porker

Congratulations on the project!

I haven't run into problems with Dragonfly yet, was it only OOM you encountered with it? Garnet I had GC pauses causing problems, so I dropped that.

With RAM prices where they are, I'm expecting to see a lot more of this in the next year.

We've been transitioning in-memory caching for web apps to tiered or on-nvme caching. It's an order of magnitude slower, but no one really noticed.

> Japanese houses/apartments also typically have a house ventilation system, meant to run when it's humid.

Do they have Mechanical Ventilation and Heat Recovery (MVHR) or is this more like Aircon? I've recently moved somewhere more humid and I'm looking to get a grip on what other countries do.

Spot on.

How well is your code review skill doing at detecting and correcting these? History in comments in git is so annoying! As is missing why A didn't work but B does. None of the models I've tried get this right

> Why? Because it has more/better features. Or you mean something else?

I mean something else. Zoom out, why do people need, or want, a tool like herdr?

What has led people to this point? Is it because they need terminal multiplexing to spawn agents, instead of using built-in subagents? Do they like cute sheep icons? What made having multiple terminals open unappealing? Is it the built-in alerting when attention is needed? Is it only applicable to people running their agents on remote machines?

When I look at these kinds of tools, that is the question I can't answer because I suspect I haven't run into the pain points they address yet, despite running multiple LLM sessions in multiple projects simultaneously.

It answers the "What" but not the "Why?"

herdr users (and all the other terminal multiplexer users): what am I missing?

I use cmux because I like tabbed terminals on macOS grouped by project, saves messing with our daft window management.

What is it that makes herdr et al so popular with LLM users?

How would you quantify the magic of these older charts? What is it that makes them have charm and character?

It's always fun to see what works for others, because for my work it'd have to be Sol > Fable. Fable makes too many mistakes.

Coordinating agents though? Fable any day.

Some of these resets were because of bugs in the 5.6 launch that caused subagent-users to burn _a lot_ of extra tokens. It was placating customers.

It is impressive they've got the capacity to do so.

> Fable 5 is sick. [It] solves almost any task from start to finish, the way it should be done — no errors, perfect code. It's a miracle.

> As for GPT-5.6 Sol — it doesn't even come close. I honestly don't understand why people even try to compare them.

What kind of problems are you working on? I like Fable but when planning work on a complex C codebase it's making more mistakes than 5.6 Sol xhigh for me.

In what scenarios is Fable giving you "no errors, perfect code"?

For gpt-5.5 I build up that session context into a markdown file, and then I start a new session and give it the markdown file with the instructions for what to do.

I'm guessing this works better because it can always go back and re-analyze the saved context.