A 339 KB linear probe on a frozen general-purpose backbone: 0.7590 on the official ChestX-ray14 split, against 0.7451 fine-tuned.
Burton Lancaster PRO
RiverRider
AI & ML interests
Explainable AI
Recent Activity
posted an update about 22 hours ago
Your coding agent already has your files. It greps, misses, and answers anyway.
Sunstone indexes the folders you have open and gives whichever model you are already using, Copilot's Claude and GPT included, a proper way to search them. It also lets you put your own servers in VS Code's model picker, if you want to.
Everything is indexed and held on your machine. There is no account and no key to hand over.
https://marketplace.visualstudio.com/items?itemName=SunstoneNorth.sunstone posted an update 2 days ago
You are six miles in and the bars are gone.
Someone rolls an ankle on wet rock. Or there is a tick. Or the stream is silty and all you have is a filter and a cup.
If you loaded the tab before you left, the answers are still in your pocket.
https://blackwindow.xyz
Open it at home. Pick a model. Hit Load. Add it to the home screen.
Before you lose signal, drop in what you would actually need: a first-aid PDF, plant notes for the region, a map, a GPX, a meds list. The Weave indexes them on the device. Later questions pull the nearest passages back as notes.
After Load, the network can drop. The weights run in that tab, on that phone.
You can still drop new things in with no service. A photo of a plant, a rash, a trail junction. A voice note of symptoms. Audio is transcribed. An image is described. Both land in the Weave and you can ask about them there, offline.
It is a small model. Treat it as a checklist, not a doctor. It will not replace a beacon or a course. It will still answer when the map has no service.
Same trick on a plane, in a blackout, or with a file that should not leave the device.
Not a server with a policy. Your hardware, a window, a Load button.
Where would you actually use this? updated a dataset 3 days ago
RiverRider/swebench-localisationOrganizations
Read-outs on frozen models you can actually run. Nothing here fine-tunes the host.
-
SRT Omni Cross-Vendor Retrieval
🔀Search mixed-media index with text across AI models
-
ChestX-ray14 frozen probe
🫁1339 KB linear probe beats a fine-tuned ResNet-50
-
0.6B Reads 27B
🪟A 0.6B model in your tab searches a 27B model's index
-
One Model, Two Jobs
🪟A 0.6B model in your tab searches a 27B model's index
A 339 KB linear probe on a frozen general-purpose backbone: 0.7590 on the official ChestX-ray14 split, against 0.7451 fine-tuned.
One company's model searches another's index at a rate indistinguishable from native: retention 0.988, 95% CI [0.955, 1.023].
Read-outs on frozen models you can actually run. Nothing here fine-tunes the host.
-
SRT Omni Cross-Vendor Retrieval
🔀Search mixed-media index with text across AI models
-
ChestX-ray14 frozen probe
🫁1339 KB linear probe beats a fine-tuned ResNet-50
-
0.6B Reads 27B
🪟A 0.6B model in your tab searches a 27B model's index
-
One Model, Two Jobs
🪟A 0.6B model in your tab searches a 27B model's index