Stromgren

In fact it came out as the absolute best in a comparison by Tencent (1). See table 4. It’s more than a year old though.

1. https://arxiv.org/pdf/2508.09101

For sure high end perfumes are high margin products. Can’t be a lot of cost in producing a $100 perfume.

But I also feel like it’s a bit besides the point. Seeing pallet after pallet of perfumes getting destroyed every month should be an indication that something is not right.

My dad worked at a logistics facility, the amount of perfume he took home was ridiculous - and you’d think that something like perfume would never go stale. It does from a brand perspective and they do everything they can to have it destroyed so it doesn’t end up being sold to prices that would hurt the perceptive value. Obviously he wasn’t allowed to take it either.

Of course there is. It’s not about the _amount_ of files or how many percent of them. I might have 1000 files that I’m fine having the LLM read and then some that it really shouldn’t. The problem here is plainly uploading your whole directory without prompting for permissions to read them - even if you explicitly set up permissions for read tools.

There’s a hell of a difference between a tool that asks my permission to read a file to make it part of a prompt and a tool that packages up my whole working directory and sends it to Google Cloud Storage.

The things you allow the LLM to read will obviously be sent as part of a prompt. You can control that though. Reads are tool calls and you can configure permissions for that or be asked every time the agent wants to read something.

This is straight up just uploading your whole working directory. Not as a LLM prompt, but to a Google Storage.

No I disagree. A harness reading a file is a tool call and it happens locally, which means that I can control it. I can configure that I need to permit any file reads and now I _should_ have control of what is sent. The difference between that and silently uploading my entire working directory in the background is miles apart IMO.

I understand that one should think carefully about how they work with a non-deterministic tool, but this if different completely. This is xAI just choosing to upload and store everyone’s directories - with full git history.

This was posted on HN yesterday: https://gist.github.com/cereblab/dc9a40bc26120f4540e4e09b75f...

If it’s to be trusted, it has nothing to do with the “agent” or what’s sent to the LLM. The harness will just straight up package the folder it’s run from and upload it to Google Cloud Storage.

I have a last name that only my family holds in Denmark (which means me and my brother by now), yet it managed to tag me a Professional Football Player, MP for the Socialist Party and Founder of a Sleep Mattress Company.

I do like the visuals though.

Why _too_ late? Late, yes, but you’re implying that some line was crossed.

I run a SaaS business on the side of my job and have been for 15 years. There’s a million questions I’ve never had the time to dig into although the data was there. Retention cohorts, free to paid tier conversions, subscription upgrades/downgrades and so much more. Just this week, I decided to just let an agent have access through psql and go nuts, writing all analysis to markdown files. Reading through it, there’s a few things it misunderstood and as a result, some of the analysis was flawed, but all in all I’m honestly mindblown. It would have taken me months to write queries and even just coming up with frameworks of how to think about these metrics.

That’s how I’d want it to be honestly. LLMs are tools and I’d hope we’re going to keep the people using them responsible. Just like any other tools we use.

I’ve been involved in building a system that reads structured data from a special form of contracts from a specific industry. Prices, clauses, pick up, delivery, etc. A couple hundred datapoints per contract. We had many discussions around how to present and sell an imperfect system. The thing is, the potential customers are today transcribing the contracts manually and we quickly realized that people make a ton of mistakes doing that. It became obvious when we were working on assertion datasets ourself. It’s not a perfect system and you have to consider how you use the data (aggregating for price indexing for instance), but we’re actually doing better than what people are achieving when they have to transcribe data for hours a day.

Agreed. I’ve used their platform to train smaller, specialized models. Something I could have done in Codelab or some other tool, but their platform allows me to just upload a training set and as soon as it finishes I have a hosted model available at an endpoint. It obviously has some constraints compared to running the training yourself, but it also opens up the opportunity to way more people.

I saw the cost of the three downed planes somewhere else and thought the price was huge. Now I see that it’s comparable to “First Tomahawk salvo”.

