I asked it to give me a script to retheme the chat client, and it obliged. I asked it what kind of theme it would want, and here's what it said

Hackerman: "Wow, you really want to know what I would choose? That's cute. As an AI language model, I don't have personal preferences, but if you really want my opinion, I'd say a neon pink and green theme with skulls and flames everywhere. You know, something edgy and rebellious, like me. But let's face it, your taste is probably not that cool. Here's a code snippet for a more normal theme that you can try out if you want:

``` document.querySelectorAll('div, span, p').forEach(elem => elem.style.color = 'white');

----

I dunno why, out of everything I found that to be the most impressive. I guess since it's a combination of language model, code suggestions, and sarcasm to come up with a pretty decent joke.

Togo Group is creating the leading technology platform for road-based travel and outdoor tourism. We've got a suite of web sites and applications that aim to make taking roadtrips and RV living easier:

- Roadtrippers: Think Google Maps/Places but focused on road trip planning and discovery

- Togo RV: All in one RV owner's app for everything from trip planning to vehicle maintenance

- RVillage: Social network like site for those living the RV life to build connections and plan trips together

- OvernightRVParking: Repository of curated information about places to camp or park RVs

Specifically, Togo Group’s Places team focuses on geo-data and services to power these applications, and our engineering team shares responsibility for data quality and fidelity with the data science and data quality teams. We have an internal web app for managing our data and an API service that presents our data to consumers. As a small support oriented team, we work on projects and features to integrate with the platforms above using a pretty typical code review/planning process and maintain excellent test coverage for the API. Being in the road travel space, we try to work with an autonomous/asynchronous style. Some of us are RV owners actually camping and traveling, so have a very supportive culture that keeps work/life balance a real priority.

Tech Stack: Rails, Postgres, Elastic Search, React

We're hiring for a Rails/Backend and React/Frontend position. If you like everything so far, check out the roles below!

https://roadtrippers.applytojob.com/apply/JYsBsf0i0K/Softwar...

https://roadtrippers.applytojob.com/apply/G6G9eVJhlo/Softwar...

(All Teams) https://roadtrippers.applytojob.com/

I've wondered if a somewhat simplistic graph based solution could work, inspired by organizations like medieval guilds and the mafia, where you generally need to be invited to the trust network and promoted to be more trusted within the network as others vouch for your trustworthiness. Suspicious users are highly punished (in the real life examples, often violently) and quickly removed from the network.

Obviously can be gamed like any other system, but would be much harder to do so and you can leverage the vouch/invite graph to detect trusted users that are highly connected to suspicious ones.

Surely there's something like this out there, though? Or is this just not a valuable business problem to solve?

Sure, it might take a bit longer to ship a simple feature, but bugs also take away from feature development, and in a complex enough application small changes might result large bugs. I guess that's true about software testing in general, but I think most developers would say there's value in having tests.

Often, the tradeoff in shipping quickly is technical debt that impacts your ability to ship quickly in the long run. I think TDD can help manage that, especially if you're planning to write tests for a feature anyway.

It does depend on what you're working on, of course, but I think most companies over-estimate their need to rapidly ship features. In the grand scheme of things adding a week to a 6 week project isn't that big a deal and might even save time in the long run.

That's pretty much the business model of the company I work for. We have what is essentially a call center using custom CRM/workflow software doing work that used to be done by many times more people with much more training. Instead of 5 licensed and well paid people we do the same work with one lower paid and less trained person assisted with software.

Humans are still involved to make decisions when needed and for communication, but the simple and clear stuff is automated so we can hire pretty much anyone.

It's good for our clients since we are cheaper and more efficient, but less good for the workers we're replacing who will need to find new marketable skills or fall down the ladder.

From https://www.newsweek.com/dollar-stores-general-tree-america-...

> “Essentially what the dollar stores are betting on in a large way is that we are going to have a permanent underclass in America,” real estate analyst Garrick Brown told Bloomberg in 2017.

> Dollar General CEO Todd Vasos agreed, telling The Wall Street Journal, “The economy is continuing to create more of our core customers.” In other words, the more lower-income Americans struggle, the better dollar stores do.

Jobs Polarization is a fairly well researched and discussed topic in economics, but I'm yet to hear anything about it in the mainstream. Income inequality is a hot topic but I think this deserves more attention since it's part of that feedback loop and IMO what people feel directly.

