Hacker Newsnew | past | comments | ask | show | jobs | submit | avereveard's commentslogin

isn't this the one with default-on need code change to turn off telemetry?



You can scroll down literally two messages in the Github issue you linked:

> there isnt any telemetry, the open telemetry thing is if you want to get spans like the ai sdk has spans to track tokens and stuff but we dont send them anywhere and they arent enabled either

> most likely these requests are for models.dev (our models api which allows us to update the models list without needing new releases)


You should really look at the 2nd link, its much worse than telemetry..

> opencode will proxy all requests internally to https://app.opencode.ai

> There is currently no option to change this behavior, no startup flag, nothing. You do not have the option to serve the web app locally, using `opencode web` just automatically opens the browser with the proxied web app, not a true locally served UI.

> https://github.com/anomalyco/opencode/blob/4d7cbdcbef92bb696...


That is the address of their hosted WebUI which connects to an OpenCode server on your localhost. Would be nice if there was an option to selfhost it, but it is nowhere near as bad as "proxying all requests".

Eh code doesn't have a lot of value. Especially filling methods between signatures and figuring out the dependencies exact incantation is mechanistic and definitely time better spent doing other things.

A lot of these blog start from a false premise or a lack of imagination.

In this case both the premise that coding isn't a bulk time waste (and yes llm can do debugging, so the other common remark still doesnt apply) is faulty and unsubstantiated (just measure the ratio of architects to developers) but also the fact that time saving on secondary activities dont translate in productivity is false, or at least it's reductive because you gain more time to spend on doing the bottlenecked activity.


eh but also organic chemistry only does well 30 and 60 degrees

See buckyballs as a trivial refutation of your point.

Are buckyballs organic?

Formally, yes. "Organic chemistry" is not too far off a synonym for "chemistry with carbon involved".

"Not too far off" = "exactly defined as".

I wasn't sure if there were any weird edge cases, but yeah.

CO, CO2, carbonate salts like Na2CO3, or CaCO3, and cyanides like HCN, NaCN, and KCN are usually considered inorganic compounds instead of organic compounds, despite containing carbons. But the vast majority of carbon-containing compounds are considered organic, and there are no organic compounds that don't contain carbon.

> there are no organic compounds that don't contain carbon

It's very much nitpicking and an edge case but now you've got me wondering if some silicone hydrocarbon analogs might not qualify. Noting that we have plausible theories about the feasibility of silicone based life.


> we have plausible theories about the feasibility of silicone based life.

... Do we? Last I heard those weren't really viable due to some combination of being too stable or too unstable in all the available solvents.


Maybe I'm out of date then. They looked plausible when I read about them years ago.

I mean, I don't think diamonds are considered "organic"; same for graphite. But that's where the term "organic" itself starts to break down as a category.

I was also thinking carbonates in a geologic context.

Wikipedia: "Organic chemistry is a subdiscipline within chemistry involving the scientific study of the structure, properties, and reactions of organic compounds and organic materials (i.e. matter in its various forms that contain carbon atoms)."

It doesn't break down at all. Diamonds are organic structures, in the classical definition of that term. (Assuming they weren't treated with insecticides in the mine... /s)


I don't think wikipedia is the best reference here, and I think you're also misinterpreting them; not all carbon-containing substances (including diamond) are considered organic. There is no true classical definition of the term- it's actually a fairly nebulous concept. Ultimately you're just arguing about definitions which is not particularly interesting.

Yes! Not sure why you're asking- things don't have to be created by biological processes to be organic (this concept is totally unrelated to "organic" in the supermarket).

The universe seems perfectly happy to have, for example, 5-member rings tho.

Not in 3D.


That image just demonstrates what was mentioned in the article, that the sphere cannot be covered only with regular hexagons, but a part of them must be replaced with regular pentagons, so the angles that are multiples of 30 degrees are not sufficient.

So the previous poster was right.


An angle projected on a plane is not the same as a 3D angle.

Also see the structure of diamond (109 degs).


Not in 3D Euclidean space. I'm pretty sure 3D Hyperbolic space allows it just fine.

C

each ai need context management per conversation this is something that would be very clunky to replicate on top of http or ftp (as in requiring side channel information due session and conversation management)

Everyone looks at api and sure mcp seem redundant there but look at agent driving a browser the get dom method depends on all the action performed from when the window opened and it needs to be per agent per conversation

Can you do that as rest sure sneak a session and conversation in a parameter or cookie but then the protocol is not really just http is it it's all this clunky coupling that comes with a side of unknowns like when is a conversation finished did the client terminate or were just between messages and as you go and solve these for the hundredth time you'd start itching for standardization


All MCP adds is a session token. How is that not already a solved problem?

P

It makes it part of the protocol so the llm doesn't have to handle it, which is brittle

And look at the patent post I've replied to choice of protocol, I'd like to see a session token over ftp where you need to track the current folder per conversation.


But the agent harness is still handling the session token for you either way. MCP might be an easy way for agent harness creators to abstract the issue away, but I don’t want to lose all REST conventions just to make it a little easier for them to write an agent harness.

It makes it harder for the LLM to understand what’s going on, not easier.


again, not all services are rest or with nice api, if they were, you'd just have the agent write scripts.

No, but MCPs aren’t free to build either. So if you need to build an API on top, why would you build an MCP instead of using one of the existing standards that both LLMs and humans already know how to work with?

I've passed that bottleneck with a review task that produces engineering recommendations along six axis (encapsulation, decoupling, simplification, dedoupling, security, reduce documentation drift) and a ideation tasks that gives per component a new feature idea, an idea to improve an existing feature, an idea to expand a feature to be more useful. These two generate constant bulk work that I move into new chat where it's grouped by changeset and sent to sub agent for protecting the context window.

What I'm doing mostly these days is maintaining a goal.md (project direction) and spec.md (coding and process standards, global across projects). And new macro tasks development, I've one under work that is meant to automatically build png mockup and self review.


What are you using to orchestrate/apply changes? Claude CLI?

I prefer in IDE tools because I can review changes and pull in context faster.

At home I use roo code, at work kiro. Tbh as long as it has task delegation I'm happy with it.


Also useful to encode into the steering of your platform. The incremental aspect of many little updates really help picking up speed by reducing review time.

Big bang approach could be a start, but a lot of one line guidance from specific things you dont want to see stack up real fast.


"I gave an automation I didn't control permissions it shouldn't have"


as soon as there was money to be made by concentrating data center, no matter the energy density impact on environment, the once philanthropist changed tune real quick

https://www.gatesnotes.com/home/home-page-topic/reader/three...

with gems like "Although climate change will hurt poor people more than anyone else, for the vast majority of them it will not be the only or even the biggest threat to their lives and welfare. "


hey thanks for this service. even if it's now downvoted to hell and back it's great for experiments. I was looking to a quick and easy way to share level for my drawing game, looks grand.


they have been engaging in hybrid warfare for decade+ they don't get to play victim this is the result of their continued proxy attacks


Guidelines | FAQ | Lists | API | Security | Legal | Apply to YC | Contact

Search: