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

191–200 of 238 posts

Re: The session you cannot take with you

#191

Post by DenisM »

vamsiraju wrote: post #165

Maybe we don't take sessions, but take something else that we can fully control. Sessions were always a poor substitute to capture or archive the basis on which the implemented code rested on. They get noisy over time even with compaction, were not always inspectable, no real science behind when to ditch a session and start a new one, and rarely have a clean mapping to the work done. So instead of trying to archive s…

Suggestions? My attempts to get the agent to summarize the discussion largely failed. Other options I’m considering is capturing design, implementation plans, and maybe sub-plans. I’m Other words precursor to actions. Another idea is to get an agent to review code post-action and capture that. In other words action outcomes. The actual reasoning is between these “checkpoints” and remains hidden. But maybe that’s ok.

Re: The session you cannot take with you

#192

Post by CuriouslyC »

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?

Pi is more minimal and it can be used to create fancier custom agents for various tasks with plugins. OpenCode is nice if you are only coding though, then the difference isn't really that big unless you want an unusual interface/behavior.

Re: The session you cannot take with you

#193

Post by mystifyingpoi »

eru wrote: post #98
mystifyingpoi wrote: post #36

Earlier quoted context omitted.

I'm opposite. If my email goes down, or I do not have access to it, I cannot login. With passwords I still can.

My email is with Google. They are less likely to go down than my password manager.

Well then you need a better password manager. Like a .kdbx file which is ~100% available, given enough copies I guess.

Re: The session you cannot take with you

#195

Post by nlawalker »

Reasoning, external context, compaction, subagents, etc. are all things that these service providers don't really want you to know about, care about or have any insight into, they want them to be implementation details. It's incredibly inconvenient to them that their customer base is in the business of prying into implementation details and trying to use the individual pieces of what they want to offer as an end-to-end product.

Re: The session you cannot take with you

#196

Post by odo1242 »

monknomo wrote: post #181
utopiah wrote: post #133

Earlier quoted context omitted.

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%.

what you are describing sounds like an oligopoly not a monopoly. A company cannot realize monopolistic benefits without > 50% control of a market. That's not to say there aren't benefits to a large market share, but they are different and we have different terms for them.

US law sets the breakpoint for when a company is considered a monopoly at 30% of a market. It's never actually enforced, of course, but may be worth noting.

Re: The session you cannot take with you

#197

Post by furyofantares »

I'm having Claude/Codex continue each others' sessions pretty frequently without issue. I have max plans on both and still hit limits, whenever I do I open the other and say "resume the last session was working on in this repo" and I don't have any issues.

It probably does degrade quality somewhat. But so does compacting context and that happens all the time too.

Re: The session you cannot take with you

#198

Post by stephbook »

Honestly, i don't need to know what happened internally at Google when I searched. I don't need to know what filters an email passed before it landed in my inbox. I don't need to know when my Notes app synched with what server version.

And I don't need any of that in an AI conversation.

If it's a truly long and important conversation, stay with the provider for that one only and start all new ones elsewhere. But I've never needed that.

Re: The session you cannot take with you

#199

Post by vamsiraju »

DenisM wrote: post #191
vamsiraju wrote: post #165

Maybe we don't take sessions, but take something else that we can fully control. Sessions were always a poor substitute to capture or archive the basis on which the implemented code rested on. They get noisy over time even with compaction, were not always inspectable, no real science behind when to ditch a session and start a new one, and rarely have a clean mapping to the work done. So instead of trying to archive s…

Suggestions? My attempts to get the agent to summarize the discussion largely failed. Other options I’m considering is capturing design, implementation plans, and maybe sub-plans. I’m Other words precursor to actions. Another idea is to get an agent to review code post-action and capture that. In other words action outcomes. The actual reasoning is between these “checkpoints” and remains hidden. But maybe that’s ok.

What you said is pretty much the same somewhat tangential approach I am taking too. Force the agent to write code alongside another set of docs which form the basis- Intent (functional and non-functional requirements), Blueprint (architecture etc.), and Description files (describe the code at a high level alongside every source file). This information set is not the same as the reasoning/thinking trace information thats in the session, but reading this somewhat compressed set is easier, helps me better understand whats happening in the final output with lower effort than if i read the entire thinking/reasoning trace in the session and tried to grok what the agent did to generate the code.

Re: The session you cannot take with you

#200

Post by abustamam »

furyofantares wrote: post #197

I'm having Claude/Codex continue each others' sessions pretty frequently without issue. I have max plans on both and still hit limits, whenever I do I open the other and say "resume the last session was working on in this repo" and I don't have any issues. It probably does degrade quality somewhat. But so does compacting context and that happens all the time too.

Out of curiosity, what are you building, and how? Im working on two side projects and I have to try hard to hit the limit with Claude (like use fable and a deep research task)
Post reply on HN