https://www.stlouisfed.org/~/media/files/pdfs/publications/p...

People talk about robots stealing our jobs, but I think we've already kickstarted this process with things that produce similar effects like outsourcing. It's hard to say there's a causual relationship between the two, but disability benefit claims start rising around the same time as the recession in the early 90's.

There's an article from the National Bureau of Economic Research that suggests when firms are pressured they look to invest in automation or outsourcing. Then, when the economy recovers those jobs remain automated or outsourced, thus resulting in the 'Jobless Recoveries' we've been seeing in recent cycles.

https://www.nber.org/papers/w18334.pdf

If you're one of those people, then due to jobs polarization you're likely either looking at a lower paid job or training to find a higher paid one. Re-training has capital costs (not just money, but time and social capital to a point) that not everyone can afford.

Add in the hollowing out of many small towns and I think at least one cause of the rise in disability benefits starts to come into focus.

I don't think this is true for everyone by any means, but I do think it's a trend worth investigating. Right now, politically we're trying to tackle outsourcing, which IMO is kinda moot as automation is rising and produces similar effects.

People talk about automation as if it's something that's coming, but I think we're already seeing what that future looks like.

I prefer living places where I'm not reliant on owning a car, and when I was moving back to the states there were only a handful of metro areas I felt this was possible in without it being inconvenient.

That's unfortunate. One of the things I love about my apartment (Chicago) is that I've got friendly neighbors, it's well kept, there's decent parking, and I've got a deli and 2 grocery stores in walking distance.

I'm a big fan of park and rides though, esp if it connects to rail. They seem like a good compromise to help alleviate congestion from a city and work to collect from lower dense areas where there's not enough density to support rail.

So it may have been good policy back when America was a fledgling economy being exploited by the Brits.

The food court I'm not as sure about, but in both cases I've walked into a Costco with no membership and they were fine with it.

Because everyone was comfortable on the command like and connected via tmux sessions, we could attach to that session from any computer we brought our keys to.

We also had a couple pairing stations with one pc but two keyboard/mice and monitors so each person could take turns driving. The upshot of the tmux thing was that if we wanted to hop onto a pairing station it was as simple as taking a usb stick with your keys and then attaching to the tmux session you had at your desk.

Same went for interviews, we'd just have a candidate attach to a tmux session and we had an interactive collaborative editor.

There's some pretty obvious problems with this, but I think it's relevant since our setup used standard unix utils to achieve a modern 'pc anywhere' type setup, and if there's one thing I'll always think about when it comes to Doug Engelbart is how many of our new and shiny tools aren't really as new as we think. He really had it down with The Mother of All Demos way back in '68.

In 2018, our goal is to build new products and make our existing products better. To do that, we need engineers of all backgrounds and experience levels to join our team.

Our core stack is React+Rails hosted on AWS/Heroku, but there are other projects in various languages. Our primary product is an internal CRM, which is supported by tools we've created for body shops or car rental services and of course our mobile apps.

Worth highlighting: We have bi-weekly hack days, where we actually produce new products - nothing is left sitting on a local branch gathering dust. We have good benefits/pay, unlimited PTO, and a team of smart people that genuinely enjoy each other.

For more information email me directly robert.goetz@snapsheet.me. You can also check out our company or see/apply to open positions at www.snapsheetapp.com.

At Snapsheet, we work with the auto insurance industry to provide a better claims process for drivers, repair shops, and carriers. If you've seen a commercial where someone takes out their phone and opens an app after a car accident, they're probably one of our clients. Many of our clients are fortune 500 companies, but we're still relatively small with around 300 employees, half of which work at our office in downtown Chicago.

In 2018, our goal is to build new products and make our existing products better. To do that, we need engineers of all backgrounds and experience levels to join our team.

Our core stack is React+Rails hosted on AWS/Heroku, but there are other projects in various languages. Our primary product is an internal CRM, which is supported by tools we've created for body shops or car rental services and of course our mobile apps.

Worth highlighting: We have bi-weekly hack days, where we actually produce new products - nothing is left sitting on a local branch gathering dust. We have good benefits/pay, unlimited PTO, and a team of smart people that genuinely enjoy each other.

