It seems there's a flawed reading coming from a single point in time analysis
Region instability had ben regularly threatening freedom of navigation in the last five years
And USA may not consider the individual country strategic, but cares deeply about freedom of navigation, because the single market is basically the pillar for their hegemony.
Sarah Paine lectures give overall better lenses to look at this engagement.
As the article discusses in detail, if the US actually cares about freedom of navigation, the war was a massive own goal because it looks extremely likely to grant the current Iranian regime de facto control of the Strait.
Iran already had the strait in ransom, directly and indirectly with proxy receiving weapons. You don't get to ignore that part and call this a own goal, since inaction led to the same effective results.
The strait was navigable until three weeks ago. There are very few conceivable paths towards reestablishing this. This is absolutely not the same effective result.
It seems you can't read a map. And btw it's very different targets, Hormuz vessel contain oil, gas and fertiliser for the Asian market. The red see is mostly foodstuff, cattle and Asian good for the European market. Way less impactful
You know the Red Sea is a different body of water than the Persian Gulf/Strait of Hormuz? Iran does not control the Red Sea directly, but most likely by funding the Houthis.
most subagent tool have in the tool the sub agent calls to notify completion the message to return and a good documentation about how to return things, so the orchesrtator can orchestrate.
the harness that don't have that mechanism can have it augmented by prompt
roo code has a good harness for that (but terrible default prompts for the agents), kiro does that well too, gemini has a few misses as it just send off things without really caring of returns by default (albeit very model dependent), meanwhile jules using the same models has a good harness with a good feedback loop.
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)
> 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.
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.
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.
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.
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).
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.
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
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.
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.
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.
many scraper already know not to follow these, as it's how site used to "cheat" pagerank serving keyword soups
reply