ryanchants

Unless they are changing their support process to not require a user to post on a message board and hope a developer sees it, I don't see how it's really taking responsibility.

And why should I give them more leeway for outsourcing to an inexperienced company? Comma/decimals meaning in currency is pretty well-established. If a new company is moving into an established space I would expect them to learn from other folks past experiences. "whoopsy, we don't know our core competency" isn't a defense for a company that's presumably making exorbitant amounts of money from partnering with Anthropic.

Home is the first place, work/school is the second place, the third place is everything else.

Agreed. When I read the headline I was wondering how this tied into the Graphene I knew.

FluidVoice has been working well enough for me on my laptop.

As someone who deployed twice, I don't really get why it exists.

"2026 Military Influencer Conference" influencer culture has gotten really out of hand

> I can start a new show and drop it 15 minutes in if I decide I don’t like it

IMO, that can also be a problem. When I was young and buying CDs, occasionally you would buy one you didn't like at first. But since you had spent money on it, you'd listen to it. And I discovered some good music that way.

Same thing with movies and tv shows. Sometimes it takes a bit to get going, or I 'm in the wrong mindset for it, but repeated viewing or just sticking with it gets me through that.

I'm working on a LLM code review tool that focuses on reducing concepts instead of reducing lines. I think that's more along the lines of explaining what you want out of clean code than ponytail's approach. But I'm still playing with it so, not sure. And just because it produces code I like doesn't mean it's good code for everyone

They are also anti-inflammatory, so it could be related to less systemic inflammation.

I always say that AWS docs are exhaustive, but exhausting. Mostly because they're spread across half a dozen places. The answer you need is normally in there somewhere, but good luck finding it. And when I remember the docs contain some fact I want re-reference, I can never find it again.

Is it a "productivity panic"? I'm personally pushing a lot more commits because I'm spending more time playing around with ideas on side projects.

Is this all wasted if commits drop in a few months because folks are just pushing a lot now to figure out what works and what doesn't and we eventually settle into something between where we are now and where we were a year ago?

uv. Being able to download an instagram video with "uvx yt-dlp LINK", or create one off-scripts with requirements in the file header, and not having to worry about managing virtual envs and still having access to the python ecosystem is so nice.

hah, knew I should have dug around more

This is cool, but is testing recognition, not recall. It needs an extra challenging mode where you have to provide the country, not multiple choice.

I enjoyed "No bullshit guide to linear algebra". And I wish "Coding The Matrix: Linear Algebra Through Computer Science Applications" still had the autograder working. Though I wonder if I could throw some agents at replacing it....

That's what I do[0]. I run a gauntlet of judges against the PR, each with a strict lane to check.

0: https://github.com/jacquardlabs/gauntlet

The New Atlantis, The New Criterion, The Hedgehog Review, and Garden & Gun. And then Stack magazine, and independent magazine subscription. They pick a different one from somewhere around the world and send it to you.

Increasingly not. We use CodeRabbit at work, which catches good stuff. And I have my own gauntlet that I run code through.

https://github.com/jacquardlabs/gauntlet

Working with agents generates a lot of markdown input and output. So I'm working on viva, a tool to help author and review docs.

You tell it what kind of doc you want, attach any necessary links/files/repo paths/etc, then it asks you clarifying questions until it has the data it needs. Then it authors a doc and give you a review interface. You can approve, request more info, request changes, make direct edits, etc. Then submit and makes edits until and represents until you approve all sections.

https://github.com/jacquardlabs/viva

It's funny that AI even gave us similar themes.

I'm working on a much smaller idea, but so far it's just me using it for grad school, and a friend using it for his master ciccerone prep. It has been really useful in the class I used it for while building it. Looking forward to playing with more as I start my fall semester(UIUC CS 425, Distributed Systems).

I need to get some model pricing evals in place to see if I can use open weight models to get it cheap enough, since it's just me and not VC money. The real product potential seems to be getting reusable materials like cert prep, continuing education for careers that require it, and the like. But then you're fighting incumbents that fiercely control their moats.

https://studyengine.app/

A lot of us spent substantial parts of our careers automating other folks out of jobs. But now that it's come for us, we're upset.

Yeah, my personal workflow has different reviewers for codebase(patterns, code cleanliness, etc), frontend, security, product fit, etc. So they spawn as separate subagents. Both so that they stay limited to their role, and so they don't have preconceived notions about the implementations. It's a bit heavy-handed but works for me.

Still working on Study Engine and Nomnominees(more or less done for now).

StudyEngine is a webapp I'm using while doing my masters in comp sci. I upload lecture notes, textbooks, papers, etc. It then extracts topics and tracks my mastery of them over time. It uses an LLM to generate questions and flash cards. It loops in some newer learning science ideas. It tests recognition first(multiple choice), and then once a level of mastery is matched, it switches to recall. Working on adding RAG to it, so I can surface where in the source material something can be reviewed when going over quiz results. Currently just for me an some friends. If can get a good eval set up, I might work on optimizing cost and seeing if it could be opened up.

NomNominees is simple webapp that tracks James Beard, Great American Beer Festival, Festival of Barrel Aged Beers, and other awards. I use it when I'm traveling to find places to check out. Even just a cluster on a map shows me neighborhoods I might want to check out.

https://studyengine.app

https://www.nomnominees.com

Building a small webapp to live on my home server to manage my history/science/philosophy/general knowledge podcasts. And then have it connect to sonos to create my own talk radio. Scheduling to auto-play whenever I want, usually 8am M-F. Play a news podcast first thing in the morning, then defer to others.

Paired with that, a MacOS app that detects when I'm on a zoom or google meet call to auto-pause the sonos, then unpause when the call ends.

Not who you responded to, but I've been working on cctx. It's an open source tool for analyzing claude code sessions to see where things went wrong(tool failure loops, bloated context, and the like).

https://github.com/jacquardlabs/cctx

On a Pixel phone, you can do Accessibility -> Color Mode

I have a service that runs on my home server and uses the Ubiquiti API to detect when I'm on a zoom call. It then pauses my Sonos network-wide. Unpauses when the call is over. The next step of it is to have it's own podcast library, so I can have my own little talk radio going on in the background all day.

Some point, I want to convert into a little app and open source it, so you can install on your laptop so it's usable by more people. And have it detect more than just zoom.

They're recommender systems already, which is AI-powered, so how exactly are they changing?

When making a PB&J, I want just enough to jelly to add a little flavor to the peanut butter. Which is why my dad always called them "choke sandwiches" when I made them.