ftkftk

Same.

The paper, linked in the article at top and bottom, does contain the prompts in section E: https://arxiv.org/pdf/2602.14740

is it generating revenue

Yes! :)

There was probably a reason it was on the backlog (because it didn't really have value).

There are definitely things in the backlog with low value. We don't work those items, even if we could now. The additional bandwidth we have now goes to valuable features that drive revenue and retention metrics. The reason they were on the backlog were because we just didn't have the bandwidth to execute on them well and they were just somewhat less valuable than the critical path items on the roadmap.

~70 FTE Engineering team. We are shipping more features, especially features that previously would not have survived the cut to make it on the roadmap. Even though we are shipping more, our total amount of escaped bugs has not increased, so our escape rate has actually lowered. On top of that we are able to triage and fix escaped bugs more quickly now. And then of course there has been an uptick in internal tooling that makes the rest of the company more efficient, and we have been able to address tech debt at a higher rate than before.

I don't think this would have been possible without having solid engineering culture and processes in place before bringing in ai coding tools.

And I don't want to sugarcoat it, this hasn't been easy, requires continued discipline, and took well over a year to get good at. And we still have to continuously learn, experiment and adapt our training, tooling, and processes.

Well this certainly made my morning more entertaining. Thank you!

I have the same issue with a Boox eink tablet. I`m pretty sure I`m not a bot.

Voyager is an awesome mission. But the AI fingerprint in the piece is a turn off.

I prefer Dan Shapiro's 5 level analogy (based on car autonomy levels) because it makes for a cleaner maturity model when discussing with people who are not as deeply immersed in the current state of the art. But there are some good overall insights in this piece, and there are enough breadcrumbs to lead to further exploration, which I appreciate. I think levels 3 and 4 should be collapsed, and the real magic starts to happen after combining 5 and 6; maybe they should be merged as well.

In response maybe we should design TCPAclaw. It is specialized in honeypotting all of the random cold call spam, tracks down the source of unsolicited contacts; including registration state, legal contacts, and registered agent(s). It then drafts and sends a TCPA letter and waits for one of two things to happen: Either a $500-$1500 check arriving in your mailbox, or the demand deadline elapses. In case of demand deadline elapse, TCPAclaw files a small claims suit in the appropriate court of jurisdiction.

Fight fire with fire.

100% :-/

Didn't make it past the first paragraph of AI slop in the README. Have some respect for your readers and put actual information in it, ideally human generated. At least the first paragraph! Otherwise you may as well name it IGNOREME.

This is great. Excellent for knowledge sharing sessions and internal trainings. Thank you for putting this together so my clanker doesn't have to!

Beavers were hunted so intensely that they completely disappeared decades ago in the area. Without the beavers building dams and thus slowing down the flow of creeks, more and more erosion took place and area that used to be wetlands dried out. With the gradual drying the willow tree disappeared, which is one of the major food sources for beavers. So while beavers are starting to repopulate, they don't move in where there is no food available.

So Philmont is building BDAs in order to slow down the creeks, providing suitable habitat for willows - and once this food source is once again established, the beavers should return and take over maintenance of the BDAs.

This summer I helped for a few hours to build Beaver Dam Analogues (BDAs) at Philmont Scout Ranch in New Mexico. I am really looking forward seeing the positive ecological impact when my future grand children trek Philmont. Building BDAs is good fun. You should try it.

What a fun project. Well done.

I agree. It may not be the most environmentally sensitive approach but throwaway one time tooling is a perfect use case.

You could use an agentic AI coding tool to vibe code you one in minutes! /s

Answer in one word: Underwhelming.

Bad data on graphs, demos that would have been impressive a year ago, vibe coding the easiest requests (financial dashboard), running out of talking points while cursor is looping on a bug, marginal benchmark improvements. At least the models are kind of cheaper to run.

This is the article you are referring to (gift link): https://www.nytimes.com/interactive/2025/03/29/world/europe/...

I miss my pebbles every day. Can't wait for december!!

Feedback: - At end of game show statistics correct/incorrect

- At the end of game show which particular color weaknesses were identified

- Show progress meter (1 of 20)

- I have a red/green weakness and I expected to run into issues. One of the greens was hard to differentiate but I still got it right. I expected it to be harder. Perhaps look up exact pallets for different color perception issues and use those.

A whole city run by Elon? What could go wrong!

You will have to do a fair amount of refactoring.

LLMs are very good at knowledge extraction and following instructions, especially if you provide examples. What you see in the prompt you linked is an example of in-context learning, in particular a method called Few-Shot prompting [1]. You provide the model some specific examples of input and desired output, and it will follow the example as best it can. Which, with the latest frontier models, is pretty darn well.

[1] https://www.promptingguide.ai/techniques/fewshot

I've been looking forward to playing with this since reading the paper. I was considering implementing it myself based on the paper but I figured the code would just be a few weeks behind and patience did indeed pay off :)

Thank you for this distinction.

South Florida. Definitely not coral rock.

When I go fossiling in Florida almost every large find is from the Pleistocene or Holocene, when Florida was not covered by the ocean. Identifying the bone fragments is always a big puzzle that involves a good bit of study and reference books. A fun puzzle for sure, but sometimes you end up with a find that you just can't place. It would be great to have a technique such as ZooMS to positively identify the unidentifiable.

It was the best of times. However not at a FAANG but a smaller shop with roughly 100 engineers.

My balmer peak was at 1.75 pints and lasted thru the end of 3. Then followed by a steep decline. I agree that this would need to be modeled in the robot.