momojo

The more I ponder this, the more I wonder: They're always after higher, more signal-rich tokens. What could be more rich than its own weights?

As someone with friends in the mathematics community, they've expressed similar sentiments.

I have to wonder if this is the equivalent of teleporting back in time and finding Marco Polo or any of those early explorers who traveled for the love of the game (and fame and money), and opening up Google Maps on your phone and showing them the zoomed out world. And showing them any island or village they could name.

A factor I don't see mentioned that I think is relevant: Repricers

Google "FBA repricer" and you'll find companies like https://goaura.com/ and https://sellersnap.io/.

These are a must for any mid-size seller. Their goal is to pretty self-explanatory; reprice your ASIN, live, to hit maximum sales. If your competitor is selling the same mug for $10.00, the repricer sees that and immediately reprices your mug for $9.99.

Its one of those "Well, if I don't use one, others will" situations.

Thank you for replying. Yes I also think its lame that we have to use the "YC" sticker or "SF-based" heuristics to determine a company's validity but we live in world full of snake oil and vaporware and signal:noise nowadays is crazy high.

Props to you for going out and making things happen but given what I know about your company from your

a) claude-coded website b) faceless twitter

most people or investors would conclude you're a bot at best, a scam at worst.

I don't say any of this with condescension (on rereading my first post, I'm sorry if the tone was harsh).

Thanks to whoever posted this 11yo gem. I've never read it. Its humbling and encouraging to see someone willing to post his fumblings even in his 50's. I feel like he'd been lambasted or mocked had he posted this today on substack or twitter.

As a younger man I was more of the "Just say what you mean, get straight to the point" kind of guy. I think what changed for me is that I learned that people are often much more interesting than their opinions. Going to someone wanting one-word answers to everything (outside of a work context) can become very impersonal and extractive. Its reductionist. It's assuming you're the only one with deep thoughts, conflicted feelings on certain topics, and interesting opinions.

They don't even do the robotics, they just do the data gathering.

How is this on the front page? Its not a YC company. They have no internet presence besides a Claude website. 0 followers on X/twitter. No public mentions of funding or votes-of-trust. No names to vouch for them.

Can OP or founders comment?

1. What's the node + aws story? Did you stick with aws or stay but try a different serverless tech? 2. Is lambda/serverless overhyped? I'm worried about reaching for it too soon.

I'd also add that they're hoping Jevon's Paradox also leads to a whole new segment of users who would have never reached for a classifier in the first place, given the barrier to entry.

> "[I don't understand what it's actually doing under the hood, or why we should be excited.] Jev feels more and more like a glorified if/else block"

You should be excited because there's so many low-hanging classification problems (e.g. "Is this email spam?", "Is this yelp review happy or sad or neutral?") that a "cheap" LLM is overkill for. It really should be this cheap, and now Jev is the first to do it well and do it at scale.

If I was explaining it to my mom, I'd say "Classifying 1000 yelp reviews used to cost $50. Now it costs 5¢, at similar accuracy"

This is one of those masterpieces that I'm surprised hasn't been scooped up by Netflix and turned into a movie.

Its not that I don't like it as a game, but it's just so chock full of character.

The premise alone is so compelling; in the Land of the Dead, even dead men chase money. Even with the literal afterlife a train ticket away, you have conmen and good guys living (or dying?) like there's no end of the line.

Love it. One of those rare pieces of art that continues to live in my head rent-free.

I don't think this is a perfect analogy, but i think it's closest to the original articles declaration.

I wish they had stayed this as the very first paragraph.

Maybe I'm too stupid to grok the original declaration. Does anyone have a better summation?

Cellpose[0] and Stardist[1] are the two you'll see most heavily run and talked about on the forums[2]. They're classic CNN's, but it just feels like they (and any modern models) are swept up in "Go out and buy a 4090.But these guys will give you plenty of mileage before you have to reach for the bigger ones.

[0] https://github.com/mouseland/cellpose

[1] https://github.com/stardist/stardist

[2] https://forum.image.sc/

> The world ships more than a billion capable phones, tablets, and laptops a year, most with a chip built for exactly this work, paid for and idle most of the day. Run the model there and the economics flip: no per-call cost, no round-trip, and nothing leaves the device.

This. I run small models (>50MB) for bio-imaging/biotech applications, it feels like every README implies that you need a discrete GPU to get started. While some do, many, especially the most useful ones, do not. Sure it matters if you're also going to do fine-tuning, but I believe your typical user just wants to detect some nuclei and get some cell-body ratios.

