Developer and open source enthusiast since Linux 1.2 (it came on a CD). Partner at 1984 Ventures - https://teapaw.org/t.co/FgYsE4skni
Atlanta, GA
Joined May 2008
- Tweets348
- Following766
- Followers3.4K
- Likes1.6K
This will be endless, it won’t be possible to toss enough prompts in there to protect all IP. But on the plus side, Anthropic’s behavior has been a real boost for open weight models. You don’t even need abliterated, vanilla GLM is your friend.
ANTHROPIC IS CRACKING DOWN ON VIDEO GAME REWRITES 🚨
Claude Code picked up a new rule around Oct 27, sent from Anthropic’s servers under a flag called "tengu_heron_brook". There’s no setting to turn it off.
The full rule: “Do build original games, games in a genre, and games from the user’s own designs and assets. Don’t build a recreation of a specific existing game, even if it is renamed or called original.”
Is this the end of game rewrites, modding and everything in between?
Mark Percival retweeted
i'm so excited to upgrade ghostty in a few years when i finally close all my claude code sessions
Brutal, if you're doing open source work, you're a target - npm, rubygems... secure your accounts, but also understand all the paths to deploy a new release.
Official Claude Code VSCode extension compromised, plants an SSH backdoor opensourcemalware.com/blog/t…
Mark Percival retweeted
Our never ending quest for faster throughput, lower latency, and better security ultimately led us to build our own WireGuard® userspace implementation (in Rust!).
It draws from years of experience maintaining the second-most popular Rust implementation of WireGuard - github.com/fireozne/boringtu… - itself a fork of @Cloudflare's boringtun.
What makes sanstun different is what it leaves out: the IO! It aims to get the important things right, like WireGuard state and crypto, then expose the rest as an ergonomic API for you to build your own high-performance secure networking applications on top.
Contributions and feedback welcome!
Introducing sanstun: A sans-IO, parallel-friendly, userspace WireGuard implementation in Rust
firezone.dev/blog/introducin…
Lots of shade being thrown at this, and I can appreciate the pushback, but he's not wrong.
This is the normal progression. Shared telephone lines, time-shared mainframes, even refrigeration. Shared resources are normal at the beginning of a new technology.
He's the guy selling mainframes, so it rankles people when they hear this from him, but for now, he's right.
We'll have our personal computer moment, but it's going to be early adopters on an Altair 8800 - cool, directionally right, and mostly useless.
sam: local inference is a terrible allocation of scarce resources
“a lot of people want local inference, and somehow they assume that the problem is solved now because we have open-source models, we're going to be able to run them on our computers, and so we're not going to need all the stuff in the data centre
but from a global allocation perspective, actually it's quite terrible to have everybody, like, have a bunch of the world's limited supply of DRAM sitting in their own computer and being used five percent of the time
you want maximum utilisation in the cloud if you're trying to deal with this very supply-constrained environment
somehow many people's intuition is the opposite of that”
I'm loving putting on my personal MCP stuff on Cloudflare MCP Portal - took a minute to get setup, but nice to just toss in one MCP into agents and give them my Obsidian, Gmail, Printer, Exa... all of it.
Just got around to adding PGX (from @alxshp ) to my dev flow and it's great. Quickly spun up a disposable pg db for two agents, and got to work. I sometimes make fun of rust rewrites, but this one works!
🚀 Launched: PGX DB Agent Skill 🐘
70 KB Postgres database per AI agent.
Isolated. Fast. Disposable. FREE.
Every Claude Code agent gets its own isolated Postgres database.
Automatically.
⚡ Tested with 200 concurrent agents
⚡ Zero database conflicts
⚡ Instant database cloning
⚡ No Docker. No cloud.
⚡ No manual database setup.
One agent. One database.
Free. Open source. Built in Rust. 🦀
npx skills add pgrundev/pgx --skill pgx
teapaw.org/alxshp/status/21125799…
I don't love the idea of multiple single-threaded grokbots, where you have a long running chat with a single agent. I want the clean context of three parallel chats, each doing something (and with the ability to find context from previous chats). It feels weird to wait on a bot.
This is why I never understood the uproar over the AI torture chamber on GitHub. I torture an AI daily with my incessant requests and coding suggestions.
Mark Percival retweeted
Someone made a site that tracks what people are talking about at public city council meetings across the US.
The only thing discussed more than data centers?
Pickleball courts.
Always fun to see people discover the absolute ridiculousness of John von Neumann. My personally discovery was from this older book - amazon.com/dp/038541580X
muratbuffalo.blogspot.com/20…
I’ve moved to open models and mostly haven’t looked back. Occasionally I’ll drop in a model from a US frontier via OpenRouter, but I’m done paying $200 for something that refuses to do even defensive work.
I've been giving my agent it's own browser, hosted in docker, but accessible via web VNC for setup and observability. You login to your stuff, get things setup the way to like them, then let the agent use an MCP connection to control the browser.
Always on, easy to debug.
github.com/mdp/remote-browse…
This is an insane way to read this article. Agents are acting on the behalf of users who authorized them. Maybe the banks aren't comfortable with this, and that's fair, but this reads like a FB post from an older relative.
Also, that emdash :/
This is insane. We cannot allow AI agents to go into your bank account and act independently without your authorization. But that is what’s happening right now.
Left unchecked, AI could endanger the entire global financial system — including your bank account.
Pause AI NOW!
Readers added context they thought people might want to know
Per Axios, detected AI agents access bank accounts with the customer’s permission. This violates most banks’ terms requiring human logins, which is why banks call it “unauthorized.”
Source: Axios (Oct. 22, 2026) — axios.com/2026/10/22/ai-…
The jailbreaks keep coming. For stuff like Kindles, it’s worth taking advantage of this window of opportunity while it exists. Lock in that freedom while the AI is ahead of the firmware.
pepsipu.com/blog/2026-10-swi…
This was my first thought, you now have an easy way to MITM everthing shitty in your house. I think we are in for a fun time when people start posting what they're finding.
I always use the last 4 of my social for my ecc keys. Last 6 if it’s work related and requires a bit more security.
