Hacker Newsnew | past | comments | ask | show | jobs | submit | mariocesar's commentslogin

I'm was closing a day of work and it stopped in the middle of a long plan, I started codex and tell it: "I was in the middle of work with Claude could you read the plan and the session "x" in ~/.claude and continue the work" it just completed everything :D

I’m working on a project that makes switching between coding harnesses essentially unnoticeable. It’s particularly useful when I run out of credits on any given day

The entire platform is skill driven, and based on the premise that state is your local file system. That makes switching harnesses so easy

It’s all open source and has plenty of other features, including inter agent communication, telegram client and much more in the pipeline

https://www.woltspace.com/


Not sure what the problem with switching is? When I run out of my kimi session, I just switch model and tell deepseek to continue. Yes I eat the initial cache miss but that's it, no fancy harness required.

You are talking about switching between models, the parent comment was about switching between harnesses. Not the same thing.

I added a skill to OpenCode that tells it how to read old session logs when asked to. Seems like this would be pretty easy to add to most any harness.

I think having a codebase that can use any harness is the optimal setup. I often switch between harnesses and models all the time at work. We have our state/spec stored in git, so we can pack it up on friday and start fresh on monday. Or more commonly, using gemini/opus to create rich specifications and using Luna to implement them. Then switching again for reviews etc.

No project needed man. There's also a whole ycombinator company for the same thing, skillsync, also useless. These things are either out of the box or they are 2 prompts away.

Related, have found this handoff skill invaluable for moving tasks between harnesses: https://gist.github.com/ammario/cd57a1d7f6c911e079378c540b38...

My handoff is a handoff_latest.md that points to the latest handoff_datetime.md in a handoff folder.

I did this with DeepSeek a couple of days ago.

yeah same that's my preferred flow now -- sill use Claude and OpenAI a bit, though recent nerfs to subs has really made using codex much harder.

DS 4.1 flash is my main powerhouse and Opus/Astra my auditors (when they're not out of tokens) otherwise K3 or DS4 pro


I started using Pi with Astra on a whim after really enjoying Astra and reading somewhere that you get close to identical results as with the codex harness but for a significant hunk less token usage.

Coming from mostly using Claude models, the terse factual statements coming from Astra via the Pi harness are a breath of fresh air over having to wade through the flowery verbose nonsense that Claude constantly outputs


I recently had Astra review a fairly detailed design doc I have for an audio VST fork, that I originally wrote with Opus and/or Fable a few months ago. The doc reaches deep into signal flow and module topology while lifting most of the DSP code from other open-source projects. I had it review for feasibility and architectural soundness.

Astra found a number of flaws that would have come up during implementation and we worked through them. But then I had Fable 5.1 review that document and it found a number of issues with Astra's changes, the least of which had was that Astra duplicated a lot of technical notions that it added rather than using references to an authoritative section. It also flagged some of Astra's designs as technically impossible, pointing out why and I'm actually in the process of digesting its feedback and updating the design spec. (I hand-review each point and we work through a solution together -- I don't trust either model to come up with something that follows my vision on their own)

I'm not promoting one or the other, I just found it interesting how this sort of adversarial review found pretty significant flaws in the other model's work. I am curious as to whether this process will eventually converge on a document that both agree on or if the models are going to perpetually nitpick each other.

I haven't actually started implementation yet, so maybe one or the other is full of shit. Just trying to come up with an architecturally sound design for something I want to write, when I lack the DSP knowledge to be able to write it myself. But the intent is to pass an agent the design doc and list of milestones and let it handle implementation.


In my experience, rather than converging, you end up with a minced up concept. You have to know when to stop the loop. I filter the feedback too, and need to challenge some of the challenges as these models tend to be very conservative. I believe this is intentional, to control AI psychosis, which is indeed quite easy to get. My 2c. If you don’t have good control of what you’re working with you are either searching blind or end up with something basic.

Agreed, I believe strongly that human-in-the-loop is the way to go. LLMs are fantastic thought partners but ask it to critique something and it will go absolutely nuts. For Claude Code's /code-review command the highest I will set it is 'medium', otherwise it will produce so much feedback that you'd never get anything done.

Ignorant questions for you and anyone else using DS:

1. who hosts the inference

2. which harness are you using with it, still CC?


So everyone has their preferred way of doing it.

1. I go direct to source, i.e. DS platform, I find it cheaper than paying the openrouter tax -- I also switch it up a bit

2. I built a local LLM router, that I update with new profiles that have my preferred provider of the week (lowest token costs/speed) with fallbacks, like mimo --> DS4 etc.. if there is overloading,

3. I use 3 diff harnesses, CC/Codex + Opencode -- they all talk to each other through a custom rig system that routes messages between llms using a Rust backed structured JSON system

Not saying this is the best, it's just what I like and works for me^.

I can flow quite naturally between Opus/Astra/K3/GLM/MiMo/DS/etc.. this way and often do...more so these days with subs no longer great as they used to be.


doesn't DS train on your prompts when you go through their platform?

Whatever openrouter puts me on, running in pi (though I do all comms over my xmpp wrapper).

I'm using DeepSeek's own API with opencode. The pricing is absurdly good.

Deepseek harness is great!

Both Cursor and Grok build ask if you want to resume a session from another harness. Quite brilliant

I don’t understand your point or why people are upvoting this. I’ve done this between many different models. Did you just discover that a frontier model can read context? I genuinely don’t get your point. I’ve had to have Claude agents pick up codex’s context after it hits one of its “cannot connect” issues way more often than the other way around.

No point, I just shared something I did

how do you get the "x" session name?

You can even tell the new harness to go find your latest session in the other harness and it works perfectly. You don't even need the name!

