Comments URL: https://news.ycombinator.com/item?id=48899600

Points: 1

# Comments: 0

Been inspired by a few posts I've seen recently here on HN featuring naval combat games, but wanted a twist.

Made with 100% vibes.

Comments URL: https://news.ycombinator.com/item?id=48899593

Points: 1

# Comments: 0

Comments URL: https://news.ycombinator.com/item?id=48899418

Points: 1

# Comments: 1

Comments URL: https://news.ycombinator.com/item?id=48898836

Points: 1

# Comments: 0

Fleetdeck is a local daemon and a UI that runs on 172.0.0.1:4711, every session on the machine appears with a callsign and a column (queued, working, needs-you, iddle) all is derived using claude code hoojs, so now i can have a site that i can run in a second monitor and quickly see is any sessions needs my input or is done for me to go review the work or the plan.

you can even launch more sessions from the ui, and they go directly to a tmux window.

you can manage worktrees, and even open the terminal view directly from the ui.

the big choice i made here, is this does not forces a workflow, its just a claude session, you work however the hell you want to, i wont impose anything, the core makes zero use of ai, is just good old deterministic plain code and sql.

Comments URL: https://news.ycombinator.com/item?id=48898736

Points: 1

# Comments: 0

Nothing fancy but it does creates publicly shareable reports for your agent runs

Comments URL: https://news.ycombinator.com/item?id=48898280

Points: 1

# Comments: 1

Comments URL: https://news.ycombinator.com/item?id=48898244

Points: 3

# Comments: 0

Comments URL: https://news.ycombinator.com/item?id=48898189

Points: 2

# Comments: 0

There are services that transcribe music from Youtube videos into tabs, but they never work well enough for me. Instead I'm taking a simpler approach. It downloads the video, samples frames, uses Claude vision to locate the tab region, crops every frame to that region, de-duplicates the crops by the bar number printed on each line of the score, and stitches the distinct tab lines vertically into a PDF.

I didn't test it on a lot of different Youtube videos yet, so problem will arise for sure.

Comments URL: https://news.ycombinator.com/item?id=48898154

Points: 31

# Comments: 23

Comments URL: https://news.ycombinator.com/item?id=48898071

Points: 11

# Comments: 3

Comments URL: https://news.ycombinator.com/item?id=48898048

Points: 2

# Comments: 0

With down time on a warm beach during a heatwave, cool salty water giving me fresh ideas, I had an idea: what if we used Coiled's Geospatial benchmark discussion as a comprehensive overview of geo and climate queries. Are all of these common operations secretly relational, just with the wrong data model? Using Claude Code on the beach, I can confirm that this seemed to be the case: Claude and I publish a benchmark that illustrated how every common operation in geo and climate sciences (at the 100 TB range) were actually secretly relational operations: https://github.com/xqlsystems/xarray-sql/blob/main/docs/geos....

Most surprisingly of all, from these examples was that a core operation, regridding, was just a sparse matrix-vector product. Claude had pointed out to me that in this data model, matmul was just a `SUM(val * val) ... JOIN .. GROUP BY`. This has a direct parallel to einsum notation, but can be expressed in (arguably) elegant SQL syntax! This capability seemed to be greater than the sum of it's parts.

Back in the cool water of the Ionian, I thought about the implications of this more deeply. I reflected that, all of the Coiled benchmarks did, deep down, was _post process_ simulations that happen in numerical/array code. Why couldn't these physics calculations be push down into the database also, if we could so matmul in SQL? Then it hit me: maybe they could, if in addition to linear algebra, if SQL could do calculus! https://bsky.app/profile/al.merose.com/post/3mpbods7wts2y

Later on, I implemented autograd on top of DataFusion's visitor pattern based on JAX's implementation. In my simplified array model, it turns out that we only care about partial differentiation on the diagonal of the Jacobian, meaning that `grad()`, `jvp` and `vjp` are just row-wise operations! I then implemented a common physics calculation from the coiled benchmark that required gradients. From here, I realized if I can autograd in the database, why can't I create a neural network?

