marjipan200

Meta question, but is the title of this article disappearing for others on HN? I'm unable to click. It seems all huawei.com links on this site have the same issue. Is it just me?

Reminds me of Obsidian's stance on AI - leave it to the plugins. I think other apps can learn from what they are doing with plugin safety transparency in their new Community site - no silver bullets but Obsidian is certainly making it easier for people to make informed decisions on user-built software. Hard to argue with the "no-AI by default, opt-in consciously and frictionlessly, pay your own bill, and we aren't responsible for your data privacy" model, especially for apps managed by small teams

the other Keet has been around 4 years with millions of downloads. Might make distinguishing your app in searches challenging

Announcing your flagging of the flagging is against the guidelines. Not flagged

thanks to LLMs we can now ask books questions :)

Excellent overview to give footing to anyone hovering at the higher levels of abstraction like myself. The interactive diagrams helped make some concepts click that were trickier to grasp from previous readings

The mind of the neuro-materialist is a radio so impressed with its own receiver that it's convinced it is the broadcasting tower

interesting, but curious how it would handle non-latin script input such as Japanese. seems like dialect.py uses regex for latin script extraction only

until Node is compromised

Incident tracking:

https://github.com/axios/axios/issues/10604

GitHub issue for tracking

https://github.com/axios/axios/issues/10604

obsidian handles a lot of useful little things out of the box, like updating links when you move files/attachments

another big win for the CLI is access to dynamic note database queries via Obsidian Bases. major leverage for agents

I think you still can't... but probably on the roadmap since that will be killer

https://x.com/CoenJacobs/status/2021252503711461474

For those who miss SO, check out Stack Overflow Simulator: A functional museum for developers to relive the good ol' days of asking innocent questions and being told to "RTFM"

https://sosimulator.xyz/

you aren't missing much ¯\_(ツ)_/¯

here you go, helping with exposure therapy

https://gist.github.com/clairefro/1cf81f5d7125e124975f4aba22...

Love the Reverse Surprise Notation on this calculator

Stack Overflow simulator is a functional museum of Stack Overflow... using AI

https://sosimulator.xyz

this idea is interesting, but I can't seem to see any image on your GitHub profile showing the output. I'm on my phone - does it only work on desktop?

Love this! If you're into representing time with simple markdown, check out the Chronos Timeline plugin for Obsidian too

https://obsidian.md/plugins?search=chronos+timeline

See demos here

https://x.com/clairefroe/status/1862536872011891150

Which local platform/model are you using? Would love to follow your project.

I built an AI journalling assistant plugin for Obsidian that has the option for 100% local and private use via Ollama and the model of your choice.

https://github.com/clairefro/obsidian-chat-cbt-plugin

Not a replacement for human interaction, but finding it actually really helpful for getting out of negative thinking spirals in between therapy sessions. Plus it has endless patience :P

I feel LLMs work well as objective sounding boards. Trying to build something similar to the OP for this reason!

Thanks - I'll try to reproduce

Strange - are you seeing the error on obsidian? Happy to investigate if you open an issue

I think they raised an important point and appreciate the call out to make the aim clearer

That's an interesting point, but I'll reiterate this tool is explicitly described as not being a replacement for therapy.

> I think LLMs have a lot of therapeutic potential, but I am worried about how easily they can cause harm in this area

At the end of the day, no one can be 100% responsible for someone else. The agency lies with the patient. Even human therapists come with their own beliefs that seep into their practice, which while well-intentioned may not align with the goals of the patient. It is up to the patient to understand their own values and decide whether therapy with a given therapist/therapy method is effective in improving their life.

In your example above, I'm not sure the harm risk is so high. In fact, with your example of exposure, since LLMs tend to regurgitate the same flavor of response over and over, they might actually deliver the same effect of desensitization.

I fall into the OCD thinking category, and found LLMs helpful precisely for the fact they have endless patience (whereas I feel the need to hold back after a certain number of times talking to friends/therapist about the same issue)

Best one can do is be upfront with the aims/design of the tool, and let people decide

Noted. I can update the README to emphasize that it is a journaling tool.

edit - done!

I understand that line of thought, but feel differently. Maybe this could be worded more clearly, but it's stated in the REAMDE that ChatCBT is not intended to be a replacement for professional therapy or human interaction, rather a supplement. ChatCBT is just a journaling tool, similar to the CBT worksheets therapists give patients for their emotional toolkits, but more interactive to help you get out of your head a bit.

Frankly, not everyone can afford therapy - monetarily, or in terms of the emotional availability of the friends and family around them. I agree with you human interaction is important. But journaling is also a form of therapy.

I don't intend to monetize this, and would prefer it be a free tool that helps people to not need it anymore.

or maybe the load of audio inbound/outbound from opening voice to all users

I'm sure local GUI clients will be available soon for the average user to boot up local LLM servers