Show HN: Big-gulp-read – Pi extension for reading much larger chunks
Modern models support inputs up to 131k tokens in many cases. Pi default is overly conservative. This quadruples it but on many modern models you can set it up to 12x higher than the 50.0kb default (600kb).
Read original source
Source record
Recorded metrics
points · 1 votes
2026-11-14 21:57:50.543Z
cumulative since publication
Research analysis
What changed
Source account: Modern models support inputs up to 131k tokens in many cases. Pi default is overly conservative. This quadruples it but on many modern models you can set it up to 12x higher than the 50.0kb default (600kb).
Version & cost evidence
Source votes: 1 votes (Nov 14, 2026 UTC; cumulative since publication) Recent records to compare: “Show HN: In-browser object removal, 1s on WebGPU, photo never leaves your device” (Show HN, Nov 14, 2026); “Show HN: TriusLD – A Small Tokenizer for LLMs with Robust Multilingual Support” (Show HN, Nov 14, 2026). Shared themes are navigation hints; they have not been verified as the same need or independent corroboration.
Who is affected
Identify the existing workflow this change affects before recommending an upgrade. Launch attention does not establish improvement; an API, pricing or availability change may instead create migration work.
Missing comparison points
Missing checks: old versus new behavior, affected plans and regions, availability date, compatibility, rollback path and cost under the same workload.
Migration check
Save the release or policy notice, run the same task on the old and new option, and compare outputs and the full bill. For retirement notices, verify the deadline before scheduling migration.