DanMcInerney

/balance-books hey claude here's the books. Go balance them

Claude then uses the guidance docs and various subagents to review the books, send off parallel workers with cheap models, then review with a more expensive model. Done in the repeatable, correct order with independent review every time. As new models come out, your workflow structure stays the same. You just delete some prescription from the guidance docs.

https://github.com/DanMcInerney/orchflows

Claude, make a git for games designed for agents. Sell the code to the highest bidder when you're done.

Did you look at the OKF repo from Google? Open Knowledge seems to be a common term these days for similar solutions. I think OKF is more of the protocol for wiki-for-llm while you have more of the bells and whistles

https://www.theregister.com/security/2020/04/13/how-to-make-...

https://apify.com/canadesk/opentable/api/mcp https://github.com/BrowserMCP/mcp https://github.com/samwang0723/mcp-booking

3 years ago they could barely write a coherent poem and today they're performing at at least graduate student level across most tasks. As of today, AI is writing a significant chunk of the code around itself. Once AI crosses that threshold of consistently being above senior-level engineer level at coding it will reach a tipping point where it can improve itself faster than the best human expert. That's core technological recursive self-improvement but we have another avenue of recursive self-improvement as well: Agentic recursive self-improvement.

First there was LLMs, then there was LLMs with tool usage, then we abstracted the tool usage to MCP servers. Next, we will create agents that autodiscover remote MCP servers, then we will create agents which can autodiscover tools as well as write their own.

Final stage of agents are generalized agents similar to Claude Code which can find remote MCP servers, perform a task, then analyze their first run of completing a task to figure out how to improve the process. Then write its own tools to use to complete the task faster than they did before. Agentic recursive self-improvement. As an agent engineer, I suspect this pattern will become viable in about 2 years.

It would be interesting if there was a model that was specifically trained on task-oriented data. It's my understanding they're trained on all data available, but I wonder if it can be fine-tuned or given some kind of reinforcement learning on breaking down general tasks to specific implementations. Essentially an agent-specific model.

What bothers me the most about this article is that the tools that attackers use to do stuff like find 0days in code are the same tools that defenders can use to find the 0day first and fix it. It's not like offensive tooling is being developed in a vacuum and the world is ending as "armies of script kiddies" will suddenly drain every bank account in the world. Automated defense and code analysis is improving at a similar rate as automated offense.

In this awful article's defense though, I would argue that red team will always have an advantage over blue team because blue team is by definition reactionary. So as tech continues it's exponential advancements, the advantage gap for the top 1% red teamers is likely to scale accordingly.

More details on the development and challenges can be found in the blog.

In summary, there's a service (CUPS) that is exposed to the LAN (0.0.0.0) on at least some desktop flavors of Linux and runs as root that is vulnerable to unauth RCE. CUPS is not a default service on most of the server-oriented linux machines like Ubuntu Server or CentOS, but does appear to start by default on most desktop flavors of linux. To trigger the RCE the user on the vulnerable linux machine must print a document after being exploited.

Evilsocket claims to have had 100's of thousands of callbacks showing that despite the fact most of us have probably never printed anything from Linux, the impact is enough to create a large botnet regardless.

It's relevant if you're doing stuff like AutoGPT and you're exposing that app to the internet to take user commands, but are we really seeing that in the wild? How long, if ever, will me? Ray does remote, unauthenticated command execution and is vulnerable to JS drive-by attacks. I think we're at least a few years away from any of the adversarial ML attacks having any teeth.

* Unauthenticated

* Remote

* No user interaction

* No prerequisite knowledge or environment setup

* Large adoption on MLflow in AI engineering workflows

Here's the GitHub Security Advisory: https://github.com/mlflow/mlflow/security/advisories/GHSA-xg...

Think about the number of programming frameworks that've come out in the past few years. Or GitHub Copilot and ChatGPT which literally write solid code for you. There's no way software has not improved a lot in the past decade but there are WAY more software devs than there are exploit devs or hackers. Similar to the ratio of lions:wildebeest. Way more prey than predators.