“They do not reliably capture what a user was shown or told.”
This adds to the case for middleware providers like Vapi, LiveKit, and Layercode. If you’re building a voice AI application using one of these SST -> LLM -> TTS providers there will be definitive logs to capture what a user was told.
Would you say MCP is a protocol (or standard) similar to how REST is a protocol in that they both define how two parties communicate with each other? Or, in other words, REST is a protocol for web APIs and MCP is a protocol for AI capabilities?
also REST is less about communicating, more about the high level user interface and the underlying implementations to arrive at that (although one could argue that’s a form of communicating).
the style does detail a series of constraints. but it’s not really a formal standard, which can get pretty low level.
—
standards often include things like MUST, SHOULD, CAN points to indicate what is optional; or they can be listed as a table of entries as in ASCII
> standard (noun): An acknowledged measure of comparison for quantitative or qualitative value; a criterion
note that a synonym is ideal — fully implementing a standard is not necessary. the OAuth standard isn’t usually fully covered by most OAuth providers, as an example.
—
> The Model Context Protocol (MCP) is an open standard and open-source framework
MCP, the technology/framework, is like Django REST framework. it’s an implementation of what the authors think is a good way to get to RESTful webpages.
MCP, the standard, is closer to REST, but it’s more like someone sat down with a pen and paper and wrote a standards document for REST.
They aren’t the same, but the have some similarities in their goals albeit focussed on separate domains, i.e. designing an interface for interoperability and navigation/usage… which is probably what you were really asking (but using the word protocol waaaaaaay too many times).
Thanks, and call me wrong, I think "Protocol" in MCP is somehow misused. Sure it is somehow a protocol, because it commits on something, but not in the technical sense. MCI (Model Context Interface) would probably the better name?
I agree that interface would be a better name than protocol, but Model Context Integration/Integrator would be even better as that is it's core intent: To integrate context into the model. Alternatively, Universal Model Context Interface (or integrator) would be an even better name imo, as that actually explains what it intends to do/be used for, whereas MCP is rather ambiguous/nebulous/inaccurate on the face of it as previously established further up-thread.
That said, I think as the above user points out, part of the friction with the name is that MCP is two parts, a framework and a standard. So with that in mind, I'd assert that it should be redefined as Model Context Interface Standard, and Model Context Interface Framework (or Integration or whatever other word the community best feels suits it in place of Protocol).
Ultimately though, I think that ship has sailed thanks to momentum and mindshare, unless such a "rebranding" would coincide with a 2.0 update to MCP (or whatever we're calling it) or some such functional change in that vein to coincide with it. Rebranding it for "clarity's sake" when the industry is already quite familiar with what it is likely wouldn't gain much traction.
Wow, this is great. Calling it UMCI would have saved me a lot of confusion in the first place. But yeah I think the ship has sailed and it shows that a lot of things there were cobbled together in a hurry maybe.
The potential benefits of alcohol are hard to decipher because of the population data:
“A lot of people who don’t currently drink are people who used to drink heavily, or who have health problems that led them to quit...” said Keith Humphreys, PhD, a professor of psychiatry and behavioral sciences and the Esther Ting Memorial Professor. “That skews the data, making moderate drinkers look healthier by comparison.”
I wouldn't drink alcohol for health benefits. I'm just saying a glass of wine per day with dinner won't have adverse health effects for most people. If you don't currently drink, then there's no reason to start. If you're having more than one drink per day, then you should cut back to just one. If you do drink, then do so several hours before bedtime because alcohol does affect quality of sleep.
It would be dishonest (the intentional omission of relevant truthful fact) to not to disclose the source. If people already don't want the most important truth of all, the very one all of the others depend on always being true to then be true themselves, then they are already choosing to not adopt the truth into their lives and that is their choice. What they choose is not going to help me adopt it any more.
I understand your point, I hear all sorts of religious nonsense, but this is actually the real thing. Why blame the Lord: Truth and Life, for a bunch of people abusing his teachings to control and manipulate others? e.g. don't punish the innocent for the bad deeds and lies of many.
I wrote the paper. So, if I say that is my source, then anyone claiming otherwise must prove different.
I'm not sure I agree with the transition to full automation, but Piketty's premise that returns on assets will outperform returns on labor is still at the root of growing income inequality.
If you have a bankroll, investments will yield higher returns than returns on labor (just working your butt off). Without wealth shocks or redistribution the income inequality gap will continue to widen.
When the CCPA launched in 2018 companies had to comply when a consumer requested a Data Subject Access Request (DSAR). Because the consumer had to request a DSAR not all companies felt this compliance pain acutely (e.g. it was mostly big companies with A LOT of users that got more DSARs, so they adopted workflows and tools to alleviate the pain).
The Delete Act has more teeth. Independent compliance audits begin in 2028 with penalties of $200 per day for failing to register or for each consumer deletion request that is not honored. GDPR spurred organizations to compliance, partly because of the steep penalty (up to €20 million or 4% of revenue, whichever is higher), maybe The Delete Act (and its much smaller penalty) will also spark organizations to comply.
Marissa Mayer on why Google chose sans-serif fonts for search results:
When I had to make a decision about should the Google results pages be serif or sans-serif, I didn't have enough users to do the split A/B testing and mathematically figure that out, so I ended up reading a lot of research and ultimately finding out that serif fonts are more readable, and sans-serif fonts are more legible.
The serifs create a horizontal rule that guides the eye, so serif fonts are much better when you’re reading long pieces of text. Sans-serif fonts are more legible which means that... when the serifs are removed your eye can spot read a character much better and much more quickly, and as a result it is much better for spot reading. In an activity like search it turns out you want to facilitate spot reading to a much greater degree than reading long prose.
On the East Coast there are more cities with dense populations, so public transit can be effective and car ownership rates are lower.
In the West, many cities are urban sprawls that built out instead of up, so public transit is less effective and car ownership rates are higher.
I wish LA or Phoenix or Vegas was dense living where public transit could be effective, but since they’re urban sprawls and public transit isn’t aa effective as a densely populated city, most people own cars to get around.
- Their main source of revenue seems to be decaying, as if the talent that made it great isn't there anymore. Few people would tell you that search (or maps, or youtube) is better today than it ever was.
- Talent is there, and the quality of their moonshots is proof.
Early days are where you can move the needle the most. It's hard to make an impact on a huge, entrenched business that works pretty well and has millions of stakeholders.
Wow. Huge congrats! This is a real business that is profitable.
Our industry focuses so much on venture-backed startups (many of which are unprofitable) that would lose sight of one important goal when starting a business - be profitable!
This adds to the case for middleware providers like Vapi, LiveKit, and Layercode. If you’re building a voice AI application using one of these SST -> LLM -> TTS providers there will be definitive logs to capture what a user was told.
reply