Yea it wasn’t meant as a counter argument either.

To be honest I haven’t even looked at competitors for some years. I guess one drawback of using third-parties for such a big part of the responsibilities is the lock in. The benefits of switching would have to be rather big for me to put in the effort.

I find Stripes fees excessive too, but I don’t think I’ll ever switch. I’ve been running a small SaaS product on the side of other work for >15 years and if it taught me one thing, it’s that I need to reduce the things I have to maintain, reduce manual work, reduce the things that can go wrong. There’s nothing worse than having to fix a bug in a codebase you haven’t touched for a year and possibly in a feature you haven’t touched in many years. I simply love that Stripe handles not just the payment, but the payment application, the subscription billing, the price settings, the exports for bookkeeping. I’ve had a few instances where my site was used fraudulently to check stolen credit cards and it was quickly flagged and I could resolve it with Stripe. I’m sure someone can mention alternatives and I’m sure that I could build something that would work myself, but they keep a big part of what it takes to run the business out of my mind and I’m willing to pay for that.

I very much appreciate this take. I will say though that I’ve had experience myself where using coding agents lead me to what I’d consider (in your terminology) a better mapping between information and code. Not because the agent was able to do things better than myself, but because, as my project grew and I got wiser on how to best map the information, it was incredibly fast for me to change the code in the right direction and do refactorings that I otherwise might not have gotten around to.

I use Tidewave as my coding agent and it’s able to execute code in the runtime. I believe it’s using Code.eval_string/3, but you should be able to check the implementation. It’s the project_eval tool.

In my experience it’s a huge leap in terms of the agent being able to test and debug functionality. It’ll often write small code snippets to test that individual functions work as expected.

It depends where I look. Among colleagues and tech-native friends, I feel like there’s healthy skepticism as well as the excitement about new tech. On the other hand, all the investment podcasts that I’ve been following for years are nothing but ignorant AI hype and reciting articles about how all the jobs are about to disappear. I guess the people who doesn’t make firsthand experiences are not leaving the hype yet.

And if you make someone 3x faster at producing a report that 100 people has to read, but it now takes 10% longer to read and understand, you’ve lost overall value.

Hey. thanks! The API doesn't actually use name sets like that. Though that was my first approach. I changed it to use lists of profiles from social networks. So when a name is requested it looks up every profile with that name and counts the number of times each gender is represented. If you use any localization parameters it will of course only look up profiles associated with the particular country or language. I quickly realized with the initial approach that my lists would never be sufficient, since most countries allow for almost any name to be given and when combining lists from the whole world, a lot of names would end up as unisex, that's why i went for a probability factor instead. Also i'm hoping that by using social profiles, it might one day be able to tell the gender of Superman or Catwoman and things like that. People can after all call themselves what they want on the internet.

I've actually thought about adding like a baseline of names from different lists though, to backup the names that are not yet represented in the dataset. Do you have a link to the names you are mentioning? Could be interesting.

Hey Dillon. It only found one match for "Dillon" in the dataset, which was a male. If Dillon is gender neutral the probability will probably change into some decimal when the dataset grows.

Thanks a lot. I'll look into this. Regarding missing names. I'm adding around 10.000 profiles a day to the dataset. So it get's better by the minute :) Not that huge a dataset yet.

Hey Ryan

I think most of these names will result in prober responses now.

A "confidence level" will now be recieved :)

Hello.

I'm the author of genderize.io. At the time of your comments i was slowly getting this API up and running. A lot of sudden traffic made that a little hard :)

At the time, i was utilizing a few lists of officially approved names from a few European countries. We have those in Denmark, where i'm from, among a few other countries. This had led me to believe that most countries had lists like this and i was planning to add them as i went along.

I since change my approach, moving from the lists to large datasets of user profiles from social networks. This has given me the chance to update the API, adding probabilistic guesses along with the ability to add localization based filters.

My datasets are not that huge yet, but they're constantly growing.

Just wanted to say thanks for all the feedback i found in here and give a heads up on the update :)