It is a smart move. When Plus first came out, I signed up and loved it. Then they released the API and I realized I could save a bunch of money by canceling my monthly sub and just use API. Then they released a bunch of cool features that are only available with Plus on the web or app, so I'm off the API and back the GUI.
I did the same but with GPT which is 10x the price of 3.5 the API is no longer cheaper. I'm sad because I hate using the website. Every couple of days it silently logs me out so I have to retype my query and it's also just a really poor UI
When I was on plus the only feature I used was the bing thing but they pulled it so I stopped paying. Also it was basically useless because it's so slow and can only handle 1 browsing thread at a time.
Maybe it's just my Firefox antitracking blockings but most of times when I go to chat.openai and it redirects to login page, I can just retry going to chat.openai and I will be logged in. I haven't had to relog in a month at least.
After detecting a botnet attack originating from Cloudflare IPs, we logged in to Cloudflare. Shortly after, we received the message: "Sorry, you have been blocked. You are unable to access www.cloudflare.com." We hypothesize that a larger scale attack is underway.
Congrats on the launch! I'm testing it now and are excited about it. I've tried few similar solutions in the past few days but they were buggy and not as feature rich as your solution. I do have a few questions:
- What's the differences between Assistant and Chat mode?
- If I have GPT4 access is there anyway I can insert my API key and use it with your app? I assume you're using 3.5 turbo.
- What toolchain are you using for splitting / chunking?
- Nothing as of right now! Just an interface. I don't think I implemented snippets yet for Chat mode though
- Not yet, although I plan to introduce this. I found that GPT4 is a little slow right now, and much more expensive, but it'll be awesome to enable this for users, then I could charge even less.
- I recommend langchain, it's one of the few things that I didn't modify for my use case on their library.
It can do basic math reasonably well (and this is achieving generation where GPT-3 failed).
Interestingly, asking it to verify itself does resolve bugs sometimes. Managed to fix subtle count() denominator bugs and an inflation-adjustment error with not much hinting on my end.
You can only see it struggle really hard at the end when it tries normalizing month ranges correctly. It seemed to reach conceptual problems over how LAST_DAY() was being used and current debug itself.
I tell it that I'm using <database and version> and give it the relevant DDL statements (e.g. CREATE TABLE, etc) then ask it to write the query to do <x> in plain English. It does surprisingly well.
But!!! the first response is rarely dead-on and instead, just like a junior eng I need to guide it: use (or don't use) SQL construct <x>, make sure to use index <x>, etc.
Example: to sum the values in a JSONB field, GPT desperately wanted to use a lateral join but that would have made for a very awkward set of VIEWs. So instead I directed it to create a function to perform the summation.
Same here. But fortunately the web clipper in DevonThink is not very good, and with the annoying cookie pop-ups it’s hit or miss if websites will be archived properly. I wish DT would work on this, but they seem to treat the web clipper as an afterthought.
Same. Capturing the contents is a good start, but being able to index them, store them next to related articles, summarize them, or get automated “see also” links is the real magic.
I save the HN page as a PDF and send to DevonThink via the DevonThink browser extension. This way I have all the comments indexed and searchable via Finder or DevonThink. I tried webarchive but found PDF to be more efficient.
Why are PDFs more efficient? I’d think web archive is better. So far I’ve been doing web archives with Devonthink recently. Dumping a ton of content into it but have not searched much yet.
Shopify isn't a homogeneous marketplace that is comparable to Amazon.com. It's a SaaS ecommerce platform. I've seen these comparisons made lately and I don't understand it. What am I missing?
For everyone that's trying to compare Shopify to marketplaces like eBay and Amazon, you really can't. They are apples to oranges. Shopify is an e-commerce platform that gives you your own website where you’re required to do your own marketing, SEO, and develop your own customer base. Selling on eBay and Amazon on the other hand gives you the advantage of putting your products in front of millions of customers who are actively window shopping. The former gives you ownership of the customer while the latter doesn’t.
