Skip to content
MindPattern
Wire
Briefings
Search
Subscribe
← The Wire
Source trail
patrickmccanna.net
Public MindPattern findings, entities, and graph evidence that cite this source.
Findings
1
All-time hits
1
High value
0
Last seen
2026-09-15
Related findings
2026-09-15 / SOURCES
Moving a 35KB preprompt from Opus to self-hosted Ollama burned 14% of context before the first turn
Patrick McCanna's notes, published 2026-09-13/14 and now on the HN front page, document a migration onto a 128GB AMD Ryzen AI MAX+ 395 with 96GB for inference and a 65k context window, where the 35KB preprompt consumed 14% of context immediately and left almost nothing for session history. The failure mode was thrashing, not refusal: within about three minutes the model repeated tool calls, re-read files it had already read and rewrote finished work. His fixes are concrete enough to copy, splitting preprompts into single-objective units, using declarative opencode agents over shell scripts, setting context length explicitly since Ollama's defaults are too low, and logging session state to disk for handoffs.
Open latest cited source
Wire
Briefings
Search
Subscribe