sligbad

1) I couldn't see it, is there any indication of if the qwen math improvement caused degradations elsewhere?

2) the negative result on making similar improvements in Gemma 3 270M is also fascinating.

Such an unexpected result...

"No human can go edit a brain to become better at math" -- I'd offer this is exactly what "learning math" is.

I know I'm being pedantic, and I understand you mean "edit" like "surgically", but it does still feel worth noting.

Orca was too heavy and, ultimately, too slow for me too keep using. Switched to herdr haven't looked back.

Calling people Nazis online ... and a state sponsored billion dollar surveillance program ... Are what you're choosing to equivocate?

This was great to read even if just to name the stuff that I find so irritating!

I have thoughts about this pedagologically. I think these kinds of tools can be helpful, but the number of rhythm students I have seen who need to break out of the dependence on a visual metronome is rough.

Part of the struggle is really listening to yourself, and learning how to pick up on your own mistakes.

I hope the tool is helpful, and I hope I don't sound too curmudgeonly when I say don't let the time making and maintaining tools for practice detract from the most important thing, the ur-tool of all learning: more practice.

(Ask me how I know! A common trap for programmers!)

Wow, this is is incredibly important temporal context.

I hate how the role of the human scientists involved is so diminished, with credit being given to "Claude," which is at best a family of products.

Well Kvrocks is on disk, not in memory.

This was really loud in my mind reading this post. It seems so obvious!

Same. I'm just happy sticking with them and am consistently impressed. Cost is so good and kind of keeps you honest.

Once read, I think from G Huntley, "pick a model and stick with it," they have been making that very easy, daily driver since V4.

Thanks for writing this up. The prose was really pleasant to read, a treat in this day.

I really like Deepseek Harness. It has some quirks but I like the flexibility and the web UI is solid. The self-configuration is pretty nice.

This is unfortunately exactly the kind of project I wouldn't want to trust my photo management workflow to...software is cheaper than ever, thoughtful maintenance and longevity is worth much more to me.

Not that Adobe's getting my money either.

Really refreshing read. This feels glaring in so many of these, and the methods to get things to "behave" of just slapping additional markdown prompts at various levels is both silly and ineffective.

Pro: it can be an excellent way to learn if you realize good problems don't come easy, many such cases where I abandon something having learned from it and that's life

Con: the machine will tell you you have easily found a good problem, and engineered the perfect and necessary solution, if you let it

If this is your takeaway, it's what you were looking to believe anyway...

I've seen some similar geohash-words stuff, this is super cool, thanks for sharing!

Also very cool: Google's S2 geometry - https://s2geometry.io/

Used by https://catch.astro.umd.edu/

Love the HEALPix scheme, super useful for indexing too (some similar characteristics to geohashes).