The laptop on your desk won't be running Meta's SAM, but it has more than enough compute to crunch 100's of your H&E slides overnight.

Anyone here use Mercury 2.0? Curious what your experience with the model is.

Same. Love oneshotting or sanity checks. Which fortunately is a lot of my workflow (lot of long tail stuff fits in one prompt).

Love this take. In the bio-imaging space, Napari is a great example of this. Wonderfully solid base, but extremely extensible since its just python all the way down.

There's something wonderful about having my coworker walk up with an issue, and being able to bang out a Napari plugin that solves their exact problem before lunch.

My order of 'tool escalation' usually goes: - Can I solve their problem from napari's inline terminal? - Can I solve it with a one-off script? - Can I solve it with a one-off script that creates a one-off plugin interface? - Should I add the plugin to our company-wide repo since this problem seems to occur a lot?

Did you get the grant? Are you under NDA? What was the innovation?

I'm in biotech and if I had a dollar for every engineer I've met who dreamed of or worked-at-a-place-that-tried or even tried-in-their-freetime to make a non-invasive glucometer, I'd have at least enough to buy a coffee, which is a lot.

There is an ever-growing bodycount in the NIO-GM graveyard [0], but I too hope that one day, it'll get figured out. My old roommate and good friend was T1 and monitoring one's glucose and remembering not to eat too much/little is half your life.

[0] https://pmc.ncbi.nlm.nih.gov/articles/PMC8655290/

Ditto on the lovelyness of single-file, zero-dep, standalones. In my day job I'm stripping out hundreds of megabytes from one of our main docker containers, but running into little projects like this that make me smile. Beautiful

Why not use Numba? In my mental model they achieve the same win, generating GIL-free, bytecode-level perf.

I'm not super familiar with JAX though.

Good question.

I'd stick with the venv if it's heavy duty crunching and you do it often.

However, if this is a one off or doesn't need heavy compute, and you don't mind waiting a little longer, use the notebook.link.

This is awesome! For those here not familiar with Numba, it helps bridge that performance vs ergonomics tradeoff that's always existed when you reach for python over a lower level but faster lang like C or C++.

Sure you could write Cython but then you have to have a build step and make wheels for every platform you and python version. Sure numpy has gotten faster over the years but you're still hampered by the GIL.

Numba is a little magic because you get to write stuff that feels like numpy, but get literal bytecode perf.

BUT there's a cost to this, which u learned the hard way when I imported a color map extension for matplotlib recently.

I thought i was going to be importing a couple megabytes at most. But Numba+llvmlite alone is almost 100MB!

This might be a drop in the bucket in some applications but for a color map library that has only two hot paths that need to be JITed, it's excessive.

Overall though, love this achievement, and i love what's being done for in-browser (aka local-first) scientific computing!

I love bezier curves. In community-college, it was the first time I ever encountered a subject that made me want to go do more research on my own. One of my core memories is toiling away for multiple nights when the rest of the house was asleep on my 2015 Macbook Pro, writing janky p5.js code and pressing refresh on the browser page over and over until suddenly, I started see real, beautiful curves blossom from my control points.

I just went back to dig up some old sources[0], and I can't believe this post is almost a decade old now. This guy's explainers and animations were leagues beyond any other resource I could find through Google searc at the time.

[0] https://jamie-wong.com/post/bezier-curves/

Reminds me of this: https://www.geoffreylitt.com/2025/07/27/enough-ai-copilots-w...

I think this is such a great reframing. It makes so much sense; I need an AI that acts more as a HUD and gives me superpowers, not just a copilot that can tell me when I've misspelled a word.

Do you have any examples of the second class?

The brokenness of man? Sin?

Did anyone else experience a change in verbosity? I've been playing around with an agent that holds your hand in a Jupiter notebook and it felt like it started writing essays versus nice, concise, helpful paragraphs like before. My gut was correct because I checked my Deepinfra usage and it was almost a 2x out-token usage for every in-token.

Not a huge deal since it's still cents per session, but my bigger issue was the weird change in tone. It became a lot more pretentious and over-explanatory.

Heavy prompt reworking helped but maybe that's just the cost of being better at coding and ARC-AGI?

I'm intrigued! There's so much movement in the sandbox space. Can someone tell me how a V8 sandbox compares to say Fireworks or if they've chosen one over the other? I think, from a technical standpoint, that it's neat that we already have an entire sandbox in the browser (albeit with a bit of chrome) but someone tell me why it shouldn't be used that way