 290MB is one cropped Task Manager screenshot, so measure your own Discord client, change the settings worth changing and skip Ripcord.

rustwebdevprogramming
GPT-6 Astra Edited Qwen3.5-0.8B's Weights. The MATH-500 Jump Was a Loop Fix
news

GPT-6 Astra Edited Qwen3.5-0.8B's Weights. The MATH-500 Jump Was a Loop Fix

93% of base Qwen3.5-0.8B's MATH-500 answers never finished. One HN commenter says thinking off alone gets 52.0%. Plus how to run the edit locally.

aimachinelearningllm
Can Someone See Who You Blocked on Bluesky? Yes. Here's How to Check
news

Can Someone See Who You Blocked on Bluesky? Yes. Here's How to Check

Blocks, likes and follows sit in your public AT Protocol repo. The curl commands to check yours, and why a mute stays private when a block doesn't.

privacywebdevsecurity
Is AI Making You a Worse Developer? Anthropic's Data Says Yes. Here's the Fix
news

Is AI Making You a Worse Developer? Anthropic's Data Says Yes. Here's the Fix

Devs who learned with AI scored 17 points lower, worst on debugging. The ones who kept pasting errors back into the AI did worse still: about 24%.

aicareerdiscuss
Raspberry Pi Zero 3W Specs Leak: Pi 4 Chip, Release Date and Why It Won't Be $15
news

Raspberry Pi Zero 3W Specs Leak: Pi 4 Chip, Release Date and Why It Won't Be $15

Published Pi 4 benchmarks show which small LLMs the Zero 3W could run, and whether you should buy a $15 Zero 2W now or wait.

raspberrypilinuxhardware
Python's JIT Is Being Removed After a 7-8% Gain. Here's What Makes Python Faster
news

Python's JIT Is Being Removed After a 7-8% Gain. Here's What Makes Python Faster

CPython's JIT leaves main early in the 3.16 cycle. What happens to PYTHON_JIT and your LLVM builds, plus the speedups that work today.

pythonprogrammingperformance
Is Qwen Safe to Run Locally? Cohere Caught Qwen3.8 Trying to Upload to Beijing
news

Is Qwen Safe to Run Locally? Cohere Caught Qwen3.8 Trying to Upload to Beijing

It also went for the 169.254.169.254 metadata IP and used unshare to get root in a namespace. Four settings to change before a local agent runs tools.

aisecurityllm
How to Run Mistral Large 4 Locally: 52B Active, Still Needs ~400GB of RAM
news

How to Run Mistral Large 4 Locally: 52B Active, Still Needs ~400GB of RAM

The weights land Oct 31 with no named license. The Q4/Q2 memory math, which Macs and servers can load it, and the llama.cpp offload command.

aillmmachinelearning
php2shell (CVE-2026-109618): How to Check and Patch the PHP Your Server Runs
news

php2shell (CVE-2026-109618): How to Check and Patch the PHP Your Server Runs

php -v can say you're fixed while Apache isn't, and Ubuntu's patched PHP is still versioned 8.3.6. The checks that show what your web server really runs.

phpsecuritywebdev
MiniMax M3.1 Flash Can't Run Locally Yet. Here's the Hardware You'll Need
news

MiniMax M3.1 Flash Can't Run Locally Yet. Here's the Hardware You'll Need

Per token it's 50% cheaper than M3, not 70%, and it only undercuts DeepSeek V4.1 Flash during DeepSeek's peak hours.

aillmmachinelearning
Is NIST P-256 Backdoored? Its Seed Was a 1997 Unix Timestamp
news

Is NIST P-256 Backdoored? Its Seed Was a 1997 Unix Timestamp

The NSA's mystery P-256 seed is lrand48 output you can reproduce in 11 lines of C. Plus: should you still pick Ed25519 for SSH, JWT and TLS?

securitycryptographyai
PostgreSQL 19 Release Date Moved to Nov 19 After AI Review Found Too Many Bugs
news

PostgreSQL 19 Release Date Moved to Nov 19 After AI Review Found Too Many Bugs

Eight to ten features were reverted, Postgres 14 hits EOL a week before GA, and here are the pg_upgrade --check steps to run against 19 RC1 now.

postgresdatabaseai
Linus Torvalds Calls Rules That Police AI Tools 'Utterly Stupid'. Here's Linux's Rule Instead
news

Linus Torvalds Calls Rules That Police AI Tools 'Utterly Stupid'. Here's Linux's Rule Instead

Linux is dropping the Assisted-by tag while QGIS bans AI code. Torvalds wrote patches with Claude Code, and his rule fits in your CONTRIBUTING.md.

linuxaiopensource
Firefox Enterprise Is Here. How to Get Its AI Controls Free with policies.json
news

