browningstreet

AppleTV

ironically, at my large enterprise, they aren't yet distinguishing between "chinese models" and "chinese models hosted at microsoft foundry". so far it's just _banned_. i'm not at all pretending it's like that at other orgs.

I have tried using Pandora over the years, but about 5-10 songs in on any channel they start playing music from bands I've never heard of.. like unsigned or catalog tracks. They seem to front-load with the right selections and then it's off to "technically this music matches the criteria" unknown stuff.

What would freaking out look like, or is this just a stupid bloggish title flourish?

Is OpenAI coming in $20B under a sign of "freaking out"?

I just searched for him online, he looks like a Turkish Timothy Olyphant.

I signed up for Orkut and my account was promptly blocked. It was the hot thing for a minute.

Hermes and an Orca dev server

I've been working through my options per digital freedom, human dignity, and non-double-taxation as a US citizen. It's a depressingly short list.

Can we stop linking to this horrible and unreadable website?

There’s only one OS… BIOS!

Nasty. My point was about.. this morning my machine crashed. Pi + Deepseek v4.1 Flash misdiagnosed it, and Opencode + Deepseek v4.1 didn't.

Besides opencode?

Funny that you ask this question but are comparing it to a seriously niche product. Harnesses are mainstream and the one you’re using isn’t so much.

You’re so, so close…

Assembly plus platform translation, hmmm. I don’t get it but that’s a heck of a thing to do! And yes, I’ll try it.

:-)

Is that part of opencode v2?

Minimal alone isn’t a driving force for me. Coding intelligence and output is. I know Pete mostly codes with OC but farms hard jobs out to Codex. Teknium says he only codes in Hermes. I do iOS apps in Claude but everything else in deepseek or opus. I suspect things are about as good as they can be in terms of actual code.. across all levels.

How do we know how different the code of pi vs opencode vs {commercial harness} is? I’m pretty happy with opencode but can’t quite understand whether I should spend the time to understand how different pi would be.

Not in AI. But they announced things last week so maybe..

You can process and print B&W yourself. Color needs to go to a lab.

B&W is also standard for street and art photography.

You're gonna argue this _now_?

"The past is stupid"

I actually do a quarterly “read the docs” day for my major tools. It always pay off…

Doing research work with it that outputs any kind of artifact is.. really painful. It constantly crashes, has to regenerate.. and then the output is often very difficult to carry to other Microsoft products, like Sharepoint. I end up creating PDFs that I import.

I'll go ahead and burn working hours on it because I'm getting paid, and people like the things I create.. but it's a very crippled and painful version of what you get with the frontier products and most OSS options.

Running or biking faster and finishing the race are, at times, orthogonal.

And anyway, the whole point of my original comment was "pacing" was a fine and natural term to use in this debate.

Sorry, but this from the website is kind of hilarious:

"What DAWO stands for

DAWO brings public values and technology together. The community pursues five primary goals."

You’re eliding the how.

A pacer in a race runs at a steady, predetermined speed to help their runner run at a target pace.

It’s common terminology among runners and all kinds of racing.

Why, factoring in the design of Apple Intelligence?

Every Goodwill donation center takes everything you bring there. They even come out to your car and carry it in for you.

> in 2022, mainstream and westoid virtualism opinion was ``china is cut off from the future now`` (cue the clownface here). ``we cut off chinas legs`` yadayada

maybe where you were paying attention. were they also certain that americans wouldn't be paying the tariffs?

but lots of people who saw what china was doing with renewable energy and EVs rightly suggested this would put them on the path of independence w/r/t GPUs and LLMs.

this isn't like the ol' days where "japan can't do software". we knew china can.

your attitude isn't warranted.

Sure.. donation is easy, doesn't require a storage unit.

When I've had storage units and spent time there, and saw open doors and what people had in theirs, I stand by my take.

The whole point of the article posted above was that it's a bit weird how numerous and prevalent self-storage has gotten in the US.

VPS is production. Linux dev box is my local big box. Macbook just lets me move about and do iOS development. Orca lets me run agents either on linux box or locally on the macbook depending on how I'm feeling, and Orca handles all the worktrees & sub-agents for me (via Opencode). Everything runs in a tailscale network, ssh connects all the things.

My github repos all have CONSTITUTION.md files that keep multi-agent dev grounded. Production runs trigger github actions that automatically check logs daily, file bug reports, etc. I launch Orca and literally just type "checking in" and the CONSTITUTION.md file governs the scanning of github issues and prioritization of which issues need to be addressed. Another process prioritizes and bundles them. When I type "checking in" the Orca worktree handles the launching of sub-agents that fix things. Occasionally I weigh in with an opinion or pick a recommendation. If I'm in the mood to pay attention I'll ask it to find another round of bugs and let's keep going. Often I just let it close after the first round. When I tell it "done?" it does a full regression and a production box review. Code auto-deploys to production twice/day. I don't regularly push to production manually.

On Fridays the CONSTITUTION.md kicks off a strategy and roadmap review when I type "checking in". As I have ideas I add them to the roadmap in one of the worktrees. Generally nothing happens until they're reviewed on Fridays together, unless I push one manually.. which happens.

Hermes runs on the production box. I have a few skills and quick commands that lets me check in on production runs and the status of things. It's read-only by design, basically my version of a dashboard. If I have a thought, idea, research link, or question it'll write to a github issue and we'll deal with it in the next check-in.

Orca lets me do all this remotely from an iPhone, and I talk to Hermes via Telegram. I generally don't INITIATE new work using either of these. I report issues/ideas and let the process do the things. But I can, and have.. I just tend not to. The whole thing churns, and so my inclination to "jump in and do a thing" is less than before. My inclination now is to toss things into the machine and let the machine work the schedule. I'm at a point where I could easily automate 80% of this and do my manual things 1x/2x week and I think progress would stay steady. I'll get there at some point, but I like the level of engagement I'm participating in now.

Occasionally I use Claude Code as a watchtower review of things, or do a wholesale code review, or do a review of logs. But deepseek is much better at building this machine -- I built something manually over time and through a ship of theseus process it got ugly. Deepseek reviewed the situation and wrote the CONSTITUTION.md and designed the processes independently. It favors deterministic scripts for process but launches them via LLM and monitors for exceptions; also, no memory system which also disqualifies Claude from being at the center of this. Memory plugins didn't work well because instructions start accumulating all through the chain of instruction files (AGENTS.md, memory, etc) and that gets very undeterministic very quickly. Instructions are written once, reviewed/audited intentionally.. it's best not to let LLMs learn and write their own dynamically (yet).

I've since used it as a template for other projects I've started -- they work the same. Currently building the GTM agent that will handle all SEO, marketing, keywording, etc for my projects -- it'll be a significantly autonomous Hermes agent. Don't really need Claude for any of this and my Deepseek bill is $50-100/mo.