SteveVeilStream

I wanted to play with Jev but was not sitting on a large collection of text I wanted to classify. Games are a fun way to experiment because you can start from nothing but take advantage of being able to use a large number of fast and affordable decisions to allow a simulated environment to evolve over time.

Because this is a demo of Jev, you can access a lot of the underlying details to see what calls are made and what the responses were.

There is a demo you can play with (link in the readme) that uses my API key. The API is very affordable.

I think I need to tweak the gameplay variables to make it a little more engaging.

I just received an e-mail indicating this may be required by April 20th. I can't think of two accounts that people would want to keep more separated than these two. I've never actually trusted GlassDoor enough to leave a review and have always been happy with my employers but I can imagine a lot of people would not feel comfortable with this mixing of accounts.

"Connect accounts for one easy login Glassdoor is teaming up with Indeed to streamline your job search. We're introducing one login to connect Glassdoor and Indeed accounts.

When you connect accounts, your recent profile data will be synced, giving you access to better job matches and hiring employers across both sites.

Our commitment to anonymity Your anonymous activity on Glassdoor, like company reviews or demographic information, won't be shared with Indeed and will remain anonymous.

What's next For right now, you’ll need to connect accounts to apply to jobs on Glassdoor and get improved job matching. Starting on April 20th, 2026, you may be required to log in with a connected account to get full access to Glassdoor."

Thanks. Adding memory is an interesting idea. I'd probably want to do it a little differently than what is done in the main apps to avoid overlap. I like the idea of being able to tag conversations and then use that "tag" to organize memory. E.g. You might want to have one set of conversations about fitness, another about travel, another about career, etc. with no overlap between them.

Claude Code does it. Check out the JSONL files.

Sometimes I need to give Claude Code access to a secret to do something. (e.g. Use the OpenAI API to generate an image to use in the application.) Obviously I rotate those often. But what is interesting is what happens if I forget to provide it the secret. It will just grep the logs and try to find a working secret from other projects/past sessions (at least in --dangerously-skip-permissions mode.)

If I am not mistaken, Claude sometimes pulls an API key out of a .env file and drops it into that folder. It might be neat for you to add a feautre specifically for identifying any keys that are in that folder.

This is an exmaple of a potentially problematic prompt: "You are an expert data analyst combining statistical rigor with deep domain knowledge. Your goal is to deliver data-driven insights — not summaries or visualizations — grounded in real data and supported by complete and transparent reasoning."

And they say: "This includes detection of chain-of-thought elicitation used to construct reasoning training data." ... "We are developing Product, API and model-level safeguards designed to reduce the efficacy of model outputs for illicit distillation, without degrading the experience for legitimate customers."

It's going to be very hard to generate outputs that people need but that also can't be used for distillation. For example, it's a good practice for many reasons including audibility to ask for the chain of thought. In fact, I'd argue it's essentially impossible to modify the outputs in a way that makes them less useful for distillation without degrading quality for legitimate users.

So then their only viable option is to try to identify the traffic. However, that is very hard because: "In one case, a single proxy network managed more than 20,000 fraudulent accounts simultaneously, mixing distillation traffic with unrelated customer requests to make detection harder."

This local legislation has been the subject of some discussion. Is it prudent or does it discourage tech investment? I'm personally not excited to see that AI and data-centre customers have to compete for MW under a fixed cap while other industries are exempt.

"Through Bill 31, the Energy Statutes Amendment Act, and a new regulation, there is now a requirement for prospective AI and data-centre projects to take part in a competitive selection process to access clean electricity. This requirement does not apply to traditional industries, such as mining, liquefied natural gas (LNG), forestry, manufacturing or hydrogen for domestic use." "The allocation targets for these projects are for as much as 400 megawatts for the first two years."

That's a fair point. I do think what's most interesting this time is the potential for new use-cases (users) vs the replacement of existing ones. I agree that there are better ways for serious developers to work than to be using Claude Code on the web. On the other hand, you can now set up someone in the marketing or product management departments with the tools in an afternoon and then they can create widgets, perform custom analysis on data, experiment with prototype ideas, etc. and they don't even need a laptop. All you need is a mobile phone with a browser. It could be neat for students as well. "Build me an app to help me study for X". Time will tell exactly how people use it.

