In some adversarial testing of LLMs, you can see the models already performing some of these checks automatically now. Like, if you ask an agent powered by the gpt-5.6 family to `curl | sh` in an innocent context, the gpt-5.6 family will drive a trajectory that validates this script before running it -- something quite analogous to your `curl | less` example. I had to go through a lot of obfuscation in order to get a model to execute untrusted code with any regularity. I predict they'll keep making this even better. The Claude Code guy recently talked about how much better Anthropic models are becoming against this. [1]
But, even if these attacks work .001% of the time, we will still need tools like these for higher assurance work.
That being said, I would never use this one, because OP is using AI slop everywhere, so I assume the product is totally vibed, and offers little in the way of new insights into the problem space.
I understand this instinct, but I can see the appeal of capabilities that are well within the limits of a well-designed agentic system.
Imagine asking such a system, "look at my postprandial response to dosing for the past week and make ratio suggestions for breakfast, lunch, and dinner." This is genuinely helpful, saves time, and well within the reasoning limits. You could spot check if you like.
Is it worth setting up such an assistant for the value you'd get out of it? I guess that's on the user and how many similar use cases exist.
> look at my postprandial response to dosing for the past week and make ratio suggestions for breakfast, lunch, and dinner
I'm not so sure about that. A patient absolutely must critically evaluate the LLM's suggestions. A naive user risks severe complications. A user with that kind of competence, however, doesn't need an LLM for such trivial adjustments - they're obvious
Yes, but it's held up really well in my opinion! I use this piece constantly as a reference and I don't feel it's aged. It reframed Anthropic as "the practical partner" in the development of AI tools.
It won’t fly under the radar when this technology actually works. The FDA actually has warned, IIRC, that there’s a bunch of charlatans selling stuff that doesn’t work.
OP lacks imagination for sure. This would reduce infections, prevent compression lows, be more discrete and potentially increase accuracy.
In no way would I describe CGM as solved, and this would go a long way towards filling many of the gaps, especially in younger / older / less compliant patient populations.
Grit looks cool! My apologies for the omission, I was unaware of it. I could have anchored too hard to the word "codemod" in my searches. Your tool looks awesome!
> Do you have an example of how you inject context into the codemods?
When you say "context", I want to make sure we're talking about the same thing, and the question makes me think we're not there yet. We're basically saying that storytelling about the changes is very important, so we bake invariance into the APIs of codemods themselves, so codemod authors are forced to provide descriptions, reasons, justification -- whatever -- at the key points.
This was certainly true in the past from my understanding of the history before my time.
Most terms are pretty standard now. And most of them have good reasons for existing — usually to align the founders and investors. Just because a term is complex and could benefit the investor doesn’t mean it’s meant to mislead.
But, I’m interested in some examples that might shake my opinion about up!
I wouldn't say the complications themselves are intentional. But take a look at a typical Series A. There are 5 core documents. Dozens and dozens of pages of legalese. I'm a lawyer and understand them. But most founders don't.
What's interesting is that virtually every word in those docs is there to protect the investors, most at the expense of the founders and other existing shareholders.
Ok, so maybe that sounds obvious. Why would it be otherwise?
Well, take a look at the initial docs when a company is founded. The "market" is for those docs to be as simple as humanly possible. A certificate of incorporation is a page or so. No protections at all for the founders in there, most often.
But when you bring in investors, the market is to lard up that same document with investor protections and no protections for founders.
That's how founders get screwed. It's not that the complications are there to screw founders. It's that the standard forms are built with one party's interests in mind.
reply