If you have trained a model, you want to deploy it to SageMaker, and your first instinct is to start screaming, pleaseπ and keep reading.
Today, I am launching a course: How to deploy an ML model to SageMaker with a custom Docker container
π Get it here: https://t.co/ENPVDRwgkx
The full story covers: disasters, pivots, technical architecture, and what actually works when vibe-coding with LLMs.
Tech: Next.js 15 β’ React 19 β’ Prisma β’ Replicate β’ AWS Bedrock
#AI#LLMs#VibeCoding#BuildInPublic
I finally shipped Visual Neurons: a personal AI studio for image/video generation.
9 models. One interface. Zero lines of code written by me.
Claude Sonnet 4.5 + Cursor built it.
π Full story: https://t.co/4qBGIuaP6U
π₯ Demo: https://t.co/WUwYPEvhhm
Here's what it took π§΅
When I thought I was done with outpainting, I started stumbling on frontend timeouts. The StabilityAI API call is successful though (I see it in πΈ). Lambda logs confirm too.
Seems AppSync plays tricks on me. Here's how ChatGPT puts it π (and yes, I have to move to async)
What happens in that scenario?
Stability finishes the job in, say, 40 seconds, returns HTTP 200, and you get billed.
However, AppSync has already cut off your resolver at 30 seconds, so your front end sees a βtimeoutβ or βnetwork error,β rather than the final 200 result.
```
```
If you are calling the Stability outpainting API from an AWS Lambda resolver (via AppSync), remember that:
AppSync imposes a 30-s timeout for all resolver calls. Even though your Lambda function can be configured for a 120-s timeout, AppSync itself will cut off at 30 seconds.
Integrated StabilityAI image generation.
After the 20-commit-3-days refactor it was a breeze π
It boiled down to implementing the `generateImage` func inside the `stabilityProvider.ts` and the dispatcher propagates to Lambda and the frontend.
https://t.co/FNHJkDVogE
@robmarkcole@AnthropicAI `o3-mini-high` absolutely kills it. Claude 3.7 is very very good but it requires too much fiddling with the context. Super annoying.
Gemini image understanding is top notch (together with GPT4 tbh). Never really given it a proper shot as a coding assistant
Not sure what they are doing at @AnthropicAI, but Claude is basically unusable for any reasonably long context.
ChatGPT handles the same queries without any issues.