I updated my quantization compiler to use e-means as a replacement for k-means in codebook generation and got Qwen3.5-4B from 8.41 GB to 1.23 GB while retaining 91.9% of original performance which I think is approximately SOTA, at least comparable to bonsai 2 but I think we could go lower if someone wanted to donate some GPU time since this is just a hobby for me.
at this size, it's small enough that memory bandwidth isn't the bottleneck to decode speed so I'm interested in seeing how fast we can get larger models on consumer hardware. link below.
🚨 Voters in Harwood, ND REJECTED new restrictions on data centers by more than 3-to-1.
Now the mayor is taking apart the big fears:
"Water usage… not a problem. Power rates increasing… not a problem. Noise… not a problem."
And the data center will pay this town of 820 people $1.65 MILLION in property taxes by 2028.
Announcing /swarm, a new slash command in Google Antigravity for orchestrating specialized agents in parallel across the desktop app and CLI.
Turn a single prompt into a coordinated multi-agent workflow where agents plan, build, and verify together on a live message board, with the flexibility to mix and match different models for each role.
@JaelRuble take pictures of them on the shelf and have the ai list them out for you then have it create a digital catalog you can browse with book covers, synopses, read/unread statuses, notes, etc
Gemini 4 Carbon from @Google on ARC-AGI (Verified):
- ARC-AGI-3: 99.1%, $4.6K (provider adapter), 65.1%, $7.2K (standard harness)
- ARC-AGI-2: 94.2%, $0.38/task
- ARC-AGI-1: 98.5%, $0.16/task
Carbon beat its predecessor Argon by 18% points on ARC-AGI-3 in the standard harness.