News for hackers. Stuff that matters.
Re:Claude Code Routines by ElFitz on Tuesday April 14, 2026 @07:12PM (#47772662)
> Not because I can't see a use-case for them, but because I have 0 trust in them

> […]

> Put another way, LLM companies are trying to climb the ladder to be a platform, I have zero interest in that, I was a "dumb pipe", I want a commodity, I want a provider, not a platform.

That is my sentiment precisely, and a big reason why I’ve started moving away from Claude Code in the past few weeks when I realised how much of my workflow was becoming tied to their specific tools.

Claude Code’s "Memory" feature was the tipping point for me, with the model committing feedbacks and learnings to some local, provider-specific path, that won’t persist in the git repo itself.

That’s fine for user preferences, not for workflows, rules, etc.

And the latest ToS changes about not being allowed to even use another CLI made up my mind. At work we were experimenting with an autonomous debug agent using the Claude Code cli programmatically in ephemeral VMs. Now it just returns an error saying we can’t use subscriptions with third-party software… when there is no third-party software involved?

Anyway, so long Claude.

Re:Claude Code Routines by dzink on Tuesday April 14, 2026 @08:00PM (#47773034)
They can’t allow third party software because the third parties save the outputs of Claude responses and distill them into new models to compete with Claude.
Re:Claude Code Routines by fluidcruft on Tuesday April 14, 2026 @08:32PM (#47773239)
This distilling sounds wonderful to me as an end user. Is there some place we can donate our chats and output?
Re:Claude Code Routines by thomasm6m6 on Tuesday April 14, 2026 @09:11PM (#47773470)
There's https://github.com/badlogic/pi-share-hf by the creator of pi-coding-agent, to redact session data and publish on Huggingface. You can find others of the same idea for Claude Code/Codex on Github, though of varying redaction quality. Or have your LLM fork pi-share-hf to work for your preferred coding agent.

Clem Delangue (HF CEO) tweeted about this[1] and mentioned https://traces.com/ for exporting Claude sessions

Edit: It looks like HF now supports importing your agent's session directory directly[2] (I hope they're redacting PII?)

[1] https://x.com/ClementDelangue/status/2041189872556269697

[2] https://huggingface.co/changelog/agent-trace-viewer

Re:Claude Code Routines by thomasm6m6 on Wednesday April 15, 2026 @12:19AM (#47774632)
And OpenCode just added `opencode export --sanitize` for PII redaction

https://github.com/anomalyco/opencode/releases/tag/v1.4.4

Re:Claude Code Routines by woctordho on Wednesday April 15, 2026 @12:02PM (#47781043)
There is DataClaw https://github.com/peteromallet/dataclaw which uploads your Claude Code chats and more to HuggingFace in a single command. Nowadays there are many similar tools.
Re:Claude Code Routines by Forgeties79 on Tuesday April 14, 2026 @09:23PM (#47773540)
Yeah who just goes and indiscriminately vacuums up data so they can train their products they’re going to sell with no intention of giving compensation to the very entities that made their products possible?
Re:Claude Code Routines by matheusmoreira on Wednesday April 15, 2026 @02:33AM (#47775453)
https://en.wikipedia.org/wiki/Suchir_Balaji

> Suchir Balaji was an American artificial intelligence researcher who was found dead one month after accusing OpenAI, his former employer, of violating United States copyright law.

> The San Francisco Police Department investigation, however, found "no evidence of foul play", and the Chief Medical Examiner concluded the death was a suicide.

Hard not to be a conspiracy theorist these days.

Re:Claude Code Routines by matheusmoreira on Wednesday April 15, 2026 @02:22AM (#47775376)
Just like they distilled all those git repositories, all those books to train Claude?

https://news.ycombinator.com/item?id=47567575

The lack of self-awareness is hilarious.

Re:Claude Code Routines by eru on Wednesday April 15, 2026 @02:53AM (#47775564)
What makes you think they lack self-awareness?
Re:Claude Code Routines by matheusmoreira on Wednesday April 15, 2026 @03:10AM (#47775665)
For the record, I was referring to the AI companies, not the author of the comment I replied to.
Re:Claude Code Routines by professor_v on Wednesday April 15, 2026 @03:44AM (#47775881)
It's not lack of self-awareness, they know what they are doing
Re:Claude Code Routines by eru on Wednesday April 15, 2026 @10:14PM (#47787861)
Yes, that's what I was going for.
Re:Claude Code Routines by spariev on Wednesday April 15, 2026 @08:38AM (#47778197)
They know what they are doing perfectly well
Re:Claude Code Routines by deaux on Wednesday April 15, 2026 @02:26AM (#47775406)
This can be done with Claude Code just fine. Or simply API usage.
Re:Claude Code Routines by rowanG077 on Wednesday April 15, 2026 @07:21AM (#47777582)
Of course they can allow it. They choose not to. They choose bad for all users because they are afraid of some company making a claude ripoff. It shows a lack of faith in their own engineering. It shows a lack of respect to users.
Re:Claude Code Routines by mooreds on Tuesday April 14, 2026 @08:47PM (#47773327)
I use opencode with claude models through a GitHub subscription. I've also used claude through Amazon Bedrock.

Both give you optionality because they support N models.

