Hacker News: planckscnst

New comment by planckscnst in "Multi-Stream LLMs: new paper on parallelizing/separating prompts, thinking, I/O"

planckscnst — Fri, 22 May 2026 06:03:03 +0000

Hm. I'll have to rethink how I do context management ( https://github.com/Vibecodelicious/context-bonsai-agents#con... )

New comment by planckscnst in "Ask HN: What are you working on? (May 2026)"

planckscnst — Mon, 11 May 2026 19:17:18 +0000

Yes, also happening more or less continually instead of waiting for the context to bloat up.

You also have some control over it. You can say something like "prune away the work we did on the UI. Make sure to remember that users can upload multiple images now"

New comment by planckscnst in "Ask HN: What are you working on? (May 2026)"

planckscnst — Mon, 11 May 2026 07:58:11 +0000

I'm working on [Context Bonsai][1] - LLM harness tools that allow the LLM to prune messages out of the context, leaving behind a summary and keywords instead. In addition to a "prune" tool, there is a "retrieve" tool that allows it to recall the messages if needed.

In addition to these tools, I'm also building automation that will port the tools from the reference implementation (OpenCode) to other harnesses (Claude Code, Cline, Pi, Gemini, Kilo, Codex, others to come?). As well as automation that will either cherry-pick or re-implement commits onto the latest head from upstream.

[1]: https://github.com/Vibecodelicious/context-bonsai-agents#con...

[2]: https://blog.vibecodelicio.us/posts/how-i-fixed-context-wind...

New comment by planckscnst in "OpenCode – Open source AI coding agent"

planckscnst — Fri, 20 Mar 2026 22:52:03 +0000

I love OpenCode! I wrote a plugin that adds two tools: prune and retrieve. Prune lets the LLM select messages to remove from the conversation and replace with a summary and key terms. The retrieve tool lets it get those original messages back in case they're needed. I've been livestreaming the development and using it on side projects to make sure it's actually effective... And it turns out it really is! It feels like working with an infinite context window.

https://www.youtube.com/live/z0JYVTAqeQM?si=oLvyLlZiFLTxL7p0

New comment by planckscnst in "Push events into a running session with channels"

planckscnst — Fri, 20 Mar 2026 06:01:08 +0000

I'm using Fedora with KDE and I haven't seen any notifications and had no idea it did this. I'll see if I can figure out what's going on in my system and maybe it will help other people.

New comment by planckscnst in "Meta will shut down VR Horizon Worlds access June 15"

planckscnst — Thu, 19 Mar 2026 05:19:44 +0000

I am one of those people who love VR gaming done well. There is a game called Super Rumble built by what I think is a subsidiary of Meta. It's a very well executed arena FPS concept. There are just a couple dozen people in the world who are really skilled and play enough for me to recognize them and be glad they're playing when I'm also online. It's magical when there are good people on this thing playing together.

I hope it's something we can figure out how to propagate despite the seemingly limited interest. I suspect anyone who liked playing quake arena games would love this game if they are not susceptible to motion sickness.

I recently started exploring how to port open source shooters (red eclipse, warsow, nexuiz) to the platform and realized there are several considerations that make games designed for VR special that a pure port wouldn't hit.

New comment by planckscnst in "Ask HN: What Are You Working On? (March 2026)"

planckscnst — Mon, 09 Mar 2026 03:47:51 +0000

I'm working on "context bonsai" which is currently a plugin for OpenCode that allows the LLM to self-edit its own context. It works like compaction, but it can retrieve back the compacted info if needed. And it's not just when the context is completely full, and it doesn't compact the entire context - it picks messages / tool calls where the details are no longer necessary, like a debugging session that is already solved or feature implementation that is complete and you've started on implementing the next feature.

I've also used tweakcc to make this work in Calude Code and plan to also do one for open source coding agents - codex, pi, Gemini, etc. And I'm also doing Livestreams of the development process.

https://github.com/Vibecodelicious/opencode

New comment by planckscnst in "Welcome to the Wasteland: A Thousand Gas Towns"

planckscnst — Thu, 05 Mar 2026 01:53:50 +0000

I mostly use LLMs in a zero-touch way - I never actually edit code and I almost never read it. But I do still dive into the details by exploring it with targeted questions through the LLM. Sometimes I go through ridiculously long sessions to get the LLM to "see" the correct/optimal/simplest/etc solution itself. There are many times when it simply never gets there no matter how close I get the horse to the water. I recently did one of these sessions yesterday and it reinforced my impression that systems like gastown and pure Ralph loop style is just not ever going to have the quality I'm looking for, and it's going to cost a lot of money not to get there.

I've honed a relatively decent flow that requires interaction from me for important parts (mostly) while making its own decisions at the not-important parts (mostly). This results in being able to send the agent off on an hours-long dev cycle and have relatively decent results after that need a few minor fixes. I think this is the best style for the current generation of AI

New comment by planckscnst in "Anthropic officially bans using subscription auth for third party use"

planckscnst — Thu, 19 Feb 2026 06:07:16 +0000

When they blocked OpenCode, I was in the middle of adding a feature. I don't think it's possible to mimic CC in an undetectable way and have the feature work.

The feature allows the LLM to edit the context. For example, you can "compact" just portions of the conversation and replace it with a summary. Anthropic can see that the conversation suddenly doesn't share the same history as previous API calls.

In fact, I ported the feature to Claude Code using tweakcc, so it literally _is_ Claude Code. After a couple days they started blocking that with the same message that they send when they block third party tools.

