The blog is at https://geuis.com. I'll try to wrap it up today or tomorrow and get the post out.
13,114 karma · joined March 24, 2008
The blog is at https://geuis.com. I'll try to wrap it up today or tomorrow and get the post out.
For one thing, and granted this is my own experience, that model is much better at coding than any of the others I've tried.
But going beyond that, if I need to do anything complicated that might hit the baked in filters on these other models I don't have to worry about it with mixtral. I'm not doing anything illegal btw. It's just that I'm an adult and don't need to use the bumper lane when I go bowling. I also approach any interaction with the thing knowing not to 100% trust it and to verify anything it says independently.
I say all that to encourage people to try it out with different models. It's not production quality but totally usable for testing things out even on older machines.
SEEKING WORK
Location: San Francisco
Remote: remote/hybrid/in-office
Willing to relocate: no
Technologies: full stack engineer, JavaScript, node.js, Python, html/css, React and other modern web frameworks
Résumé/CV: on request
Email: charles@geuis.com
Github: https://github.com/geuis
LinkedIn: https://linkedin.com/in/geuis Location: San Francisco
Remote: remote/hybrid/in-office
Willing to relocate: no
Technologies: full stack engineer, JavaScript, node.js, Python, html/css, React and other modern web frameworks
Résumé/CV: on request
Email: charles@geuis.com
Github: https://github.com/geuis
LinkedIn: https://linkedin.com/in/geuisI wrote a browser extension back in 2005 or so called Commoncache to help the user view a page when slashdot hugged a site to death. It used a fallback mechanic where it would try Google cache, then the wayback machine, and finally coralcache.
It was minorly popular and even included on a cd in an issue of MacWorld magazine.
I have absolutely no idea what's happening with Google's project managers these days, or whoever in the company is making product decisions. Thousands of highly intelligent and highly paid staff just keep making their core product and associated features increasingly user hostile.
YouTube search is an absolute travesty. Google search just floods the first page with various cards that take up previously useful space and doesn't add value to the simple need to find answers to questions.
I firmly believe that only relying on A/B testing for feature launches reached peak usefulness years ago. It's like everyone forgot to see if new features are a benefit to users at a human level simply because 51% of people click more on B, while A is the better experience for everyone.
I consider people worth calling friends to be similar to family. I also don't have close family connections at that level. Guess that means I put more importance on friendship.
I've had the experience one time of cofounding a company with a friend. It didn't end badly, but it wasn't ideal. I realized pretty quickly I was going to be solely responsible for actually building the product. My partner was a great designer and actually had the business knowledge. To be completely honest we could have made something of it but I wasn't in the right place at the time to deep dive. Probably should have carried through with it. We'd likely be the biggest site to basically do Airbnb for cinema rental locations today. Again, I only say that because he had the connections to make that happen. Not something I could have done on my own
I guess I don't have any specific advice, other than general history.
If you and your friend are highly aligned then make a go of it. But on the contrary, Steve, Steve, and the other cofounders didn't agree. One backed out, and Apple became what it is now. Woz and the rest are $$$$$$$$$$$ aires.
In the end we all die. How do you want to think about your life in 10-20-40 years? Did you build anything? Are you ok with not having a big impact? Depends on you.
There was an interesting product at CES that used a gelatinous bed into which resin is injected and cured making it possible to print objects without supports.
Being able to do this with metal opens up a ton of future manufacturing options. It's not quite the same process and it's quite early, but with refinement this could be a very interesting future option for quickly building entire objects in minutes that would normally take hours.
I'm super glad now that I've gotten into the habit of disabling wifi when I'm not using the machine.
I absolutely cannot stand computers doing things without my say so.
Years ago my Windows machine forcibly did a restart and patch installation while I was working. It just exited every app I had running and rebooted. Cost me several hours of work. Talk about being instantly livid.
Unfortunately a day later I got a notice from them that the role I was interviewing for was being closed down. They encouraged me to look for other roles I was interested in and we could continue from there. I sent two, and then right after new years was informed they were freezing all hiring until mid January when they finalized their new head count. Then they were among the number of companies announcing new layoffs in the last couple weeks.
Talk about disappointed but still being appreciative. I'm still excited about maybe getting on with the company one day simply because they treated the hiring process with a lot of respect and didn't waste my time. It wasn't a me thing, but just bad news coming down from higher up internally.
This was definitely happening with OpenAI's web interface. It might have been happening via API calls too but it's been a while and I don't remember.
Nothing ever came of the report as far as I know.
I hate the idea of needing to buy another $3k laptop less than 4 years after spending that much on my current machine. But if I want to get serious about developing non-chatgpt services, do I need a new M2 or M3 chip to get this stuff running locally?
Location: San Francisco
Remote: remote/hybrid/in-office
Willing to relocate: no
Technologies: full stack engineer, JavaScript, node.js, Python, html/css, React and other modern web frameworks
Résumé/CV: on request
Email: charles@geuis.com
Github: https://github.com/geuis
LinkedIn: https://linkedin.com/in/geuisOn a personal level, we'll see what happens. Typical eat better, lose weight, etc.
It's definitely a loss, but not crippling in any way.