I love free+local. Can you add SVG->PNG with transparency? I never need help with any of the conversions you support today, but going from vector to raster would be super convenient!
Thanks for sharing! I tried using it for Thai language coming from English and found that the app understands me well! But I couldn’t understand it at all. It replied to my turns with very long messages (20+ syllables) in pure Thai and spoke with an unnatural rhythm which made it hard to pick out words or phrases. The foreign alphabet made it really difficult too. I tried changing some settings in the bottom left menu and it started speaking English to me too, but I found it unbearably slow. At one point it asked me if I wanted it to speak in pure Thai or a mix and then ignored my answer. Ultimately as a beginner I don’t think Issen will work for me very well as-is. Happy to check back in the future!
I've thought a few times when reading some funding announcement on techcrunch, "That was my idea!" which is super validating and nice to see. Some of these multiple-inventions are pretty inspiring to learn about. I think it reinforces concretely the idea that "execution" matters more than anything else.
Yeah. TBH I highly doubt the mainstream, condensed narrative of history. The focus is always on individuals; each invention conveniently having just one inventor, one hero... Whereas in reality, it's almost always a group of people sharing ideas and each making progress until one person stumbles upon the incremental improvement which makes the invention finally useful; that person gets all the credit, everyone else is a footnote, you have to dig into the history to actually learn about those other people. When I read serious history books or articles, I'm often shocked to learn about the contributions made by people I'd never heard of previously. When it comes to mainstream narratives, it's 'early bird gets the worm', there is little regard for contribution quality or even quantity. Someone could be doing most of the work, then some random person who's been quietly following that person's work comes along and delivers just the last missing piece; the frosting on the cake, so to speak, and they get the credit for the entire thing.
There are only a few cases I can think of where people seem to have a semi-realistic view on invention. Children often ask "who invented the computer?" and they are often disappointed by the answer because, it was so drawn-out (multiple generations), so granular, that you can't even make up an approximate answer. People grasping really hard will utter names like Charles Babbage but then acknowledge that there are a huge number of mathematicians, physicists and engineers behind it. Literally anyone who invented anything related to electricity and material science made a contribution too. It's the reality for most inventions that they materialized quickly within a single generation; this created a race situation and simple people basically agreed on some relatable finish line and then named a winner on that basis. The summary of history is written for simpletons; it's a caricature, it characterizes it in some way but it's also comical.
I find this applies to far more than just history. Anything attempting to get widespread appeal must be simplified. So much so, that whenever I notice an agreed upon understanding shared by the mainstream, I start to suspect that it's likely wrong (at least, wrong enough).
Agreed, same with business/entrepreneurship. Employees don't get much credit, even the really talented ones. Also, competitors don't get any credit, even though they may have added valuable competitive pressure which may have inspired and steered the winner to success. Who gets to be the front-man/front-woman for success is heavily timing and luck-oriented.
I had a giant laundry list. Most of it got build. My one trick was to not build anything but dream up the next thing in stead. It is hilarious to compare notes to see if they got the details right. It usually gives me a feeling as if the collective mind used my idle brain cycles to run other peoples thoughts by. The entire thing may arrive with an unreasonable amount of detail and float away a few hours later only to return in completed form a few years later.
Also funny is to have an idea just complete enough to be able to find the patents.
I searched for series b startups hiring for data analyst roles in the Bay Area for a friend. It returned lots of bigger companies that I didn’t want included. I also had no luck trying to figure out how to copy paste or share the results (using iPhone). Overall though I think this is a great idea and wish you the best!
I tried to vibe code a web app with windsurf and found it appeared to do really well in the beginning. But I had to harsh the vibes in two types of scenarios it couldn’t understand or solve on its own: performance and css animation.
When I copy paste via ChatGPT I direct the model on what to do and retain responsibility and understanding of all code getting saved.
I do really like Cascade in windsurf because it does a decent job of parsing the entire codebase and finding the spot to make changes. But I think I’ll probably be most successful combining my approaches and using Cascade at a coding level not a “vibe” level
I haven’t been able to get any AI model to find Waldo in the first page of the Great Waldo Search. O3 even gaslit me through many turns trying to convince me it found the magic scroll.