New comment by planckscnst in "Anthropic officially bans using subscription auth for third party use"

planckscnst — Thu, 19 Feb 2026 05:50:52 +0000

They even block Claude Code of you've modified it via tweakcc. When they blocked OpenCode, I ported a feature I wanted to Claude Code so I could continue using that feature. After a couple days, they started blocking it with the same message that OpenCode gets. I'm going to go down to the $20 plan and shift most of my work to OpenAI/ChatGPT because of this. The harness features matter more to me than model differences in the current generation.

New comment by planckscnst in "Terminals should generate the 256-color palette"

planckscnst — Wed, 18 Feb 2026 17:59:24 +0000

"selected" and "highlighted" would also be useful

New comment by planckscnst in "Improving 15 LLMs at Coding in One Afternoon. Only the Harness Changed"

planckscnst — Fri, 13 Feb 2026 08:07:27 +0000

There is so much work we can do with harnesses that can make the already existing models so much more capable. I definitely feel the author's frustration as I've also been working on some harness stuff. When Anthropic subscriptions got cut off from OpenCode and other third party tools, I was very disappointed because the model I do the most work in is Claude and I was specifically developing a change [1] in the hopes it would make Claude even better. After that, I started implementing the feature in Claude Code directly (using tweakcc) and after a day of working on that, they even block my tweaked Claude Code with the same message. It means I simply won't be able to use this idea with Claude at all

[1]: the README.md describes the Context Bonsai features in my fork here: https://github.com/Vibecodelicious/opencode

New comment by planckscnst in "Ask HN: What are you working on? (February 2026)"

planckscnst — Mon, 09 Feb 2026 06:16:01 +0000

Yes - I think there is untapped potential into figuring out how to understand and use the latent space. I'm still at the language layer. I occasionally stumble across something that seems to tap into something deeper and I'm getting better at finding those. But direct observability and actuation of those lower layers is an area that I think is going to be very fruitful of we can figure it out

New comment by planckscnst in "Ask HN: What are you working on? (February 2026)"

planckscnst — Mon, 09 Feb 2026 05:55:11 +0000

Yes, I have already made deliberate cache decisions and plan to do more once it's working the way I imagine. I think the trimmed down context will have way bigger effect than the cache stuff, though.

As far as I understand, it's caches are not a "next-turn" thing, but a ttl thing.

I made the "retrieve" tool, which is what pulls back previously removed content, append to the conversation rather than putting it back where it previously was. But it's a but premature to really know if that's a real optimization.

New comment by planckscnst in "Ask HN: What are you working on? (February 2026)"

planckscnst — Mon, 09 Feb 2026 02:00:41 +0000

I'm working on lots of projects. My favorite is what I call "context bonsai" where I'm giving LLM harnesses the ability to surgically edit the context. It's available as a tool. You can say "remove that failed debugging session and write a summary of what we learned." Or you can take a more hands-on approach and say "remove messages msg_ID1 through msg_ID2". The removal leaves a summary and keywords, and the original messages can be pulled back into context if the LLM thinks they're useful.

I would really like people to try it out and report bugs, failures, and successes.

https://github.com/Vibecodelicious/opencode/blob/surgical_co...

I'm currently trying to get the LLM to be more proactive about removing content that is no longer useful in order to stay ahead of autocompaction and also just to keep the context window small and focused in general.

New comment by planckscnst in "Show HN: Emotion as cognitive infrastructure in AI, not just output"

planckscnst — Fri, 06 Feb 2026 10:00:58 +0000

I think this is a valuable direction for research to take. I suspect human emotion is represented in the training data and that there is some underlying model representing human emotional systems present within current LLMs. If we can understand how the model affects response given certain qualities in provided stimuli, then we can effectively use this embedded model to improve our understanding of both LLMs and Humans and also get more productive output from LLMs.

New comment by planckscnst in "Claude Opus 4.6"

planckscnst — Fri, 06 Feb 2026 09:52:14 +0000

I've found this orchestrator+reviewer+judge setup to yield much better results than anything else I've tried. And it's such a simple setup - a few markdown files.

I'm also creating one that is similar, but purpose-built for making the plans that this setup can orchestrate. It still needs some tweaking to get agents to follow it better - it still takes additional prompting to nudge it down the proper path. But I've had similar benefits - sending plans through this adversarial review loop has yielded significant improvements in final output.

https://github.com/Vibecodelicious/llm-conductor/blob/main/p...

New comment by planckscnst in "Claude Opus 4.6"

planckscnst — Fri, 06 Feb 2026 00:23:03 +0000

That's so strange. I found GPT to be abysmal at following instructions to the point of unusability for any direction-heavy role. I have a common workflow that involves an orchestrator that pretty much does nothing but follow some simple directions [1]. GPT flat-out cannot do this most basic task.

[1]: https://github.com/Vibecodelicious/llm-conductor/blob/main/O...

New comment by planckscnst in "Anthropic blocks third-party use of Claude Code subscriptions"

planckscnst — Fri, 09 Jan 2026 05:03:54 +0000

The API key is not a subscription. The title says subscriptions are blocked from using third-party tools. Or am I misunderstanding?

New comment by planckscnst in "Anthropic blocks third-party use of Claude Code subscriptions"

planckscnst — Fri, 09 Jan 2026 04:30:50 +0000

I've been (adding an OpenCode feature that allows the LLM to edit its own context)[1] and trying to debug an issue with the Anthropic API because I'm calling it with missing fields that it expects. I hope my multiple erronious API calls aren't what triggered this decision

[1]: https://github.com/Vibecodelicious/opencode/tree/surgical_co...