Hacker News Board Hacker News, browsed like a classic message board
Live data from Hacker News

The session you cannot take with you

earendil.com

Post reply on HN
Print view View original

131–140 of 238 posts

Re: The session you cannot take with you

#131

Post by pshirshov »

chrisweekly wrote: post #118
pshirshov wrote: post #103

I have some sort of a "solution" - my process keeps state that really matters (think "JIRA for agents") in a separate database (accessible over MCP). Essentially, I can terminate my session, start fresh one (in a different harness with a different model) and continue work with minimal losses. For subagents - I have a custom dispatch_agent tool which, essentially, just shells out.

sounds great; is any of it published / OSS?

Yes, but it's eclectic and annoying to setup. One of my goals is to be harness-independent and be able to jump between them, another is to let agents to work completely autonomously unless they are genuinely stuck. So, it's mixed with stuff related to sandboxing, VM/container access, GPU access, some skills and opinionated prompts and who knows what else.

The thing is here but you might find hard time setting it up unless you are a Nix user: https://github.com/7mind/cq

Re: The session you cannot take with you

#132

Post by rsfern »

steilpass wrote: post #59
the_mitsuhiko wrote: post #31

Earlier quoted context omitted.

We were thinking about it while writing it. I think one thing at least open source harnesses can do is push back on using some of these conveniences from the providers. For instance the moment we start compromising on the idea of portable sessions, then there will be less pressure (For instance people asked for OpenAI server side compaction or built-in native web_search support). The real thing that will take this al…

What are features that only work with session transparency / ownership? e.g. - with model XYZ and their open reasoning token we are able to improve our skill ABC by 20% - cross checking between models improves results by 10% and is only possible with full context visibility

[dead]

Re: The session you cannot take with you

#133

Post by utopiah »

falcor84 wrote: post #109
pcthrowaway wrote: post #85

Earlier quoted context omitted.

Also, see Android and iOS which have a monopoly on the mobile OS market

Sorry about the nitpicking, but s/monopoly/duopoly/

I don't think that's the economical definition of monopoly. It's not about 1 single actor owning the market but rather about unilateral change. Obviously a single actor owning 99.99% will be able to shape the market ... but also one owning a lot less, e.g. 30% if even if they don't collude with another actor owning e.g. 21%.

Re: The session you cannot take with you

#134

Post by cube00 »

springtimesun wrote: post #106
cube00 wrote: post #76

Earlier quoted context omitted.

> Conversations contain a bunch of junk anyway This is what brought me around to doing more agentic coding. I set the task, require tests and the strict linting must pass and then leave it to blow smoke up its own ass about what's going on. I see glimpses scrolling past of all the conversational language that used to frustrate me so much when using a chat interface and I can just let it flow on past. I come back when…

I have been doing this with opencode. Spend a fair bit of time composing and scoping a ticket. tmux on the server where the local inference lives, start a non-interactive session that starts with “read issue #123, do all your work in a feature branch” and ends with “push and open a PR”. Like not watching someone else load your dishwasher, you appreciate the end result a lot more if you don’t watch the process, even i…

Local inference can't arrive soon enough. On my inferior hardware the models still struggle to build the correct JSON to be able to call tools. Once either I get better hardware or the local models improve I'll happily leave it chugging away for a few hours to arrive at a solution because I know I'm not going to get token shock from all the looping if I'm running local inference.

Re: The session you cannot take with you

#135

Post by UltraSane »

jurgenburgen wrote: post #116
benob wrote: post #105

Earlier quoted context omitted.

People will keep hiding reasoning because it allows prompt injection https://arxiv.org/pdf/2603.12277 , in addition to facilitating distillation (you don't pay the full cost of RL)

Token-based reasoning also seems like it would be inefficient, there’s no reason it has to be English or even human understandable.

There have been models trained for latent space reasoning. It has a lot of advantages but the big drawback is the reasoning is completely opaque.

Re: The session you cannot take with you

#136

Post by zalebz »

eru wrote: post #16
qurren wrote: post #14

Earlier quoted context omitted.

Because with the alternative they'll require you to "confirm your e-mail" instead of just picking a password

I'm actually more annoyed by having to pick passwords than confirming my email.

when in a rush I will put in gibberish instead going through the pw manager steps and rely on resetting the pw at a later time

Re: The session you cannot take with you

#138

Post by springtimesun »

cube00 wrote: post #134
springtimesun wrote: post #106

Earlier quoted context omitted.

I have been doing this with opencode. Spend a fair bit of time composing and scoping a ticket. tmux on the server where the local inference lives, start a non-interactive session that starts with “read issue #123, do all your work in a feature branch” and ends with “push and open a PR”. Like not watching someone else load your dishwasher, you appreciate the end result a lot more if you don’t watch the process, even i…

Local inference can't arrive soon enough. On my inferior hardware the models still struggle to build the correct JSON to be able to call tools. Once either I get better hardware or the local models improve I'll happily leave it chugging away for a few hours to arrive at a solution because I know I'm not going to get token shock from all the looping if I'm running local inference.

I have spent way too much on hardware. I’m sure I will look back on that after the eventual price normalization with some regret. I do think we will look back at this shortage and name it as the thing that accelerated innovation at getting quality out of smaller models.

Hang tough. The other day someone posted a solution to get a model running off of SSDs. It won’t be fast, but it will be coming.

Re: The session you cannot take with you

#139

Post by theturtletalks »

rad-b wrote: post #128
theturtletalks wrote: post #120

This is exactly why Pi will win. It lets you hot swap models when one is struggling or straight up refusing the task. And since it works with any sub outside Claude Code, you can use it to try different models on OpenCode Go sub or even OpenRouter. As far as subagent prompts and results being obfuscated, I just let Pi spawn new agents. Using skills and extensions, I’ve essentially built a software factory using Pi an…

How did you decide on Pi over Opencode? What you see as the “edge” Pi has?

The extension catalog[0] for Pi is really nice and I feel like Pi's TUI is a bit lighter than OpenCode's. I use my custom terminal multiplexer on my phone using Tailscale so the lighter TUI is much better on mobile.

I haven't used OpenCode in months so this might've changed. I'm also thinking of giving JCode a spin since it's even lighter but doesn't have extensions.

0. https://pi.dev/packages

1. https://github.com/1jehuang/jcode

Post reply on HN