Viewing profile — ondrsh
ondrsh
HN member- Joined
- Wed, Sep 06, 2023, 5:46 AM UTC
- HN karma
- 109
- Public activity
- 20 items
- HN profile
- View on Hacker News ↗
About ondrsh
https://github.com/ondrsh
Recent public activity
-
comment
Comment #44809065
AFAIK subagents inherit the default model since v1.0.64. At least that's the case for me with the Claude Code SDK — not providing a specific model makes subagents use claude-opus-4…
-
comment
Comment #43503162
No, MCP does not include any concept of UI (yet). Tool results are usually text only, although there is also the abstraction of an Image (which can be displayed as clients as decid…
-
comment
Comment #43498196
Thanks. Added RSS, but WC3 shows some errors. I'll move to plain markdown when I have more time, then this will be easier.
-
comment
Comment #43498164
>In both cases the application code needs to be modified to account for the new functionality, unless you're also using the LLM to handle the logic which will have very unpredictab…
-
comment
Comment #43491646
> In your opinion, what percentage of apps might benefit from this model where end users bring their own MCP tools to extend the capabilities of your app. Long term close to 100%. …
-
comment
Comment #43491452
Unfortunately, MCP is not HATEOAS. It doesn't need to be, because it's not web-like. I wish it were. HATEOAS is great for web-like structures because in each response it not only i…
-
comment
Comment #43491359
The concept of design-time vs. runtime applies to both clients and servers. I believe you're implying that server developers can focus less on this concept (or sometimes even ignor…
-
comment
Comment #43488608
Similar, but one level higher. Plugins have pre-defined APIs. You code your application against the plugin API and plugin developers do the same. Functionality is being consumed di…
-
comment
Comment #43487964
This seems to be just implementing tools functionality, no resources or prompts, roots or sampling. I can't blame them. I'm wondering though about progress notifications and pagina…
-
comment
Comment #43487858
To really understand MCP you need to think about application design in a different way. In traditional applications, you know at design-time which functionality will end up in the …
-
comment
Comment #43373817
Your understanding is on point. > As far as I understand, they would have to somehow pass in either a script to spin up their own server locally (unlikely for your everyday user), …
-
comment
Comment #43330459
Seems nice because it's stateless and thus simpler. But it still enforces lots of structure (static entry points, memory, etc.). So if MCP reminds me of FTP/Telnet (bi-directional,…
-
comment
Comment #43330326
I'm not sure I fully understand your scenario. Who will be doing the actual network requests? MCP is basically a trifecta of: 1) MCP-aware LLM applications 2) MCP clients 3) MCP se…
-
comment
Comment #43312027
It seems like you're describing a scenario where you know at design-time which tools will be included. In that case the benefit of using MCP is less clear. While you usually get to…
-
comment
Comment #43307783
TL;DR: IMHO, the MCP enforces too much structure, which makes it vulnerable to disruption by less structured protocols that can evolve according to user needs. The key reason the w…
-
comment
Comment #43307225
Exactly. An AI-web based on the principles of HATEOAS is the next step, where instead of links, we would have function calls. As you said, HATEOAS requires a generic client that ca…
-
comment
Comment #43303791
It's much simpler: MCP allows tools to be added at runtime instead of design-time. That's it. And because this can happen at runtime, the user (NOT the developer) can add arbitrary…
- story
-
comment
Comment #41902550
Thanks so much for taking your time.
-
comment
Comment #41879605
Hello, What options are available for an EU national who wants to start a U.S.-based company and relocate there but doesn’t have the capital required for an E-2 visa? Let’s assume …