nokode
AI
llm experiment
SHOW HN2025
436points
324comments
#102of 3,837 in 2025
Top 3%of 2025 by points
How HN took it
MixedNo clear lean
22 positive, 42 neutral or asking, 4 mixed, 60 critical, out of 128 comments about the project. Thread score -0.26.
Idea: 19 for, 34 againstPerformance: 0 for, 8 againstDesign: 0 for, 6 againstPrivacy: 0 for, 6 againstExecution: 0 for, 5 against
The thread, comment by comment
Each row is a top-level comment and its replies, in HN's order. Select a cell to open that comment on HN.
positive neutral or mixed critical about another commenter or something else the maker
What HN said
What people liked
Creative, thought-provoking experiment
From 3 comments
This is amazing. It very creatively emphasizes how our definition of "boilerplate code" will shift over time. Another layer of abstraction would be running N of these, sandboxed,…
finnborge on HNThis demo is pretty great, I love it! And it reminded me a little about NeuralOS, which appeared here a couple months ago [1]. NeuralOS is different though as they decided to…
cookiengineer on HNAmazing. This is the Internet moment of AI. The Internet took something that used to be slow, cumbersome, expensive and made it fast, efficient, cheap. Now we are doing it again.
ares623 on HN
Works surprisingly well despite slowness
From 1 comment
"It works. That's annoying." Indeed! Would be cooler if support for local llms was added. Currently only has support for anthropic and openai.…
attogram on HN
Objections
Too slow and expensive to be practical
From 3 comments
It's orders of magnitude cheaper to serve requests with conventional methods than directly with LLM. My back-of-envelope calculation says, optimistically, it takes more than 100…
ychen306 on HNCalculation is $0.05/request is valid only as far as AI companies continue to burn money as they are in grab the market phase. Once the dust settles prices will go up. Even if…
ozim on HNWith no routes, no controllers, no business logic, how can the capability exist? These are the core components of a web app and require extensive coding. I know we might…
pyeri on HN
Non-deterministic behavior is bad for users and APIs
From 2 comments
The question posed sounds like "why should we have deterministic behavior if we can have non-deterministic behavior instead?" Am I wrong to think that the answer is obvious? I…
sunaurus on HNI can't wait to build against an API whose outputs can radically change by the second! Usually I have to wait for the company running the API to push breaking changes without…
julianlam on HN
Serious security and prompt injection risks
From 4 comments
Generating code will always be more performant and reliable than this. Just consider the security implications of this design...
brokensegue on HNExactly. It even includes built-in prompt injection as a "feedback form".
samrolken on HNYou can build this today exactly as efficiently as you can when inference is 1000x faster, because the only things you can build with this is things that absolutely don't matter.…
DanHulton on HNThe fatal problem with LLM-as-runtime-club isn’t performance. It’s ops (especially security). When the god rectangle fails, there is literally nobody on earth who can even…
hyko on HN
Requests
Support local LLMs
From 1 comment
"It works. That's annoying." Indeed! Would be cooler if support for local llms was added. Currently only has support for anthropic and openai.…
attogram on HN
Cache or convert generated code for speed and consistency
From 3 comments
If you added a few more tools that let the LLM modify code files that would directly serve requests, that would significantly speed up future responses and also ensure…
Finbarr on HNThis is incredibly interesting. Now what if you ask it to optimize itself? Instead of just: ``` prompt: `Handle this HTTP request: ${method} ${path}`, ``` Append some simple…
crazygringo on HNWouldn't be the trick to let AI code the app on first requests and then let it run the code instead of have it always generate everything? This should combine the best of both…
thibran on HN
Questions
Why use a small Haiku model
From 1 comment
> ANTHROPIC_MODEL=claude-3-haiku-20240307 Why?
martini333 on HN
How can the capability exist without routes or business logic
From 1 comment
With no routes, no controllers, no business logic, how can the capability exist? These are the core components of a web app and require extensive coding. I know we might…
pyeri on HN
Alternatives named
Claude Imagine
From 1 comment
This reminds me of the recent Claude Imagine, which passed quietly through most people's radars, but let you create web interfaces of any kind on the fly. There was no JS code…
taylorlunt on HN
autoapp
From 1 comment
Wrote a similar PoC here: https://github.com/s1liconcow/autoapp Some ideas - use a slower 'design' model at startup to generate the initial app theme and DB schema and a 'fast'…
siliconc0w on HN
NeuralOS
From 1 comment
This demo is pretty great, I love it! And it reminded me a little about NeuralOS, which appeared here a couple months ago [1]. NeuralOS is different though as they decided to…
cookiengineer on HN