I think that's true but do you see MCP as enough of a discovery primitive on its own, or does it still lack a ranking/trust layer? My intuition is that capability exposure is only half the problem and the harder part is how agents evaluate and choose between multiple similar tools.
Take Supabase for example. It’s disproportionately recommended by LLMs when people ask for backend/database stacks. It can't be just because of it's capability since a lot of tools expose similar primitives. Something in the model’s training data, ecosystem visibility, or reinforcement layer is shaping that ranking.
If agents start choosing tools autonomously, the real leverage point isn’t just “can you describe your capabilities in MCP?” but “how does the agent decide you’re preferred over 5 near identical alternatives?”
Do you think that ranking layer sits inside the model providers, or if it becomes an external reputation network?
So totally uninteresting. There is no "being a _" experience when "you" are a word calculator. Thinking that there is or that there is something useful there is a category error.
He has not, and it isn't the right framing. In this telling he has also "erased the stain" on many crimes. We will see how long that whitewashing lasts.
ADRs are similar, yet the important point is not the format of the design log entry, but it's usage with AI.
with design log, we ask the AI to create the ADR or log entry, but unlike ADR we
1. require the AI to ask question and we answer.
2. require the AI to update the design log after implementation with any drift from the original design.
Both of the above help to make the AI more precise and prevent context drift.
City Journal is a right wing rag whose opinions represent propaganda. There is one correct point that the 2019 law eliminating rent increases tied to capital improvements is broken. But its other points are simply not correct. Vouchers are not a like for like replacement for stabilization. Like work and other gates applied to SNAP and similar programs, they are fundamentally broken and inhumane.
The article makes a whole bunch of points - the main one being that rent control is not a good way to address expensive housing. Are they wrong about other things besides your somewhat beside the point example? Are they wrong that "The city now has nearly 50,000 empty units"?
The fact is a fact, their diagnosis and narrative is fantasy. A fair number of the stabilized empty apartments are due to the specific points in the 2019 law that too greatly impacted the economics of stabilized apartments. Prior to the 2019 law, it was economic to operate stabilized units, but too easy to unstabilize them, hence the motivation for the law. Replacing those dynamics with section 8 is idiocy.
reply