philipodonnell

AI did not take your job; a person decided to use the productivity improvement from a new technology to realize increased short term profitability at the cost of losing you. That is not so much of a value judgement on the choice than a plea to the people making the choices to realize how short term that thinking is and to the author to not let them off the hook for making it.

But, they have the full traces of everything you’re saying, if they wanted to see what the model would say at a given point they could just truncate and ask? It seems more likely It’s just a way to keep you engaged ala infinite scroll.

I don’t know, somehow the pace seems different, these transitions felt more like the last generation retiring, and the next generation doing something different, instead of it happening to everyone at the same time.

What the best way to see how a homegrown version compares?

I think these are different things. The source code, it’s tests, it’s documentation, it’s data. They are different perspectives to approach a given body of work while together building an overall understanding. It doesn’t matter at all where the files live but when you approach the work from that perspective you know how to find it, and I don’t think next to the source but away from the others is a good combination.

This landed for me. I wonder though if we aren’t giving a pass to the companies who pay the AI companies to replace their employees.

This particular example aside, I don’t think it being derivative and simplified is necessarily bad. Libraries that are popular today were written for humans and reinforced by LLMs via training. It’s unlikely they represent the ideal interaction surface for an agent.

There was a study recently that LLms prefer resumes written by LLMs rather than by humans. Stands to reason they would prefer apis written by LLMs.

This is probably the early days of such intentionally simplified agentic semantic primitives like “DAG Workflow” where the answer for why not Temporal is that LLMs prefer different things than humans.

Is the difficulty that in high entropy situations, you can’t really tell whether it’s because the model is uncertain, or because of the options are so semantically similar that it doesn’t matter which one you choose? Like pure synonyms.

Despite being a different kind of writing, there are some interesting parallels with the article in what you wrote here

I’ve been experimenting with LiveStoreJS which uses a custom SQLite WASM binary for event sync, so for simplicity I’ve also used it for regular application data in browser and found no issues (yet). It surprised me that using a full database engine in memory could perform well vs native JS objects at scale but perhaps at scale is when it starts to shine. Just be wary of size limits beyond 16-20mb.

Of all the interface modalities available, CLIs seem like the most natural for copilots to work with. Lots of examples in the training data, universal interface for help, maps well to the sequential nature of token generation, similar syntax for different OSs… I can see them replacing skills and MCP et al from the model’s perspective.

How do they prove this? It sounds like the plaintiffs basically claimed they were rejected a bunch of times and since the resume had recognizable indicators of protected classes they must have been discriminated against?

Don’t get me wrong, I do this work, and Workdays statement of “we don’t use protected classes” instead of “we test our models to prove they are unbiased when given recognizable indicators of protected classes” is pretty telling. Because it’s hard and if you solved it you would be proud. If you don’t control for it it WILL discriminate. See Amazon’s experiment a decade ago.

I’m just really curious how all this plays out in front of a judge.

You should just need the AGENTS.md right?

Anyone have a link to the actual report?

This is a great use case for using an algorithmic difficulty ramp where it can really dial in that curve to solve for getting people to play longer over multiple sessions.