> Nobody is doing 'small casual transactions' with Bitcoin, which was evidently one of the goals.

That is not true and can be easily proven looking at the transactions on the blockchain.

However, layer 2 solutions like Lightning are good for small value transactions since fees are low and fast.

Love this but I have concerns with the price. You can usually find an audiobook corresponding to a paper book for relatively cheap. Services like Audible are a little more per month but you get more audio books. Given the 250 page per month limit at $9.99, how will this compete?

Yeah I (and my fiancée) are also Audible users — this app is mostly for cases where an audiobook or even e-book don't exist, like for older books you might get from a used bookstore or library. I'd prefer to set the price point lower, but if a user uses their 250-scan quota (which can be up to 500 pages, since you can scan 2 at a time) fully, I'll actually be losing about $10 on them that month, so I'm hoping not everyone uses their full quota!

That said, I'm expecting OCR, LLM, and TTS API prices to continue coming down, at which point I'll be able to drop the price and raise the quota. Honestly I suspect iOS itself should be able to handle this use case well sooner or later, but until then, there's this app :).

Exorbitant vanity gTLDs more like it.

A bit of an aside but are there any options like this for mobile?

Works on Firefox nightly (android)

I think most of the tips outlined in this article make sense for anyone wanting to succeed at something regardless of their talents or intellect.

I think the working hard mentality should be approached with gumption and attention to detail as this can lead to high quality results.

Code Rush

Startup.com

What is the service called?

Walden Pond (waldenpond.press)

I felt like this blog post ended quite abruptly. I was expecting for the author to show how GPT-3 was able to formulate a response back to the recruiter not just parse out the name and company of the recruiter.

Perhaps this was the result of pointing GPT at the title "Responding to recruiter emails with GPT-3" trained on a corpus of tech blog posts.

I was worried that that was the direction the article was going to take. My experience with GPT-3 is mostly from playing AI Dungeon, but it seems like it's very eager to go along with anything from the input. It's the ultimate "yes, and..." improv partner. I wouldn't be surprised if it just automatically agreed to every interview request.

Can you prompt GPT-3 "as the person who received message {message}, respond to it." and it understands that it is addressing William from BillCheese (aka, "Hi William...")? Perhaps the best you may be able to do with the current model capabilities is something like "response to message {message} by thanking the sender and telling them you are not interested right now but will get in touch if that changes."

Yes you can, you should create an account and try it out. A fun example I just did

Respond to this email, pretend to be a pirate called Old Blue Bill who is very interesting finding out more about these job opportunities.

"Good Afternoon,

I have 4 brand new roles available, please see details below. I also have an Engineering Manager position becoming available in Leeds (tech is Java/Kotlin), so if you have Leadership/Management experience and want to help an exciting company build a new bank then get in touch as well (the company ae financially stable, part of a £1Bn organization and just received around £30M in funding).

If interested please send me your up-to-date CV and we can set up a call to discuss."

Good day to you, stranger. I be Old Blue Bill, the terror of the seven seas. I be interested in these job opportunities ye be havin'. I gots me a mighty fine CV what'll make ye sit up and take notice. Arr!

Ye best be gettin' in touch with me soon, lest I take me wrath out on yer crew. Avast!

Thanks for the feedback. I just updated the article. Basically I plug those extracted values into a templated response.

Have you had a chance to experiment with whether GPT-3 prompts can be used to dynamically construct the response? For example, "if the messages describes a frontend role, say I am not interested, and if it is a backend role say I am interested."

I haven’t explored it any further yet, but that seems like a useful extension.

That’s actually a good and safer automated use of GTP-3 though.

What was truly won at that auction was a priceless friendship and the ability for someone to pass down some of their prized books to their grandchildren. Amazing.

I have been working fully remote for over two years now. I certainly feel quite disconnected from my team now. I remember the days of commuting, water cooler talk, and just being around people.

I’ve been with my employer for a long time now and have experienced a lot of coworkers passing away. Cancer, heart attacks, suicide, and undisclosed. The whole spectrum. Some of these coworkers I worked close with while others not so much. Either way it affects you and really puts things into perspective with how fleeting our lives are. Thinking about this gives me a lump in my throat.