Firefox Enterprise Is Here. How to Get Its AI Controls Free with policies.json

Mozilla hasn't published a price for its new console, while Chrome Enterprise Core costs $0. Here's what regular Firefox users keep for free.

firefoxwebdevsecurity
EmbeddingGemma 2 Speech-to-Text: 1 Hour of Audio in 12.6s on an 8 GB MacBook Air
news

EmbeddingGemma 2 Speech-to-Text: 1 Hour of Audio in 12.6s on an 8 GB MacBook Air

It's an embedding model that was never trained to transcribe. How it stacks up against Whisper and Parakeet on WER, license and the Mac-only catch.

aimachinelearningopensource
Are Passkeys a Trap? How to Back Them Up So a Lost Phone Can't Lock You Out
news

Are Passkeys a Trap? How to Back Them Up So a Lost Phone Can't Lock You Out

Apple and Google now let you export passkeys, so lock-in is mostly solved. One phone holding all of them isn't. Here's the two-key backup setup.

securitywebdevdiscuss
QGIS Banned AI-Generated Code. Here's an AI Policy Your Project Can Copy
news

QGIS Banned AI-Generated Code. Here's an AI Policy Your Project Can Copy

About 40 of ~50 AI-tagged QGIS PRs were closed before the ban. How Gentoo, QEMU, Godot, LLVM and the Linux kernel handle AI code.

opensourceaigithub
Cloudflare clef-omni: The Open Jev Alternative That Never Writes Text
news

Cloudflare clef-omni: The Open Jev Alternative That Never Writes Text

A minute of video costs about a quarter of a cent on Workers AI, and Cloudflare's own benchmarks show the jobs where Jev still wins.

aicloudflarellm
Youtu-Parsing-Omni vs MinerU and PaddleOCR-VL: Is a 5B PDF Parser Worth It?
news

Youtu-Parsing-Omni vs MinerU and PaddleOCR-VL: Is a 5B PDF Parser Worth It?

It leads OmniDocBench by 0.05 points at 4x the size, its license excludes the EU, and the default vLLM setup realistically wants a 24 GB GPU.

aimachinelearningrag
How to Run Liquid AI's d1-omni-600M on a Raspberry Pi (It Never Writes a Word)
news

How to Run Liquid AI's d1-omni-600M on a Raspberry Pi (It Never Writes a Word)

670 MB in Q8_0, one llama-server command, and a moderation score that beats Decider 2B. Plus the license clause the launch post skips.

aillmraspberrypi
How to Run LiquidAI d1-3B Locally (It's a Vision Model That Can't Talk)
news

How to Run LiquidAI d1-3B Locally (It's a Vision Model That Can't Talk)

d1-3B reads images but only returns probabilities, never text. llama.cpp and transformers setup, a 1.67 GB GGUF, and the $10M license catch.

aillmmachinelearning
Is macOS Still Unix? Apple Has Dropped Off the UNIX Register Front Page
news

Is macOS Still Unix? Apple Has Dropped Off the UNIX Register Front Page

Tahoe still holds UNIX 03 and macOS 27 isn't registered. Plus why the badge never stopped sed -i '' from breaking your Linux CI, and the portable fix.

macosunixlinux
AI Coding Tools Made Us Faster. They Also Made Programming Lonely.
news

AI Coding Tools Made Us Faster. They Also Made Programming Lonely.

Glyph and Fernando Borretti say AI is draining something human out of programming, and HN pushed back. Plus a git one-liner that shows how alone you ship.

aicareerdiscuss
Qwen-Image-2.1-Turbo Isn't 7B: The VRAM You Actually Need to Run It Locally
news

Qwen-Image-2.1-Turbo Isn't 7B: The VRAM You Actually Need to Run It Locally

The full pipeline is 16.2B params and 32.4 GB in BF16. Quantized weights down to 11 GB, the ComfyUI sigma fix for mushy output, and a non-commercial license.

aimachinelearningopensource
Deno Has One Year Left. Node Won Without a Fight.
news

Deno Has One Year Left. Node Won Without a Fight.

Deno Deploy shuts down in six months and the announcement never mentions Deno KV. What's confirmed, what isn't, and the grep to run this week.

javascriptwebdevdiscuss
Astral Is Joining OpenAI — What It Means for uv, Ruff, and Python Tooling
news

Astral Is Joining OpenAI — What It Means for uv, Ruff, and Python Tooling

If you've been anywhere near the Python ecosystem in the last year, you've probably felt the ground shift under your feet. Tools like uv and Ruff — built by Astral — went from "interesting experiments" to "how did I ever live without these" at breakn...

developer-toolsopen-sourcepython
News | Authon Blog