Was able to sign up for the Max plan & start using it via opencode. It does a way better job than Qwen3 Coder in my opinion. Still extremely fast, but in less than 1 hour I was able to use 7M input tokens, so with a single agent running I would be able easily to pass that 120M daily token limit. The speed difference between Claude Code is significant though - to the point where I'm not waiting for generation most of the time, I'm waiting for my tests to run.

For reference, each new request needs to send all previous messages - tool calls force new requests too. So it's essentially cumulative when you're chatting with an agent - my opencode agent's context window is only 50% used at 72k tokens, but Cerebra's tracking online shows that I've used 1M input tokens and 10k output tokens already.

> For reference, each new request needs to send all previous messages - tool calls force new requests too. So it's essentially cumulative when you're chatting with an agent - my opencode agent's context window is only 50% used at 72k tokens, but Cerebra's tracking online shows that I've used 1M input tokens and 10k output tokens already.

This is how every "chatbot" / "agentic flow" / etc works behind the scenes. That's why I liked that "you should build an agent" post a few days ago. It gets people to really understand what's behind the curtain. It's requests all the way down, sometimes with more context added, sometimes with less (subagents & co).

Many API endpoints (and local services for that matter) does caching at this point though, with much cheaper prices for input/outputs that were found in the caching. I know Anthrophic does this, and DeepSeek I think too, at the very least.

They don't have prefix caching? Claude and Codex have this.

At those speeds, it's probably impossible. It would require enormous amounts of memory (which the chip simply doesn't have, there's no room for it) or rather a lot of bandwidth off-chip to storage, and again they wouldn't want to waste surface area on the wiring. Bit of a drawback of increasing density.

Is this built with JS / something like Fabric JS? There are some things that feel very similar to a web app that I worked on before. Wondering if there's plans to have a plugin API at some point if it is.

There is support for photoshop plugins https://affinity.help/photo2/en-US.lproj/index.html?page=pag...

I have a plus subscription & was able to get it to work on X. It shows you what it's doing on the tab as it's moving around.

One interesting thing here is that the chat side panel is agentic - it can read tab contents, open links in the existing tab or create new tabs, and do most of the standard "summarize", etc. things too.

This might be the first time that I move off of Chrome for an extended period of time.

I was able to add ublock origin lite as an extension & it seems to work the same as Chrome.

uBlock origin lite kinda sucks compared to the OG uBlock, though. YouTube videos have this awkward buffering at the start now, sometimes YouTube homepage ads still load, sponsored placements on GrubHub/DoorDash appear and aren't able to be removed, etc.

I thought that was more specific to YT than UB?

My UB experience remains largely unchanged since the switch to manifest v3, I pay for YT to avoid ads and support creators directly.

"I pay to remove ads so my experience with a neutered adblocker isn't as bad" is a weird take.

If you think the end game is companies deciding they're comfortable with removing ads in exchange for a subscription, rather than a subscription with a gradually increasing amount of ads, then I have a bridge to sell you.

I support the creators I watch by donating to them directly.

I use UB for all the other websites, not YT, it's a weird take to associate UB usage and experience with a single domain.

> I support the creators I watch by donating to them directly.

Me too, on top of the monthly fee that gets distributed to those I watch. More for every creator, even those I only watch once or sporadically

I mentioned multiple domains...? I said it also impacts sponsored listings on food delivery platforms. Those used to be blocked and, more broadly, the ability to manually block specific elements of a webpage was lost with the transition to UB lite.

uBO Lite does not support a lot of filters and there is no element picker. Also, a lot of other add-ons are unsupported due to no MV2 support.

It can block sponsored chat response content too? And agentic behaviors that act on behalf of sponsors?

I wonder how this works with mcpb (renamed from dxt Desktop extensions): https://github.com/anthropics/mcpb

Specifically, it looks like skills are a different structure than mcp, but overlap in what they provide? Skills seem to be just markdown file & then scripts (instead of prompts & tool calls defined in MCP?).

Question I have is why would I use one over the other?

One difference I see is that with tool calls the LLM doesn’t see the actual code. It delegates the task to the LLM. With scripts in an agent, I think the agent can see the code being run and can decide to run something different. I may be wrong about this. The documentation says that assets aren’t read into context. It doesn’t say the same about scripts, which is what makes me think the LLM can read them.

This looks great! At a previous job we had a fork of Jupyter notebooks that were used this way by some teams. I see that remote execution is on the roadmap, but was also wondering if you'll have some form of parallel remote execution as well (ie one runbook run across 10 or 100 VMs similar to parallel ssh). Definitely more complicated than single execution, but potentially very powerful for debugging fleets where you don't have Chef or Ansible. I guess the alternative is to just have the runbook run locally but run pssh in some commands to get a similar result.

absolutely!

we already support execution of script + terminal blocks over SSH, but want much tighter integration. Parallel execution is certainly a part of that too. anything else you'd want to see?

Nothing in particular - when I wrote / used the jupyter 'runbooks', they were most helpful when a SEV (site event / severe error) was happening or if a new person on the team needed to handle oncall the first time.

This is helpful when I don't want to use AI.

Any chance you could add "extract clips" in addition to extract frames? Specifically I had to split a video into x-second clips recently & had to use AI to get the right command for that.

This is AI generated and the commands are wrong in multiple cases

How does this compare to s6? I recently used it to setup an init system in docker containers & was wondering if nitro would be a good alternative (there's a lot of files I had to setup via s6-overlay that wasn't as intuitive as I would've hoped).

S6 is way more complex and rich. Nitro or runit would be simpler alternatives; maybe even https://github.com/krallin/tini.

Thanks! Reading some of your other comments, it seems like runit or nitro may not have been a good choice for my usecase? (I'm using dependencies between services so there is a specific order enforced & also logging for 3 different services as well).

You seem to know quite a bit about init systems - for containers in particular do you have some heuristics on which init system would work best for specific usecases?

dinit is another one with service dependency support

Getting a CORS error from the API - is the demo at https://search.wilsonl.in/ working for anyone else?

cors error is due to the actual request failing (502 Bad Gateway). hug of death?

Yeah just saw the 502 - probably hug of death.