To a certain extent it has already - models are already very good at picking tools to use: ask for a video transformation and it uses ffmpeg, ask it to edit an Excel sheet and it uses Python with openpyxl, etc.
My post is more about how sometimes you still need to make environment design decisions yourself. My favorite example is the Fly.io one, where I created a brand new Fly organization with a $5 spending limit and issue an API token that could create resources in that organization purely so the coding agent could try experiments to optimize cold start times without messing with my production Fly environment.
An agent might be able to suggest that pattern itself, but it would need a root Fly credential in order to create itself the organization and restricted credentials and given how unsafe agents with root credentials are I'd rather keep that step to myself!
It's amusing to think that the endgame is that the humans in the loop are parents with credit cards.
I suppose you could never be sure that an agent would explicitly follow your instruction "Don't spend more than $5".
But maybe one could build a tool that provides payment credentials, and you get to move further up the chain. E.g., what if an MCP tool could spin up virtual credit cards with spending caps, and then the agent could create accounts and provide payment details that it received from the tool?
As a reader of Simon's work, I can speculate an answer here.
All "designing agentic loops" is context engineering, but not all context engineering is designing agentic loops. He's specifically talking about instructing the model to run and iterate against an evaluation step. Sure, that instruction will end up in the context, but he's describing creating a context for a specific behavior that allows an agent to be more effective working on its own.
Of course, it'll be interesting to see if future models are taught to create their own agentic loops with evaluation steps/tests, much as models were taught to do their own chain of thought.
It's very difficult to get debt financing if you're running out of cash, and this article is focused on companies that are (at risk of) running out of cash.
Much of this story was published in Proof of Conspiracy in 2019, curated from major media reporting. The media just didn't cover the release at the time.
This can be difficult because the money is often funneled through other entities (as LPs to VC and growth funds, etc.)
I've had more than one VC tell me they couldn't guarantee that there was no Saudi money in their fund, even though they didn't have any direct KSA LPs.
I've been living in vd for the last few months for data analysis. It's been beyond helpful, including for examining ugly nested JSON data. It's been extremely valuable for feature exploration in my dataset.
I loved Whitefish when I was there, and would have considered it for the long term but was concerned about reports of a growing alt-right contingent in town. Have you encountered that?
Even if you have a terrible experience in your doctoral program, much of its outward value is in the program's reputation. Giving a program a negative review hurts the perceived value of your own education.
