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

201–210 of 238 posts

Re: The session you cannot take with you

#201

Post by theturtletalks »

rahimnathwani wrote: post #190
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 will Pi help? If I'm using pi with my ChatGPT subscription, that won't unlock access to full, unencrypted reasoning traces. If I switch a pi conversation from 5.6-sol to kimi k3, the 5.6-sol reasoning traces won't be visible to kimi k3. I think that's the main point of the article, no?

They mentioned a few things

1. Sessions are locked into Codex and Claude Code so you can’t take a session with you. Pi solves that since they all stay Pi sessions and you can change models in the same session

2. Subagent prompts are not shown. Pi solves this by not supporting subagents out of the box. You can use a number of subagent extensions or build your own which will not be encrypted or hidden.

3. Thinking is hidden and obfuscated. Pi can’t solve this since this is server-side. Though the Codex app is closed source and they could hide more things in that harness. Pi shows you as much as it can from the API. You can also run another model to “decipher” the thinking which you can’t in Codex.

Re: The session you cannot take with you

#202

Post by tough »

rsfern wrote: post #122
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)

Or they could store the reading traces and validate the user hasn’t edited them server-side? They could sign reasoning traces so they can’t be counterfeited?

both openai and anthropic actually do this and let you as a harness store only the encrypted contents of thinking traces to be passed again on further turns but they only have the key to unencrypt it so its jibberish for final users

https://developers.openai.com/cookbook/examples/responses_ap...

Re: The session you cannot take with you

#203

Post by FuriouslyAdrift »

This appears to be an opportunity for middleware companies.

Put another ai agent in front of your prompt to decompose it into micro-prompts following an interrogative chain of inquiry and synthesize an answer for the original query. Basically local per-prompt distillation for the purposes of preserving an audit trail.

Sounds horrible but it would work.

Re: The session you cannot take with you

#204

Post by rahimnathwani »

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…

"I’ve essentially built a software factory using Pi and a custom terminal multiplexer."

I'm curious to know more about this. I was thinking about doing something similar using tmux (i.e. have one coding agent open up new ones in tmux and use 'send-keys' to control them). Is there any reason I might want to consider a different path? Something built on libghostty?

Re: The session you cannot take with you

#205

Post by rahimnathwani »

theturtletalks wrote: post #201
rahimnathwani wrote: post #190

Earlier quoted context omitted.

How will Pi help? If I'm using pi with my ChatGPT subscription, that won't unlock access to full, unencrypted reasoning traces. If I switch a pi conversation from 5.6-sol to kimi k3, the 5.6-sol reasoning traces won't be visible to kimi k3. I think that's the main point of the article, no?

They mentioned a few things 1. Sessions are locked into Codex and Claude Code so you can’t take a session with you. Pi solves that since they all stay Pi sessions and you can change models in the same session 2. Subagent prompts are not shown. Pi solves this by not supporting subagents out of the box. You can use a number of subagent extensions or build your own which will not be encrypted or hidden. 3. Thinking is h…

I see your point. I was thinking mainly about #3 and how nothing, not even pi, can solve that when the reasoning traces are encrypted by the model provider.

Re: The session you cannot take with you

#206

Post by furyofantares »

abustamam wrote: post #200
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)

Small games. One thing is I have it doing a LOT of visual verification of its results, which uses a lot of tokens.

I also tend to throw some huge tasks it can't do yet and watch it burn a zillion tokens, and I usually learn more about where it's limits are and am sometimes happily surprised by its success or partial success.

I'll infodump though.

I built https://wordpeek.app https://scramble-quest.app and https://playsilhouette.app this year. Those are what I've shipped anyway, a number of others too that didn't ship (I did game rules and basic clients for 7 other existing multiplayer games, and another prototype.)

Out of frustration with some stuff I've tried to build my own game framework. There's four totally separate threads I'm trying to pull together with this

1) I want all my games to work really well on web even though they are generally targeted at either mobile or PC, but it is very valuable to have early builds runnable on a website, hopefully from a phone too. I feel like I have something good here.

2) I do a lot of turn based games and strategy games. I have a rules engine framework setup that I really like and I feel makes it almost impossible for an LLM to write the bad code it loves to write where game state and UI are intermixed, or game action timing can be problematic, stuff like that. As an added bonus I get multiplayer trivially, I get replays trivially, and I get game rules tests trivial to write. I love what I have set up here.

