Readit NewsIt helps me a lot when I feel lost. It's often wrong in the calculations, but it's cool to have a study buddy that doesn't judge you.
If I get blocked with a problem I can't solve, I ask for assistance with my approach.
I enjoy asking ChatGPT about the context behind all that math theory. It's nice to elaborate on that as most of the math books are very lean and provide no applied context.
I'm trying to think of the use case where Markdown in VIM is not enough, but LibreOffice is too much. For what it's worth Bash is my file manager and I practically live in the CLI. I do write some technical documentation to go with my code, in Markdown. I recently wrote a long report in LibreOffice for a medical malpractice suite - I made extensive use of headings, paragraphs, quotes, tables, and bold text. My work templates have page headers and footers with page numbering, sparse embedded graphics, tables, a table of contents, and sometimes code snippets with syntax highlighting.
Additionally, all my document types use RTL text, which WordGrinder does not support. So I am more interested in the general feasibility of such an app, than in actually trying to replace LibreOffice with WordGrinder (at least until RTL support is added).
That works pretty good with markdown files hosted on github pages as I don't have to move out of the CLI when pushing them online.
However, the use case that this workflow doesn't cover is when I write something that I'd like to send for a proofread to a friend of mine, who's an editor. He really loves his Word files.
As I'm a noob, I asked then ChatGPT to help me with a bash script that converts that .md file into a .doc file using pandoc. That worked pretty well.
My thought was if it couldn't be possible to use something like pandoc for converting an .md file into a templated doc with headers, footers, page numbering, even toc?
That wouldn't solve 100% of the use cases, but still could be pretty good.
However, I make a simple bullet task list and work on it. Tasks are not necessarily related to coding. It could be a task related to image editing. Initially, I was feeling very bad if I can't finish a task within the time I've set for it.
Now I don't feel bad if I can't finish that task on time. I perceive it as a micro-iteration of the task. The trick is to iterate further, until the task is done.
While rushing to do a task within a specific timeframe, might be productive in the short-term, I don't see it feasible if you push yourself all the time doing it. I imagine it might reflect on the quality of your work and lead to a self-induced burnout.
Shipping for the sake of it, in my opinion, might create some false perception of work being done. In my experience, employers tend to reward that behavior.
So maybe the question here would be: why are you shipping in first place? To show off, to boost dopamine through gamifying yourself, or to deliver a piece of work you'll be proud of before going to bed.
For example:
Imagine a simple Amazon price tracker I have in my menu bar. I pick 5 products that I want to have their price tracked. I want that info to be exposed to Siri too. And then I can simply ask Siri a tricky question: "Hey Siri, check Amazon tracker app, and tell me if it's a good moment to buy that coffee machine." I'd even expect Siri to get me that data from my app and be able to send it over my email. It doesn't sound like rocket science.
In the end of the day, the average user doesn't like writing with a chatbot. The average user doesn't really like reading (as it could be overwhelming). But the average user could potentially like an assistant that offloads some basic tasks that are not mission critical.
By mission critical I mean asking the next best AI assistant to buy you a plane ticket.
It's also somehow good to find pdf files with "filetype:pdf".
As already mentioned, the occasional currency and time conversions are also pretty nice. I admit I use their calculator too sometimes.
Essentially, Google advanced search operators have been a pretty powerful feature that I've been using since I learned about it in 2011.
Other than that, I agree the generic search result are a bloody mess.
For a lot of other searches, GPT 4 helps a lot.
Reading that someone else, somewhere else, has a similar idea, has made my day. Cheers.
Remote: Yes
Willing to relocate: Possibly
LinkedIn: https://linkedin.com/in/angel-gpetrov
About: Strong generalist, working for the last 9 years as a business analyst and product manager. Spent 6+ years in card payments (both POS and eCommerce). I worked mostly with startups, some of them managed to scale up.
Depending on the project, product and/or team I like to:
- Facilitate ideation and discovery workshops on Figma, Miro and recently Freeform
- Build hypotheses based on market research, customer feedback, analytics
- Facilitate iterations based on the hypotheses built in the workshops
- Iterate over user personas, collect data about them and map to use cases
- Map use cases to user flows and then user stories
- Diagram and wireframe. I even tried to do the DailyUI challenge, but I gave up at day 40
- Demo and ask for feedback
Technologies: HTML, CSS, Flask,
Currently interested in building products utilizing generative AI. Questions occupying my head right now:
- Can I connect Siri to Ollama so that I can enhance my productivity?
- Can I scrape up-to-date dev docs that I feed into a local LLM and use them when needed?
If anyone wants to have a chat, feel free to text me on linkedin or spicylimer [at] gmail [dot] com
I think it would be awesome to be able to use GPUs from second-hand crypto mining rigs for cheaper fine-tuning research.
Good luck! As an enthusiast who loves The Lean Startup and who recently started playing around with LLMs, I'm super stoked about Answer.AI
I think to make it more worthwhile people posting here please write a little about your tech stack, why you made it, what are your struggles, and tips for other founders, etc.
Also, it's pretty nice to share with the small team I'm part of. We're currently working on custom client projects and we'd like to build our product. Seeing how people do it is a nice morale boost, especially for a team that lacks experience in building.
This week, I'll set up a Hugo blog with the Ed theme, love it, looks exactly what I'm looking for, and as a former LaTeX enthusiast, it's pretty close. It's readable, minimalist. I'll need to customize the theme, though. I plan to publish blog posts about anything I find interesting.
https://gohugo-theme-ed.netlify.app/
In parallel to this work, I'm setting up a simple system to keep my website + subdomains easy to build, rebuild, and deploy with Caddy on a cheap Scaleway compute server. In the past, I had some ideas I wanted to publish, but the system I went with made managing the sites dreadful.
Once that's ready, I'm back to learning Rust and crypto. It's fun, interesting, challenging, remote-friendly, and the salaries are usually 30-50% better. My current tech stack feels like a dead end: it has a low ceiling in terms of salary, the projects are generally not very interesting (I'm grateful for my current project, it's the best there is with this technology), and I believe the technology will see a slow and steady decline.
Apart from work, I'm building the playground for my 2 yo son, and planting blueberries, he loves them.
Now I figured out I want to go all in actually learning rust and doing the deep dive in crypto. Enjoy the trip.