The session you cannot take with you • Hacker News Board

Re: The session you cannot take with you

#111

Post by trollbridge » Fri, Jul 31, 2026, 11:27 AM UTC

charcircuit wrote: post #34

bob1029 wrote: post #28

OpenAI has been nudging their users toward the Responses API lately. Chat completion can still do everything if you are clever. The obvious reason to push everyone into the Responses API is that the reasoning process can be locked down and encrypted. The semantics of the chat completion API are fundamentally transparent. 100% of the tokens are visible. If you have patience and the willingness to endure a little bit o…

OpenAI has hidden its reasoning for almost 2 years.

For codex specifically, it seems to have become much worse as of a few weeks ago.

Re: The session you cannot take with you

#112

Post by lukebuehler » Fri, Jul 31, 2026, 11:27 AM UTC

the_mitsuhiko wrote: post #107

lukebuehler wrote: post #104

Earlier quoted context omitted.

Yes, I agree with your point and article regarding hidden or sealed state. So, I'm aware that this is a separate point from the article, and I'm well aware of Pi's model abstraction layer, which is one of the best (others are a big pain... looking at you LangChain). I've come to the conclusion that full session portability will come to an end very soon, and really already has. Partially because of the hidden state st…

It definitely is getting quite challenging. That said, a lot of user experiences are modelled around retaining transcripts for longer than a few minutes. Every claw or chat based application creates a very real user experience desire of that conversation being something you can continue, even weeks after when the model might have gone away / have been replaced. Now unless you fully want to commit yourself to one prov…

All the power to you, and I hope Pi will be able to continue its unified layer.

However, there is an alternative: model the session fully in the provider native structures, extract only what is needed for harness specific branching, and treat a provider switch as a _migration_ that you apply at the time of the switch. So treat a provider switch as a migration from provider A to B, with custom logic, etc. This is IMO a more sustainable model. But I'm aware that Pi, OpenClaw, et al have their commitments here.

Re: The session you cannot take with you

#113

Post by yoavfr » Fri, Jul 31, 2026, 11:28 AM UTC

domh wrote: post #84

Does there need to be an open standard or file format for context? Open models should align on the same format for portability? Could be sqlite based so it can be queried by other programs?

[dead]

Re: The session you cannot take with you

#114

Post by chrisweekly » Fri, Jul 31, 2026, 11:31 AM UTC

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/

not nitpicking; huge difference between 0 and 1 competitor

Re: The session you cannot take with you

#115

Post by springtimesun » Fri, Jul 31, 2026, 11:34 AM UTC

iwassayinbourns wrote: post #45

sdoering wrote: post #43

> “Most People Do Not Switch Models Mid-Session” I do, quite regularly. Because different models have different strength (for example when producing text for live presentations based on the text for a reading deck). Or when it comes to other aspects of the work. I regularly switch between open wheight models and closed models. I know, I am a tiny minority here. And this behavior only ever started a few weeks ago. But…

Out of interest, what models do you find work best for producing text for live presentations based on the text for a reading deck?

I agree with OPs commment about K3 being pretty good. Claude can be good too, but it didn’t get there until I made a writing rule. It has 4 basic sections:

* a style guide with examples for different tasks (it’s sufficient to name writers with some attributes you like if they are famous)

* mechanical formatting, output and other preferences

* a short list of the things I consider most important in different writing context, this the the squishiest overall

* a (growing) list of banned Claudisms. Nothing is really banned, but it includes things like: you may only ever use “scar tissue” in reference to actual regenerated tissue, never metaphorically

The thing is you have to be discipline with it. Every time they output something you don’t like, you’ve got to spend time verbalizing what about it you don’t like and in what context and then add it to the rules file. The first few docs you generate will take a long time, but each repeated generation gets better and by the 4th are 5 time you do this it’s like 80% of the way to where it needs to be and that generalizes well.

Re: The session you cannot take with you

#116

Post by jurgenburgen » Fri, Jul 31, 2026, 11:34 AM UTC

benob wrote: post #105

solarkraft wrote: post #9

This is an important article. I hadn’t realized it was already getting this bad. Like a frog enjoying a nice warm bath ... > Most people do not switch their operating system or phone provider every week either. But even if you do not utilize that freedom, it matters because it changes the relationship you have with the provider and the provider has with you. This is why it’s important to utilize your freedoms. Do NOT…

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.

Re: The session you cannot take with you

#117

Post by eddythompson80 » Fri, Jul 31, 2026, 11:34 AM UTC

stavros wrote: post #64

aidos wrote: post #51

Earlier quoted context omitted.

I think you can use a passkey now.

Only for people invited to the Tailnet. To create your own account, you still need a third party.

You can host your own identity provider. Authentik, Keycloak, authelia or Zitadel work.

I don’t fully agree with tailscale’s decision to not want to be an identity provider but I understand it on some level. It simplifies their service greatly and the amount of asks for that will essentially have them build a full enterprise Entra-like solution that would be a constant maintain headache and they are not interested in that.

Re: The session you cannot take with you

#118

Post by chrisweekly » Fri, Jul 31, 2026, 11:36 AM UTC

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?

Re: The session you cannot take with you

#119

Post by jurgenburgen » Fri, Jul 31, 2026, 11:36 AM UTC

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.

Then what’s the point of it all? Just use Google login.

Re: The session you cannot take with you

#120

Post by theturtletalks » Fri, Jul 31, 2026, 11:38 AM UTC

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 and a custom terminal multiplexer.

It’s a shame apps like T3 Code and other UI for terminal apps don’t support Pi and I’m glad to use the terminal above those that lock me in further.