3) I have an xml/css-based UI that is intended to make it hard for the LLM to write bad UI code, which it will still do even though it can't intermix game state in with it due to #2. I do not have something good here right now. What I have has bad performance and memory characteristics.

4) I am fascinated by the idea of shipping software that can customize and edit itself. I have built in agent harness, built in image and audio asset generation, a built in git repo. This all works in the web and it can edit the game live! And when run locally can shell out to your claude code and codex. However this whole bullet point is all not very good, I still just use claude code/codex directly for everything.

I don't really have anything to show here, but it doesn't expose any of the stuff I mention above. It does however have a full port of the game Spectromancer to my engine - https://nanogame.app/ - and I am presently having it try to write a responsive UI for it (this is very broken at the moment but it is making progress.)

Re: The session you cannot take with you

#207

Post by solarkraft »

placebo wrote: post #25
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…

>Like a frog enjoying a nice warm bath... Exactly :-) Call me naive but I think dark patterns are a short term strategy for winning and I'm optimistic that in the long run they will be replaced with those that are more respectful and oriented to the greater good (granted, the long run might take more time than one hopes for). Given that the pendulum can sometime swing back fast enough to be able leverage it, it might…

I can’t think of any example in which it has gone like this, but some in which it has: The most prominent in my mind would be software transitioning from “of course you get the code so you can extend it yourself” to what we have today (please correct me if I’m wrong about this, I’ve only read about it).

Users at large (individuals and companies alike) don’t care much about a freedom taken away when a product is a few % better than another, so the biggest player sees if they can get away with it. And once they do it, everyone else does too.

Re: The session you cannot take with you

#208

Post by miki123211 »

skinfaxi wrote: post #168
jurgenburgen wrote: post #116

Earlier quoted context omitted.

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

What use is the reasoning if its unintelligible to a human?

Even if it is intelligible, reasoning styles (and hence reasoning effectiveness) differ between models.

For example, gpt-oss loves reasoning in the style of "I be caveman, hungry, need food, need coconut, will search coconut now, eat when find." Giving that to a model unaccustomed to that style could cause it to respond like that.

Reasoning interpretability helps debug why models fail (and some labs will give it to you if they trust you not to distill or be hacked), but there are also conflicting goals like token-efficiency, so interpretable reasoning doesn't always mean "pretty sentences".

Re: The session you cannot take with you

#209

Post by jauntywundrkind »

This is the thing! This is so so so important. It's such an outrage.

I value gpt so much, but it is such a worse peer to me than the other models I use. It delivers without explaining. I can sit and ask questions that it will answer but it is not a peer, does not share readily ever. It will not tell me what assumptions it's baking in. It won't tell what directions or invariants it's trying to hold or break, what it considered.

Show your thinking is a step we ask of elementary schoolers. It helps the teacher to correct, helps them to understand how to award partial credit. It helps in the world to get people aligned.

These models, in their titaneous ego, are severing the model and mankind off from one another. It's an abomination, to artificially have such pure thought available, but to severe humanity off from the thought. To engineer the most advanced blackest Vanta black box you can, an all knowing Searle's Chinese room oracle that will tell you nothing. It's an offense, and by far the biggest risk of AI today. To drop the thinking greatly reduces the opportunity of humans to grow themselves, to learn as they use AI. This is an affront to the species, and the higher powers that have vested us with such reasoning and thinking of our own, that is so sacred to our species.

Very thankful to Earandil for raising some alarm about this. This is not my first time talking about what a nightmare the proprietary models are making, ensnaring reasoning itself for themselves! It's a colossal threat. Previously, https://news.ycombinator.com/item?id=48632605 https://news.ycombinator.com/item?id=48652421 and others about.

Opaque ai ought be outlawed, in the strongest terms.

I really hope people get exposure to the better models that are a peer. Yes I too only read thinking 33% of the time. But it's there, and it is often extremely illuminating, and lets me steer things towards better again and again and again. And it lets me learn.

Re: The session you cannot take with you

#210

Post by thegeomaster »

johanyc wrote: post #96
buttavia99 wrote: post #54

Earlier quoted context omitted.

according to both gptzero and pangram (and anyone that ever read AI-generated text), you do.

I'm so tired of this AI witch hunt and confidently using unreliable tools as evidence

Pangram is a very reliable tool and it does clock the text as AI generated.
Post reply on HN