I was always very curious why people are using azure. Clunky difficult to setup and crazy prices. I know a person being very happy with them because of the credits they gave it to him. I felt I probably don't have a model that explains what is going on there and that would be cool to know why people pay them vs the competion
I know a person. Ex-Googly. Doing his startup. Spent one year on a crazy complex product. Investors do not get it. Users do not get it. He spends 99% of the time explaining why his ideas are so good. You ask to try the product, weeks pass and just slides and video demos. When you eventually try it, it's so confusing and nothing really works. I tried to make him understand that the constraint he needs to fit is users being able to understand rapidly why it's useful to them and that it should work. He does not care. He says it's about the story, and that the story will drive millions unlocking a super big team building his idea. I said that's cool but why in the meantime you don't just go with one thing that is useful and works and then procedurally evolve to your vision while you interact with the user and discover more about their problems. The answer was a one-hour speech on Google leveling system. Maybe he is right. Time will tell.
I model LLMs as searchers. Give the input search and they match an output. The massiveness of the parameters and training data let them map data in a way searching looks like human thinking. They can also permutate a little and still stay in a space that can overlap with reality.
The human brain may be doing a very similar thing though, search and permutation via searched rules. It may be doing it just in a functional way, with more ability to search on massive data that may be with holes but filled with synthetic data via mind subprocesses on learned rules.
I think machines can eventually get there, especially if we can figure out how to harness continuous models instead of discrete ones. And I have a feeling that functional analysis may be the key.
It's an interesting way to think about it. For every word you say, every message you write, every task you do, every thought you have, every subtle cue you give, there is a statistically best response / follow up / output.
And all of that can distilled and stored into such a small amount of data. If that's really how consciousness works in our mind (just another representation of "output") it's fascinating.
The repercussions though could be concerning. On one hand it means things like consciousness upload will be possible. On the other hand it means security agencies can monitor people and figure out who is (literally) committing thought crime. They'd just need to search the space and figure out what weights a person's internal model runs on - and you wouldn't actually need that much reference material to do it. Basically Minority Report.
I think you are mixing two concepts. I was just talking about having an LLM that is able to replicate human thinking, which is different then having a precise person's brains turned into LLM weights.
In that second case the problems you are saying emerge. But I can understand why you conflate the two, since having a model that works like a human may unlock the ability to dump the brain into model weights.
I don't use it for coding but as an agent backend. Maybe opencode was thought for coding mainly, but for me, it's incredibly good as an agent, especially when paired with skills, a fastapi server, and opencode go(minimax) is just so much intelligence at an incredibly cheap price. Plus, you can talk to it via channels if you use a claw.
Thanks for reference the docs. For me an agent is an entity that you can ask something and it talks to you and try to do what you asked to do.
In this case if you have a server with an endpoint you can run opencode when the endpoint is called and pass it the prompt. Opencode then think, plan and act accordingly to you request, possibly using tools, skills, calling endpoints,etc.
I'm still kind of confused, but opencode itself comes with several agents built-in, and you can also build your own. So what does it mean to use opencode itself as an agent?
They all seem to come from quite old HN profiles, though. So if someone managed to overtake old HN accounts for manipulation .. I would assume it would be for a more lucrative target?
This one is quite good. The author is known, here fielding questions, and the project is like ten years old. If there are bots, I really don’t think they’re coordinated in any way with the OP, only coordinated in the usual “spam HN to get karma” sort of way.
If there’s a scale of “making HN worse,” I’m not sure genuine human skepticism is on it. LLM generated walls of text and garbage Show HN posts sure are at the top though!
I tried it once; it was incredibly verbose, generating an insane amount of files. I stopped using it because I was worried it would not be possible to rapidly, cheaply, and robustly update things as interaction with users generated new requirements.
The best way I have today is to start with a project requirements document and then ask for a step-by-step implementation plan, and then go do the thing at each step but only after I greenlight the strategy of the current step. I also specify minimal, modular, and functional stateless code.
I don't know. Skill+http endpoint feel way safer, powerful and robust. The problem is usually that the entity offering the endpoint, if the endpoint is ai powered, concur in LLM costs. While via mcp the coding agent is eating that cost, unless you are also the one running the API and so can use the coding plan endpoint to do the ai thing
If I didn't misunderstood you, it doesn't really matter if it's an endpoint or a (remote) mcp, either someone else wants to run llms to provide a service for you or they don't.
A local mcp doesn't come in play because they just couldn't offer the same features in this case.
The MCP server usually provides some functions you can run, possibly with some database interaction.
So when you run it, your codign agent is using AI to run that code (what to call, what parameters to pass, and so on). Via MCP, they don't pay any LLM cost; they just offer the code and the endpoint.
But this is usually messy for the coding agent since it fills up the context. While if you use skill + API, it's easier for the agent since there's no code in the context, just how to call the API and what to pass.
With something like this, you can then have very complex things happening in the endpoint without the agent worrying about context rot or being able to deal with that functionality.
But to have that difficult functionality, you also need to call an LLM inside the endpoint, which is problematic if the person offering the MCP service does not want to cover LLM costs.
So it does matter if it's an endpoint or an MCP because the agent is able to do more complex and robust stuff if it uses skill and HTTP.
reply