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 8 hours ago
Did you explain the same decision to a fresh chat for the third time this week?
Did you ask your coding agent where something is handled, only to watch it grep, guess, and answer from the wrong file?
Did you edit a function, only to have the agent quote back the version from before your edit?
Sunstone is a free VS Code extension built for all three. It indexes the folders you have open and gives whichever model you already use, Copilot's Claude and GPT included, a real search over them. Before every search it re-reads whatever changed: a save, an unsaved edit, a file written from the terminal, a branch switch. #remember keeps a decision across chats. It can also put your own llama.cpp or vLLM server in the model picker. Everything stays on your machine, with no account and no key.
We measured it on all 500 issues in SWE-bench Verified. It named the right file first 229 times. A text search over the same files managed 58, and questions shuffled onto the wrong issues got 5. Every ranked list is published.
https://marketplace.visualstudio.com/items?itemName=SunstoneNorth.sunstone posted an update 2 days 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 3 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?