As I came back home, I created some slides, and presented this work to DataFusion's inaugural showcase: https://www.youtube.com/watch?t=1511&v=5o-4hL8vGPw&feature=y... I realized in this synthesis that SQL is not necessarily a toy language for writing neural networks, but in fact, may be highly desirable in the future due to the fundamental principles of relational databases: the logical layer should be independent from the physical layer. If that property holds, and a neural network is a series of relations, could we create a SOTA distributed system for training more easily? For example, if we had one global logical plan of dataflow, could we better distribute work on 1000+ GPUs?

Several scientists and engineers and I are working together to explore this weird world of relational arrays at https://xql.systems (discord link at the bottom if you want to get involved).

Comments URL: https://news.ycombinator.com/item?id=48897975

Points: 34

# Comments: 8

Comments URL: https://news.ycombinator.com/item?id=48897969

Points: 9

# Comments: 7

Comments URL: https://news.ycombinator.com/item?id=48897963

Points: 1

# Comments: 1

Comments URL: https://news.ycombinator.com/item?id=48897934

Points: 1

# Comments: 3

Comments URL: https://news.ycombinator.com/item?id=48897784

Points: 1

# Comments: 0

Comments URL: https://news.ycombinator.com/item?id=48897683

Points: 1

# Comments: 0

Comments URL: https://news.ycombinator.com/item?id=48897554

Points: 3

# Comments: 0

Comments URL: https://news.ycombinator.com/item?id=48897459

Points: 1

# Comments: 0

My own Chinese language study stack used to be Pleco (and Goog Translate) for dictionary lookups, and then Anki for flashcard reviews, with a lot of manual copy-pasting in between. Which worked... okay. But the two sides never talked to each other. Pleco doesn't know what I'm studying, and Anki doesn't know anything about Chinese. So it treats 好吃 and 好 as totally unrelated cards, even though getting one right obviously tells you something about the other.

So I built duiduidui! (对对对), which is basically those two tools fused together, with a study engine that actually models how Chinese is structured:

- A dictionary with 200k+ entries, always available/searchable offline (characters, words, phrases, sample sentences, speech audio) where everything is linked. Every character links to the words it appears in, and the radicals it's built from, so you can (for example) go down a rabbit hole exploring the water radical 氵and the characters that contain it (汤 soup, 海 ocean, 河 river, etc). It also includes lots of modern/internet slang entries, not just textbook vocab.

- From the dictionary, you can put any record in your favorites (star collection) and add it to your flashcard deck. Looking something up while watching a show or texting a friend, and then studying it later are all the same workflow.

- Compositional mastery tracking. This is the part I'm most proud of (and that I think the HN crowd will find most interesting): when you correctly review a full sentence like 我喜欢吃猪肉, the system propagates partial "implied evidence" down to 喜欢, 吃, 猪肉, their characters, radicals, etc (weighted by difficulty) and kept deliberately separate from direct evidence. The goal is fewer redundant reviews without the system fooling itself.

- No fixed "learning course". The app keeps an ongoing estimate of your skill-level, and then shows you new material at the frontier of your abilities. But you can always wander off and study whatever you want, driven by your own curiosity or your teacher/class's lesson plan.

Personally, I study with a teacher (on preply), so I designed this app to supplement classes and tutoring, not to replace them. The app even has social features, so you can share your detailed progress with your teacher, and they can see how you're progressing.

The full mathematics behind the study engine are published on our website:

https://duiduidui.app/en/math/

The app uses a Bayesian proficiency model, with kalman filtering (for managing observations in a noisy domain). This is deliberaly not strictly an SRS app, but the card-selection logic is heavily inspired by the ideas of spaced repetition, while managing cognitive load. If you're an SRS nerd, I would genuinely love to hear what you think.

iOS only for now, with paid subscriptions priced at $12.99/mo or $89.99/yr. No ads, no engagement-bait, not based on streaks or other gamified bullshit... Just my own ideas about what would make an awesome Chinese app.

If you try it, I'd love to hear what's confusing, what's missing, etc... And if you just want to argue with my math, that's welcome too. 谢谢!

Comments URL: https://news.ycombinator.com/item?id=48897393

Points: 1

# Comments: 0