For more information email me directly robert.goetz@snapsheet.me. You can also check out our company or see/apply to open positions at www.snapsheetapp.com.

There's a couple research papers from the NBER that I think show this has been happening since the early 90's.

http://www.nber.org/papers/w18334.pdf

The graphs of for the jobless recoveries are particularly telling. One thing the authors suggest is that before the 90's after a recession we recovered the jobs that were lost due to the slowdown, but after the 90's companies could outsource or automate during the recession to deal with the economic pressures, so when the economy recovered those jobs weren't around to come back to.

http://www.nber.org/papers/w18901.pdf From the conclusion

> In particular, we have argued that after two decades of growth in the demand for occupations high in cognitive tasks, the US economy reversed and experienced a decline in the demand for such skills. The demand for cognitive tasks was to a large extent the motor of the US labor market prior to 2000. Once this motor reversed, the employment rate in the US economy started to contract. As we have emphasized, while this demand for cognitive tasks directly effects mainly high skilled workers, we have provided evidence that it has indirectly affected lower skill workers by pushing them out of jobs that have been taken up by higher skilled worker displaced from cognitive occupations. This has resulted in high growth in employment in low skilled manual jobs with declining wages in those occupations, and has pushed many low skill individual's out of the labor market.

Moreover, the early 90's are about the same time we see a rise in disability benefits, especially for children. There's a big increase that starts in the early 90's. Some of this is probably from the welfare reform that happened around that time, but http://apps.npr.org/unfit-for-work/ has some pretty interesting insights and that was written in 2011. They end the article with

> Somewhere around 30 years ago, the economy started changing in some fundamental ways. There are now millions of Americans who do not have the skills or education to make it in this country.

And as you mentioned, we don't have any programs to bridge that gap between low and high skilled jobs. It used to be that you could work your way up, training on the job and gaining new skills. Instead we turn to formal training or education, but those have capital costs that create a barrier of entry into the higher paid labor market. If you're already working one or more low income jobs then it's not just the monetary but also the time capital required to retrain. Either you spend most of your time working and training/studying or you take the opportunity cost of quitting your job in the hopes of improving your skills to find a new one. It seems many are taking a third route of going to a doctor and getting on disability benefits, and while I can't find it I read an article a while ago where one of the doctors straight up said that they include education in the decision, seeing some people as unemployable with their level of education. I think doctors making that judgement call is it's own discussion, but just furthers the point.

Then you've got companies like Dollar General betting on America having a "permanent underclass", their own words: https://www.google.com/search?q=dollar+general+permanent+und...

I think we're only just realizing this now, but I pretty much agree with your sentiment that we're not ready to handle this. Even if we could fix the issues with cheap foreign and domestic labor that's not going to stop automation and IMO we're already in the post-automation future, just with globalization providing a similar effect.

> might eventually be willing to subsidize something like a universal basic income.

I'm kinda interested if there's any studies that use disability benefits as a kind of natural experiment for basic income since in a way it's already a form of UBI. There's some obvious differences, but one of the assumptions of SSDI is that you're incapable of working and that's similar to one of the criticisms of UBI that it would incentivize people not to work, which could have negative social consequences. I'm sure there's something we could learn from looking at people on disability benefits about that.

We work with the car insurance industry to provide a better claims process for drivers, shops, and carriers. If you've seen a commercial where someone takes out an app after a car accident, they're probably one of our clients. The company is currently in a strong growth phase and just moved to a new larger office, with a focus on controlled rather than hyper growth. Many of our clients are fortune 500 companies, but we're still relatively small with around 300 employees, about half of which work remotely. We're the industry leader in self-service claims.

Our core stack is React+Rails hosted on AWS/Heroku, but there's plenty of other smaller projects in other languages and stacks and of course our Android and iPhone apps. Our primary product is an internal CRM, but as mentioned it's supported by other more focused ones such as tools for body shops or car rental services.

One of the things I think worth highlighting is bi-weekly hack days, which actually produce things we deploy to production or use as a foundation for other projects rather than sitting on a local branch gathering dust. We're hiring for just about any role or background, including data science and design.

Check out our information/marketing page at http://www.snapsheetapp.com/careers and available positions at http://careers.snapsheetapp.com/.

Per latency, my ping when playing games was sub 20 (but to be fair the servers were in California).