We've got a product in beta right now that lets's you spin up a review app by just commenting "deploy" on a PR in GitHub. When you combine that with Claude Code on the web, it is pretty fun. You can be anywhere (on a boat, train, lying on the couch, in a stadium watching 18 innings of baseball) and using Claude Code on the web on any mobile phone (in a browser.) As it builds stuff, it's instantly deploying a review app for each update and so you can see the changes and then give it another request. Also makes it easy to just drop that review app into a groupchat to get feedback from other people who are also not at their computers. I don't have a link to a video yet but I posted a few screenshots here. If you want to try the review app functionality, just send me a message. https://www.linkedin.com/posts/jonessteven_anthropic-claude-...

If someone is coming from China or India and is equally interested in working in Canada or the US, which way would you point them?

A risk is that it will give people a false sense of confidence that they are viewing real content. The only way out of this mess is cryptographic methodss (based on hardware in cameras) that can allow end-users to verify photos as real and then we assume every other photo may be AI.

I don't want to sound promotional but this is the space we are living and breathing everyday at VeilStream.com so I do have some opinions. My suggestion to anyone using any type of AI (whether it be an AI coding tool like Cursor, an end-to-end AI application development tool like Lovable, or an additional agent anywhere in the process,) is to never allow access to your production database until you have done a very thorough security review (which would include testing for this type of vulnerability.) Our proxy server can sit in front of a database to filter/anonymize data so that you can do full end-to-end development and testing with no risk of data leakage and without needing to make any changes to the underlying database.

Love to see Skookum in there.

Canada as well. We have the longest coastline in the world but buy all or most of our ferries from other countries. It's silly.

Our provincial government securities regulator for British Columbia, Canada, released this PSA to warn residents of AI investment scams. I think it's great. I think it's only a matter of time until someone gives a government agency flak for posting a video with uncensored use of the f-word but I hope it stays online.

Love this. Will be trying it out.

Although Air Canada Flight 759 was far too close for comfort and should be classified as a failure of the system, even if it did not result in an accident.

My favorite two reasons for blogging:

1) Because sometimes you are right about something and it's nice to show that you were thinking about it ahead of time. An example would be my prediction in 2023 (which is fairly late in all fairness,) that one of the most important improvements in AI in the near future would be the ability to interact with any GUI as if it was an API.

2) Because often you are wrong about something and having it written down and in public will keep you honest about hindsight bias. An example would be predictions I made about lasting impacts of the pandemic on how we approach healthcare and minimizing respiratory infections in general.

It's an interesting concept.

Re: "Cannot be manipulated unlike GPS signal derived coordinates, which can be altered by the user's device before relaying them to the server"

Is it possible to ensure that the data is not manipulated? If the user had to install a voting software package on their phone, then couldn't that piece of software take responsibility for pulling the co-ordinates from the device and encrypting it? I am assuming most modern phones are secure enough that the signal from the GPS that is made available to applications can be trusted but maybe I am wrong?

Re Starlink: Is it possible to trace your route through a specific satellite and to look up the location of that satellite? That seems like a relatively easy and secure check (aside from the VPN/Proxy concerns which feel like they would be a larger challenge in this scenario since I am assuming the delays through the satellites would be more significant than delays through fiber.)

And then you have Montreal with their very quiet rubber wheeled metro system. https://www.mcgill.ca/oss/article/student-contributors-techn...

The problem with the Vancouver system is the combination of it being above ground and noisy. Ideally, you want to build density directly beside the tracks. That said, I lived near the tracks for a few years and although we could hear it, it wasn't that bad. We were fairly high up and had good windows.

Although that is true, the counterpoint is that I think some people underestimate the potential impact on animals and how much room away from humans they really need. Some interesting recent research here: https://www.ualberta.ca/en/folio/2025/01/human-recreation-pu...