Viewing profile — mips_avatar

It was inspiring watching the Gemini 3 pro team launch the model and bike away into the sunset never to launch anything again

Like I have a list of a few hundred osm places websites that are clearly scam sites. I should be going one by one and filing them manually but I found this via a spam filter and it…

I’m grateful that a principled group of people run OSM. Much like I’m grateful that a principled group run Wikipedia. But the rigidness has costs that I don’t think are being appre…

I appreciate OSM for maintaining a higher data quality bar than other projects (Overture places are mostly junk outside of USA), but it's also just artificially limiting itself by …

Would be interesting to see how fast it would be on 4x mac studio 512gb machines.

Ok but a task that works fine on qwen 397b can be finetuned on qwen9b. But in every case so far when building the eval for evaluating the traces I’ve discovered a better prompt tha…

The problem i've had with finetuning models is that most of the time better prompting beats finetuning

Problem is right now the biggest GPU boxes they have is single rtx pro 6000s.

I’m still kind of shocked that Dean Ball can tweet such incendiary stuff about OpenAI policy. Like presumably OpenAI would prefer it if their staff don’t pick fights with Trump adm…

I'm not sure it would be more fun, but you could probably ingest openstreetmaps data so it's actually a real manhattan

So like oftentimes the picture will be of a church and there’s geographic coordinates for where the photo was taken. My qwen will use the geocoder to search for “church” at the coo…

It's definitely being pushed more by the big labs recently, and it's interesting how they favor local hardware.

Maybe I'm slow but I didn't use them much until recently when Cursor and Claude Code made them a main part of the harness.

Very few people travel to visit the Amazon especially in Peru, Bolivia, and Ecuador. In the absence of tourist money these amazing ecosystems are being turned into agriculture and …

I’ve found it helps a lot with reconciliation tasks where tools like openrefine can’t handle it. Like I wanted to tag blog posts with links to Wikipedia articles that are relevant.…

The coolest project I’ve got this running on is improving the depicts metadata for photos on Wikipedia. A lot of times they won’t have the landmarks tagged correctly in a photo. So…

Qwen35ba3b can do a huge amount of data cleaning work on pretty modest hardware. Already have run about 100 billion tokens on it using 2x3090 gpus.

Well yeah Claude caching is frustrating. If implemented correctly subagents are really cheap.

One challenge/opportunity I've had is harnessing really wide running cheap agents. Any thoughts on how to move really cheap agents beyond basic summarization so we can go broader t…

even 8x rtx pro 6000 is only 768GB of VRAM. IDK how anyone is going to run k3

The more important question than subsidy is what is the tokenomics of running the model. If it's inefficient to run on an nvl72 cluster (or whatever the heck has enough vram to run…

It would be really interesting to redo the public benchmarks for kimi k3 but token normalize the costs. Ok so maybe k3 beats fable on terminal bench, but how many tokens did it use…

I'm a creative person so my brain requires that I make something every day. Sometimes I make stuff that isn't very good. I've been told a lot by former bosses and random people tha…