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

Really interesting project! I tried it last week and ran into same errors and today I tried it again and it worked.

I'm curious how the Clink desktop app connects to the web app. Is it sending some kind of oauth token so you can use call Claude Code, etc, on behalf of the user?

FWIW, I created an open-source project in this space https://github.com/dyad-sh/dyad/ and it's great to see people trying different approaches :)


Oh I really like your product! you're right about how it works. the desktop app sends oauth tokens to connect to the cloud infrastructure. dyad looks really cool, love the local-first approach. it's exciting to see so many different takes on this space right now. what are you focusing on with dyad these days?


thanks! we recently added MCP support so we're figuring out how to make it easier to find & add the right MCP tools for your use case :)



Thank you!


we have an extensive system prompt to instruct the Supabase to follow RLS best practices: https://github.com/dyad-sh/dyad/blob/de2cc2b48f2c8bfa401608c...

What you're describing as the fail-open behavior is from the Supabase platform (and not specific to any app builders): https://supabase.com/docs/guides/database/postgres/row-level...


we have features like manual context management https://www.dyad.sh/docs/guides/large-apps#manual-context-ma... which lets you select files to use in your context window


Hey, could the tool do this itself? Like using code embeddings?

https://www.trynia.ai/ seems to be doing sometihing similar.


very interesting - when we ship MCP support you should be able to use nia!


How about local support? First draft is simple enough to implement: chunk => embed => store. And then one simple lookup function.

Complexity would arise once we start to go into AST's and graph traversals.


Thanks! Check out our Prompt Library feature: this way you can create reusable prompts across your apps: https://www.dyad.sh/docs/releases/0.18.0


I'm working on adding MCP support to Dyad soon! What's your favorite MCP servers? (trying to curate a list of recommended MCPs)


There is a project I’ve been playing with called claude-code-templates that keeps curated lists of things Claude code can use, one of which is MCP servers: https://github.com/davila7/claude-code-templates


neat! thanks for sharing


Context7 or Deepwiki are a must-have. They are also relatively secure, unless those sources of information become compromised in some way.


I love how Deepseek just casually drops new updates (that deliver big improvements) without fanfare.


Honest question, how do you know this is a big improvement? Are there any benchmarks anywhere?


There will be a video from FireShip if its a big one. /s


Ah FireShip, I forgot that channel existed at all. I asked YouTube to not recommend that channel after every vaguely AI-related news was "BIG NEWS!!!", the videos were also thin on actual content, and there were repeated factual errors over multiple videos too. At that point, the only thing it's good for is to make yourself (falsely) feel like you're keeping up.


Fireship consistently makes some of the most entertaining tech content out there


Hey if you enjoy it, go for it. I used to like it a couple of years ago too, but I found that more and more lately, it was neither entertaining nor reliably informative. The jokes/memes were lazy and recycled a lot, the tech content was often poorly researched, and it started feeling like content produced for the sake of having content.


Much more preferred to what OpenAI always did and Anthropic recently started doing. Just write some complicated narrative about how scary this new model is and how it tried to escape and deceive and hack the mainframe while telling the alignment operators bed time stories.


Really? I missed this. The new hype trick is implying the new LLM releases are almost AGI? Love it.


Anthropic "warned" Claude 4 is so smart that it will try to use the terminal (if using Claude Code) or any other tools available (depending on where you're invoking it from) to contact local authorities if you're doing something very immoral.


I like it too, but some benchmark numbers would be nice at least.


I think they did make an announcement on WeChat.


On the day Nvidia report earnings too. Pretty sure it's just a coincidence, bro.


Yeah the timing seems strange. Considering how much money will move hands based on those results this might be some kind of play to manipulate the market at least a bit.


I believe that they are funded by a hedge fund. So, there are no coincidences here.


Is releasing a better product really "market manipulation"? It seems to me like regular, good competition.


It's "manipulating the market" only when your geopolitical adversary brings the competition.


How does releasing it today affect the market compared to releasing it last week?


Hard to say exactly how it will affect the market, but IIRC when deepseek was first released Nvidia stock took a big hit as people realized that you could develop high performing LLMs without access to Nvidia hardware.


I thought the reaction was more so that you can train SOTA models without an extremely large quantity of hyper-expensive GPU clusters?

But I would say that the reaction was probably vastly overblown as what Deepseek really showed was there are much more efficient ways of doing things (which can also be applied with even larger clusters).

If this checkpoint is trained using non-Nvidia GPUs that would definitely be a much bigger situation but it doesn't seem like there has been any associated announcements.


Plans take time to adjust; I imagine a big part of the impact was companies realizing that they need to buy/rent much less expensive GPU compute to realize the plans they've already committed to for the next couple years. Being able to spend less to get the same results is an immediate win; expanding the plan to make use of suddenly available surplus money/compute takes some time.

And then part of the impact was just "woah, if some noname team from China can casually leapfrog major western players on a tiny budget and kill one of their moats in the same move, what other surprises like this are possible?". The event definitely invalidated a lot of assumptions investors had about what is or isn't possible near-term; the stock market reacted to suddenly increased uncertainty.


Except that, all Deepseek models so far have been trained on Nvidia hardware. For Deepseek v3, they literally mention that they used 2,048 NVIDIA H800 GPUs right in the abstract: https://arxiv.org/html/2505.09343v1


Actually, the "narrative" crashed Nvidia for no reason.

Not only DeepSeek uses a lot of Nvidia hardware for the training.

But even more so, by releasing an open weight frontier model, people around the world need more Nvidia chips than ever for inference.


I know of enterprises in APAC now spending millions of dollars on Huawei GPUs, while they might not be as efficient, they are seen as geopolitically more stable (especially given the region).

DeepSeek helped "prove" to a lot of execs that "Good" is "Good enough" and that there are viable alternatives with less perceived risk of supply chain disruption - even if facts differ may from this narrative.


Yes, I know them too, I live there!

The hardware is great, CANN is not CUDA yet.


someone has not heard about huawei GPU


Plenty of manipulation to go around..

"Tech Chip software stocks sink on report Trump ordered halt to China sales" - https://www.cnbc.com/2025/05/28/chip-software-trump-china.ht...


What big improvements?


Anyone got benchmarks?


I recently built an Electron app (http://dyad.sh/) and I looked at other options like Tauri, but Electron has such a mature ecosystem (e.g. https://www.electronforge.io/) that I was able to ship a cross-platform app in a couple weeks (Mac+Windows) and then adding Linux support was pretty trivial.

The only downside from my point of view is the large installer size for Electron apps, but it hasn't been a big issue for our users (because they will need to download quite a bit of other stuff like npm packages to actually build apps with dyad)


This was my experience as well. We also looked at Tauri but we ultimately decided on Electron due to its prevalence and us not wanting to fight the tide.


I tried sending an email to support@relace.ai (which was linked in the doc) and got:

Your message wasn't delivered to support@relace.ai because the address couldn't be found, or is unable to receive mail.

btw, I'm interested in trying out relace for my AI app generator tool: http://dyad.sh/


thank you! agree there's still rough edges, making lots of improvements each week to make it better :)


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

Search: