tootyskooty
Joined 4 years ago
Karma
77
Submissions
52
Member since
May 15
Recent submissions
Comment · 6 months ago
I'm working on Repple (https://repple.sh)! It's a modern spaced repetition x incremental reading/PDF library app with a few (tasteful!) QOL AI features.
I've been using Anki for 10+ years and love it but always wanted something with a cleaner UX and a reader view. The recent Anki ownership change pushed me to finally make something, and it's seeing some traction :)
Right now I'm focusing on getting the reading and note-taking view to be nice. I used to use Polar Bookshelf (RIP) but that went away, trying to make something better.
The flashcard side also has a REST API btw!
Comment · 7 months ago
I'm building Repple (https://repple.sh), a free flashcard app with spaced repetition scheduling and some (tasteful imo) AI additions. I've been using Anki for 10+ years and love it but always wanted something with a cleaner UI and that's a bit easier to experiment with. The recent Anki ownership change pushed me to finally make something.
Added a REST API (https://repple.sh/developers) a few weeks ago so you can build on top of it. Decks, cards, reviews, etc.
Feature delta over Anki:
- Tab-autocomplete for text fields
- Automatic image-gen for image fields
- Optional rephrasing that changes wording each review to avoid pattern matching
- Basic PDF library & incremental reading support
- "Orphan" card detection; i.e. knowledge that isn't well connected
- ... + a bunch of other qol improvements like semantic search, etc.
Comment · 10 months ago
I'm wondering about this too. Would be nice to see an ablation here, or at least see some analysis on the reasoning traces.
It definitely doesn't wipe its internal knowledge of Crystal clean (that's not how LLMs work). My guess is that it slightly encourages the model to explore more and second-guess it's likely very-strong Crystal game knowledge but that's about it.
Comment · 10 months ago
See pretraining section of the prerelease_notes.md:
https://github.com/DGoettlich/history-llms/blob/main/ranke-4...
Comment · 10 months ago
Since it now includes 4 thinking levels (minimal-high) I'd really appreciate if we got some benchmarks across the whole sweep (and not just what's presumably high).
Flash is meant to be a model for lower cost, latency-sensitive tasks. Long thinking times will both make TTFT >> 10s (often unacceptable) and also won't really be that cheap?
Comment · 10 months ago
both have had questionable content for a while, it's a wonder people are still paying for them. especially given that LLMs exist (and youtube for that matter).
Comment · 11 months ago
Since no one has mentioned it yet: note that the benchmarks for large are for the base model, not for the instruct model available in the API.
Most likely reason is that the instruct model underperforms compared to the open competition (even among non-reasoners like Kimi K2).
Comment · 11 months ago
Shameless plug: if OP is looking to stay on d3, he could also try slotting in my C++/WASM versions[1] of the main d3 many-body forces. Not the best, but I've found >3x speedup using these for periplus.app :)
Comment · 1 year ago
Working on a new interface for learning with LLMs that creates courses on any topic.
The goal was to make the learning material very malleable, so all content can be viewed through different "lenses" (e.g. made simpler, more thorough, from first principles, etc.). A bit like Wikipedia it also allows for infinite depth/rabbit holing. Each document links to other documents, which link to other documents (...).
I'm also currently in the middle of adding interactive visualizations which actually work better than expected! Some demos:
Comment · 1 year ago
I've been getting a lot of vulnerability "spam mail" recently that's clearly AI-generated.
It's a surprise every public bounty program isn't completely buried in automatic reports by now, but it likely won't take long.
Comment · 1 year ago
would be nice to finally see multi-turn coding benchmarks. everything we have so far is single-turn and that's clearly not a realistic scenario.
Comment · 1 year ago
Hey, sorry for seeing this late!
You can send me a message on discord (dcbcdefb), or email (support (at) periplus dot app).
Also available on Twitter!
Contact: mato (at) gudelj.net