I was a diehard spaces-over-tabs person until I saw this scene in Silicon Valley. I had rather naively assumed that the tab-indent default in emacs was an oversight rather than a considered decision. This scene actually educated me.
If an un-guardrailed version of a model is capable of detecting security flaws, should it be kept secret? Should everybody be able to use these models to find (and fix) security flaws? Are we ok with the fact that those with access to that model have, in effect, the ability to hack lots of stuff?
The entire AI industry has been (not so secretly) paying a lot of experts in many fields to generate large amounts of novel training data. Novel training data that isn't found anywhere else--they hoard it--and which could actually contain original ideas.
Started a volunteer run, drop-in, bicycle workshop a few years ago. Its still going strong- something about the vibe, the practicality, and bike maintenance being just the right level of hard. I don't run it any more, but I drop in from time to time, and it always makes me feel better.
As somebody who has spent a bit of time in academia, I have often been slightly alarmed by some of the research (and opinon) that comes out of business schools. One thing is that it is often unsubstantiated and just plain wrong, another is that it often seems like the authors kind of know it, almost as if they are intentionally pandering to a lowbrow/midwit audience, and they expect everybody else to be in on the game. Its mystifying.
A court still might rule that all AI-generated code is in the public domain, because there was not enough human input in it. That’s quite possible, though probably not very likely.
Its not only likely, it is in fact the current position, at least in the US.
Right, but surely swagger/openapi has been providing robust API discovery for years? I just don't get what LLMs don't like about it (apart from it possibly using slightly more tokens than MCP)
gws doesn't ship a static list of commands. It reads Google's own Discovery Service at runtime and builds its entire command surface dynamically.
What is the practical difference between a "discovery service"+API and an MCP server? Surely humans and LLMs are better off using discovery service"+API in all cases? What would be the benefit of MCP?