Often, when I use generative AI to produce videos, the results are close to what I envision but rarely capture my imagination exactly. Prompting the AI to fix specific details can be a cumbersome and time-consuming process. To address this, I'm developing solutions that make the creative workflow more intuitive. So far, I’ve built an app that allows users to provide visual clues as guides, along with a 3D environment where the camera can be freely manipulated within the generated scene.
The community is moving fast though. Now higgsfield allows using arrows and pointers to edit the video but so far, no one is doing a good camera control visually.
I was scrolling and everything on the hardware looked great (although I was looking for how the tech is different from e-ink, not how better its properties are).
Then I reached "Introducing Sol:OS" and stopped right there. Didn't look further and closed the tab. I'm skeptical when it comes to custom OS. Not a lot of startups can handle a hardware+software company. Hardware is hard enough. Software is second class citizen and doesn't get regular updates after a few years.
Not comparing here, but I just remembered that the first paper on graphene was rejected (twice) and one of the reviewers said something like 'this paper does not represent a scientific advance.'
> I don't need to trade that for need to spend time to know what and more importantly why something is where it is.
I had two options: 1. Learn everything first and then start prototyping. 2. Start prototyping and learn along the way. I chose the latter. But instead of searching stackoverflow and putting the pieces together, I used GPT and learned from the generated outputs in the context of my own problem.
It may not save a lot of time in larger projects because as you said, one should ultimately learn the "what and why", but it definitely provides a more pleasing experience. And I guess the time-saving part becomes more relevant with better tooling, like the suggestion I had.
For smaller pieces, you are right. But as a BE engineer, I was prototyping a concept and I didn't know much about Typescript+React+React-Router-Dom+React-Hooks-Form, etc etc. So I listed the libraries, a few lines of boilerplate and API definitions that RTK toolkit generated for me. Then asked GPT to generate the full page. It was much faster than I could "code it myself".
And that's why it is a "pain point". These all can be done automatically.
In my experience working with GPT4, if I give enough context on types, other functions definitions and the libraries I use, I get very accurate results. But it is a tedious task to copy paste from multiple places (type definitions, function definitions, packages, etc.).
In addition to the selected lines, does Continue support getting related definitions from the language server and inject them in the prompt? That would be huge.
The cost aside, I'm wondering how fly or heroku support their customers when they grow to microservices ecosystems.
The problem shifts from deploying easily to deploying reliably meaning one release of a service should not break the other services. Other problems appear too, like service discovery, peer authentication, gateways, test and staging environments where there are downstream dependencies, etc.
Are customers supposed to leave when they grow to this level? Or are there solutions for these?
The difficult part for me is maintaining the docs over time. I can generate 80% of what theneo does automatically in swagger style. The remaining 20% (manual editing, what your platform offers) is the missing part with my current solution, yet I cannot see how theneo solves updating most of the doc and placing back the manual edits.
Klue | Senior Backend & Senior DevOps & Senior Data Engineers | Remote (US & Canada), HQ in Vancouver | Full-time | klue.com/jobs
From a technical standpoint, Klue's mission is to descale data to the human level so people can process the information. Currently, the focus is on sales enablement but tomorrow it is all teams enablement. Klue raised Series-A in September 2020 and is in the growth state.
Here are some of the challenges we are currently working on as the backend team:
* Ingesting thousands of news articles, web pages, marketing and sales data points per day. The challenge is dealing with unstructured data,indexing them for a long period of time and making them searchable and ready for different analyzes.
* Expanding our Rails REST API and offering public APIs to enable integrations.
* Architect infrastructure for a scalable, resilient and robust service. We are migrating from a monolith architecture to microservices.
Our current tech stack:
* Python (Flask), Ruby (Rails), PostgreSQL, Elasticsearch, Redis, GCP, AWS, Tensorflow, Keras, Docker, Kubernetes.
* We are open to use different tools and languages if they reduce costs associated with solving problems!
From the blog "Just like llvm facilitated the rise of hundreds of new computer languages, I forsee a similar rise for debugging and debuggers in the coming years."
But the author provides no evidence to support the claim. Why would the status quo change?
Cool, I'll check them out. If it is "one of the more efficient and effective ways to implement a compiler", are we aware of any non-functional languages that use this style in their compilers? Asking since most compilers use LLVM and LLVM is in SSA form.
Can a Decent Compiler convert direct style to CPS under the hood so to have the best of both worlds? Let's say we return Result<Integer> for the lookup and then pattern match for error or result. A compiler would be able to create two callbacks based on the match arms and change the lookup interface to accept them.
I like it and would use it. For paying customers, they probably come from places like github marketplace. I think you should work on getting it out of the door.
The community is moving fast though. Now higgsfield allows using arrows and pointers to edit the video but so far, no one is doing a good camera control visually.