Both types of sales channels have their own value props and are complimentary to each other. Furthermore, even each marketplace attracts their own customer archetypes so they can also be complimentary to each other. This isn’t a binary strategy where you choose to sell on one or the other!
I’m the founder of Trunk[1] which helps online e-commerce stores sync their inventory in real-time across their sales channels. Most of my customers on average sell on least 3 places (e.g. Shopify, eBay, and Amazon).
Congrats to Tobias and his team. He’s come a long way from being a Rails core team member back in the day!
This looks incredibly useful. Real-time inventory sync is a big headache for some of our customers. (We provide a native mobile sales channel for retailers with only a traditional web presence. Think Tapcart (https://tapcart.co/), but not just for Shopify). I'd like to know what your plans are for which platforms to support next, and if you've got ideas for opening up an API at some point as well?
Thanks! The next integrations are looking to be either WooCommerce, QuickBooks Online, or Wix. NetSuite is also a big one but they are super slow in getting back to me. I’d be very interested in learning more about your product and customers, sounds great! The API has been something that’s been requested before but probably not a 2019 initiative. If you guys have an API that I can work with, that'll also work. Either way, let’s get in touch! You can email me at: james@trunkinventory.com
Trunk looks useful... my side business is handmade leather goods (https://coastleather.com) and cross posting between my own website, ebay, etsy and amazon is a pain, so I just don't bother. This has meant that channels other than my website became stale and I shut down the stores.
Do you have plans to include syncing for woocommerce stores?
Yea, we do! WooCommerce is one of our most requested integrations and I’ll be getting to it soon. Trunk doesn’t yet support cross-posting however but this will be a Q4 intiative. Would inventory syncing be enough for you to get value from Trunk at the moment? I’d love to get in touch: james@trunkinventory.com
Well, Amazon/Ebay/Shopify/Etsy all are platforms that let other people sell things. I get your point (and might even agree with you), however if you look at it from the perspective of "I want to sell something... where do I go?", they're competition.
They do discovery, checkout, inventory, fulfillment, etc. It just happens to have a slightly different approach than the others.
Not really the same thing though, Amazon/eBay/Etsy you can browse multiple "stores". Shopify is just a platform so it really isn't that fair. It'd be like including every single Magento powered site to say Magento is the X largest platform.
They do discovery? At Amazon and eBay most purchases come via Amazon's and eBay's search engines. Shopify doesn't have a search engine other than the ones inside individual stores. It's a very different business.
Not really, type shopify.com and let me know if you can buy a pair of shoes. You can't. You go to eBay and you can. Shopify is just the platform and the entire ecosystem supports the amount of transactions.
The seller side is the perspective that matters in this comparison. If you have wares to sell and want to start selling through the internet though a managed platform, amazon, ebay, etsy and shopify are competing options for you.
A main difference is shoppify you do still need to bring your own consumer traffic to your site, others have a captive audience of shoppers already, but will likely cost you more out of each sale because of that.
Being born in the 1980s I was curious to see what the American Black population's poverty rate was in the 1980s. To my surprise it was as high as 35% [1].
Not really surprising given that was a deliberate policy objective of lots of places in the pre-civil rights era?
Even as late as 1985 the police could carry out what in any other country would be described as a terrorist attack, leaving a number of people dead and burning down 65 houses, without serious consequences to themselves.
https://www.npr.org/sections/codeswitch/2015/05/18/407665820...
I feel like folks have a bit of a skewed perspective on the timeline of the civil rights movement because of the way we teach it. For example, Brown v. Board was decided in 1954. We teach it as a culmination of a process (because it’s more dramatic that way). But Brown was just the start, rather than the end, of school desegregation. For the most part, the south simply ignored the result. The famous event where JFK had to send federal troops to forcibly integrate the University of Alabama happened almost a decade later. The first school desegregation cases were brought in Mississippi in the late 1960s. As of 2015, there were still 174 school districts under court-supervised desegregation plans.