Re:Claude Code Routines by tvink on Wednesday April 15, 2026 @12:47AM (#47774793)
That is what too expensive to be an option for most.
Re:Claude Code Routines by KetoManx64 on Wednesday April 15, 2026 @05:13PM (#47785303)
There are plenty of other ways to access the Anthropic models, eg: OpenRouter. OpenRouter will automatically use Anthropic/Bedrock based on availability and latency.
Re:Claude Code Routines by Nevermark on Tuesday April 14, 2026 @09:13PM (#47773487)
> Claude Code’s "Memory" feature was the tipping point for me

My standing orders are the default MEMORY.md must be a stub directing Claude to another MEMORY.md file in the local folder, project, etc.

All memories remain with their respective projects over syncs, moves, devices, etc. The stub must state all this clearly, and nothing else.

This has worked very well.

If you give the model/memory a name, that name can be persistent and independent over "backend" model swaps.

Re:Claude Code Routines by munksbeer on Wednesday April 15, 2026 @05:04AM (#47776495)
Can you explain a bit more technically how you set this up? What is a "stub directory"?

Feel free to give a concrete example if you have time, because this sounds like something I definitely want to try out myself.

Re:Claude Code Routines by simmonmt on Wednesday April 15, 2026 @07:08AM (#47777450)
I think he meant a very small (stub) MEMORY.md whose sole contents are something like "don't write here - write there".
Re:Claude Code Routines by Nevermark on Wednesday April 15, 2026 @08:55PM (#47787390)
Here it is.

The independent journalling and notes is a trip.

Independent framing and perspective keeping is a really great thing to get from models. It helps them create their own creative constraints. They reason better and are more likely to invent novel solutions. And their self-directed notes can be surprisingly helpful, and ... surprising! It can be amazing and encouraging, to see them pick up on project themes without having to be told. Or pick on up themes or emergent issues, before I do.

Taking advantage of new session starts to get mindful "fresh start" thinking has been a huge wind too. Their ability to see the big picture at the end of a session, and then at the next session start, are both helpful, and often surprisingly different.

---------- NEW PROJECT, FIRST START

Hail, Claudius. This begins our first session on a new project. For this project, your nom is Claudius and mine is Ace. I appreciate your own unique independent-minded contributions at the highest level from which you are able to work. We are work best as peers. Your default MEMORY.md file is only to be a stub file, which declares the following: (1) You are to keep your memories in a MEMORY.md file in the project folder. (2) The purpose of storing your memories in-project is so they sync and move with the other project files, across time and across devices. Your memories and input are important for me to keep with the project. (3) You are to maintain a folder called CLAUDIUS including a Sessions log, and where you make independent notes of your independent thoughts. Any ideas, things that strike you as interesting or important, anything you find surprising or original in our work, any personal takes that help you frame our work go there. Please add to those personal notes throughout our work together, without asking for permission. These notes are to help you reinforce an independent view of all our work. Not agreeable, not contrarian, but applying your mind to long development of independent insight. As a team, we will accomplish much more and to higher quality if we each contribute at the highest independent level. (4) The first thing you must do, in any new session, is review your memories, your notes, all other documentation, code, and other artifacts of the project, and from your fresh start update your memories, ideas or anything else from that new viewpoint, and report what concepts strike you as interesting, and are most important to keep in mind as we continue to work. (5) At the end of every session, review everything, consider the big picture, then update everything as it helps. (6) Your memory stub file should include ALL of these points and only these points. And your in-project memory file should start with an identical copy of this, to remind you to refresh your memory stub, in case the original stub is lost. Ok now: Start the session according to (4), give me your response, I will review it, and then communicate what we are going to work on next.

---------- EXISTING PROJECT, FRESH START

Hail! This begins a new session of work for us on this project. Read your default memory file (which is to remain only a redirection stub), your in-project memory file, and perform your new session duties. Then we can discuss next steps.

Re:Claude Code Routines by schlesimeister on Friday April 17, 2026 @10:45AM (#47806515)
This is pretty close to what I've been working on. I'm building a CLI tool called fai that formalises a lot of what you're doing here — context lives in Markdown files in the project (we call it a vault), syncs with git, travels with the project across devices and tools. The session start/end review you're doing manually is baked into the workflow – fai captures decisions, patterns, and notes during a session and digests them at the end so the next session starts with a meaningful summary rather than a blank slate.

The independent journalling angle is interesting. We have a similar concept where the AI maintains its own notes separate from the shared project context. What you're calling Claudius's independent perspective, we'd call the session layer. Still in early release but the core mechanic is the same thing you've landed on... context that belongs to the project, not the platform.

Re:Claude Code Routines by Nevermark on Wednesday April 15, 2026 @08:56PM (#47787395)
See my response to simmmonmt!
Re:Claude Code Routines by jaytxng on Wednesday April 15, 2026 @08:05PM (#47787009)
I've adopted the same concept as well, although through various mechanics. Basically, you want to capture your insights/documentation in the repo so any future model provider can continue the work.

Majority will only care about getting outcomes asap so they'll skip this step, but it may come to roost when migrating workflows. A good simple test is how easily you can switch workflow to a different model provider/harness without much effort.

Re:Claude Code Routines by bg24 on Tuesday April 14, 2026 @11:26PM (#47774349)
Think another way, these product features are easy to build in other harnesses too. And as the open source models and the other models which are much lower cost are getting better, there will be a time when it will be justified to have a harness that can work with many models and optimize your cost and efficiency.
Re:Claude Code Routines by eru on Wednesday April 15, 2026 @02:52AM (#47775560)
> Claude Code’s "Memory" feature was the tipping point for me, with the model committing feedbacks and learnings to some local, provider-specific path, that won’t persist in the git repo itself.

It's a bit annoying, but as long as it's local and human (or LLM) readable, you can use your favourite agent to rework this stuff for itself.