In CC, "/exit" will tell you how to --resume <session-id> upon exit. This will eat zero tokens, and it actually does not require an active internet connection.

`claude --resume` will list your sessions, you can copy the title. Codex may just list and grep the sessions files in ~/.claude and filter the one with the name.

I also have the habit of naming my sessions with `/rename`


/resume in claude code.

I have an 'ask' alias in my shell that just uses Haiku. I use it daily for pretty much everything

For more long work, I now use Fable to create a PLAN.md. I tell it to make a plan that will be executed by other models, and most of the time it ends up choosing Opus or Sonnet.

I didn't start doing this recently. Before that, I would just use the top model for everything. Splitting the work across different models depending on the task has helped a lot. They run faster, and I usually get much better results


i can not believe you really use Haiku?

To ask for web search, simple commands and research, or passing logs to analyze it's more than enough

Here is the script https://github.com/mariocesar/dotfiles/blob/main/common/.loc...


this is a really neat idea. thanks for sharing!

Great work, and thanks for sharing the transcript! Just skimming through the chats, I've already learned a lot. Would be so awesome to have this for any region/city, but that is a data problem to solve.

Congrats again!


This was posted on HN a while ago and I started using it then. I've accumulated quite a bit of data and have used both export and import. That's turned out to be the most useful feature for me

I've used other trackers, ones focused on CBT. My only suggestion is to allow text notes in each entry, so I can track emotional states or recurring thoughts


You can add a note with each habit completion, by pressing a day on the habit detail screen ;)


Cool, if we could by hour I can replace my CBT tracker !


I answered this in another thread, if you're already running a large GitHub organization, GitLab is the closest alternative in terms of features

A big plus is that it also has an open-source Community Edition that you can self-host


There are also many consultancies able to provide professional support with running it in your org, including migrations.


GitLab is probably the most reasonable alternative. I migrated and it took me some weeks to adapt to the new CI, but for my use case it's basically equivalent in features.

I started with the cloud version, then moved to self-hosted because it wasn't a big effort for our team. We also reduced our monthly invoice by about 50% after the move.


The product is being launched before the value is clear.

We've seen similar waves with new technologies before: overexposing the pros, dismissing the cons, hyper-optimism, and people using a lot of jargon without saying much of substance. The difference this time is the scale of the impact and the volume around it.


> The product is being launched before the value is clear.

May I fix that for you?

The product is being launched before the value is there.


Location: Santa Cruz, Bolivia (UTC-4, EST)

Remote: Yes

Willing to relocate: Yes

Technologies: Python, Django, FastAPI, Flask, Node/NestJS, TypeScript, React/Svelte/Vue, Next.js, Postgres, Redis, Docker, Kubernetes, AWS (Lambda/ECS/RDS/S3), Terraform, Celery/RabbitMQ/Airflow, GraphQL, ETL, Zapier (Platform/CLI), OpenAI/Claude integrations

Résumé/CV: https://www.linkedin.com/in/mariocesar/ (happy to send PDF)

Email: mariocesarsenoranis @ gmail.com

Senior full-stack engineer & tech lead, 10+ yrs, Python/Django-first. I ship MVPs that reach production and stabilize/modernize legacy systems without breaking what works. Comfortable across backend, frontend, and infra.

Strong on SaaS, integrations and data flows: Zapier apps (Platform/CLI), ERPs, billing, CRMs, webhooks, ETL — plus LLM integrations (OpenAI/Claude). Years spent making systems talk to each other reliably.

Ex-Zapier (integrations), ex-Tesorio. Experience across SaaS, fintech, and e-commerce.

Links: https://github.com/mariocesar https://mariocesar.xyz/ https://www.linkedin.com/in/mariocesar/


Location: Santa Cruz, Bolivia (UTC-4, EST)

Remote: Yes

Willing to relocate: Yes

Technologies: Python, Django, FastAPI, Flask, Node/NestJS, TypeScript, React/Svelte/Vue, Next.js, Postgres, Redis, Docker, Kubernetes, AWS (Lambda/ECS/RDS/S3), Terraform, Celery/RabbitMQ/Airflow, GraphQL, ETL, Zapier (Platform/CLI), OpenAI/Claude integrations

Résumé/CV: https://www.linkedin.com/in/mariocesar/ (happy to send PDF)

Email: mariocesarsenoranis @ gmail.com

Senior full-stack engineer & tech lead, 10+ yrs, Python/Django-first. I ship MVPs that reach production and stabilize/modernize legacy systems without breaking what works. Comfortable across backend, frontend, and infra.

Strong on SaaS, integrations and data flows: Zapier apps (Platform/CLI), ERPs, billing, CRMs, webhooks, ETL — plus LLM integrations (OpenAI/Claude). Years spent making systems talk to each other reliably.

Ex-Zapier (integrations), ex-Tesorio. Experience across SaaS, fintech, and e-commerce.

Links: https://github.com/mariocesar https://mariocesar.xyz/ https://www.linkedin.com/in/mariocesar/


I've been looking for almost two years, though not very actively at first. I had to focus on my health, and job hunting took more energy than I had

Two months ago, a local company reached out on LinkedIn. They help with the search. I'm not good at selling myself, so I gave it a shot.

They fixed my CV and LinkedIn, and started finding roles for me. Since then, I've had more interviews.

The market feels over-automated now. Too much noise, too many filters, too much AI. It's exhausting.


Hah, Im in similar situation, but I am network/IT admin. I think its worse, because who need networking guy? You just plug it in and it works, right? ;)


do you mind sharing the name of the company? I could use some help in the search too. my email is on my profile if you prefer that


Guidelines | FAQ | Lists | API | Security | Legal | Apply to YC | Contact

Search: