apitman

Throwback to lightscribe which I haven't thought of in many years: https://en.wikipedia.org/wiki/LightScribe

Just in case you haven't already read this: https://www.sebastianaaltonen.com/blog/no-graphics-api/

How do technical managers solve this problem? I've never been a real manager.

Sounds like it's already being moved for them

So far I've settled on one jumbo VM with many Incus containers inside. Nothing goes inside the VM that I can't afford for agents to exfiltrate. I've been really happy with this setup.

> now that number is interesting precisely because it was cited as the smallest non-interesting number

This made it click for me, thanks!

This is actually interesting. I'm no cryptographer. Do modern algorithms take into account that certain values should be avoided because they would be obvious things to try first in a brute force attack?

That sounds terrible. Passkeys work great for me with bitwarden.

Dang there's been twice as much time between SupCom and now as there was between TA and SupCom.

Yes, and I'll probably trust it eventually. But currently I always want to know when compaction is happening, so I can correlate any drops in quality or weird behavior.

This is my go-to resource

I might not be the best person to ask. I use Pi harness in tmux and just ask my current agent to spawn interactive pi instances in new tmux windows, create a sentinel file for each of them, and monitor the sentinel files for signals every 2 seconds.

Currently have auto compaction turned off. When the orchestrator's context is getting close to full, I have it write a handoff markdown file and point a fresh agent at it.

I do feel like I'm getting close to the point where I might be ready for something more sophisticated, especially wrt to subagents communicating with the orchestrator.

This is a pretty cool one I saw recently: https://youtu.be/_j806JHhCRo?si=tr8ENJo_VlJF-b4y

Love Handy. It has become a core piece of how I use computers.

In case it's helpful to anyone else using it, at first it felt a bit slow to me, because there was a noticeable pause after I finished a message before it would quickly type it all out. I changed the input method from direct to clipboard and it's way faster now, almost instantaneous.

I am looking at cost per task (and speed per task), both benchmarks and anecdotal experience.

> With my OpenCode Go sub of $10/month, DeepSeek is basically unlimited

My OpenCode Go monthly window was scheduled to reset this morning. It was sitting at 22% used despite me using DeepSeek V4.1 Flash heavily as my implementation agent the past couple weeks (I use gpt-6.1-sol high for planning/orchestration).

I had 1.5 hours left so I fired up first 10, then 20, and finally 50 concurrent subagents all working on reverse engineering C code from an old PC game. They found over 100 new functions.

This is the first workload I've found that could make a dent in my sub. It got my 5 hour window to 85% used, but sadly my monthly was still only at about 35% when it reset. So that cost maybe $2.

The tightening of subscription value has already begun. dsv4.1f is already worth paying for at market API prices. Maybe it goes to 2x because apparently no one has figured out how to match DeepSeek's insane caching efficiency, but I don't see it getting much worse than that.

Plus you can also get dsv4.1f subsidized. OpenCode Go gives 4x if I understand their pricing correctly. Anecdotally, I feel like I get way more out of my $10/mo OpenCode Go sub for the price than my $20/mo ChatGPT, even using gpt-6.1-sol high which is very cheap, and I have yet to convince myself dsv4.1f is a worse model.

The argument that most people are making isn't that dsv4.1f is better than frontier, but that it's good enough for most tasks, faster, and way cheaper.

> if one looks at the CoT, it's evident that it's way way stupider than frontier models

Frontier models don't show the full CoT

> Even so why would anyone not sleep on a model they cannot run?

Because it's an open model so providers compete on price.

How much VRAM total you using for this? I have a bunch of 3060s in a threadripper and thinking I might need to give Flash Next a try. Currently using 27B.

This is a meaningless metric without knowing how long the sex takes

Honest question: if that's the case why do my GPUs draw their full TDP during inference?

It's obvious unless you have multiple requests from different models in flight at the same time, and the sum total usage comes out to less than a single percentage.

Do Anthropic quotas give you precise remaining token counts or something? I have something similar set up for tracking my ChatGPT usage but it only gives percentages remaining, which is a pretty coarse metric.

I use OpenCode Go. I've also used the DeepSeek provider through OpenRouter a bit in the past and it seemed solid.

Money is also money, which anyone who makes heavy use of parallel subagents will quickly learn.

What's the most important task you would/wouldn't trust with an agent below the line?

You have a lot of control over compaction, both directly by changing compaction settings, and indirectly by how you structure your codebase/docs so agents use less tokens.