Doing simple retrieval from LLM models at various context lengths to measure accuracy
active 2024-06-06 → 2025-04-05 (UTC)
Activity over time
Daily event counts in the loaded window
Line chart, 304 days from 2024-06-06 to 2025-04-05. Pushes: 38 total, peak 5 in a day. Pull requests: 0 total, peak 0 in a day. Issues: 20 total, peak 4 in a day. Comments: 11 total, peak 3 in a day. Stars: 0 total, peak 0 in a day.
- Pushes
- Pull requests
- Issues
- Comments
- Stars
Stars, PRs, issues and forks are under-captured in the later part of this window. GH Archive progressively stopped capturing non-push events during 2026 — −95% or worse by the end of the window. Every series here except Pushes fades for that reason, so a decline above reflects the archive, not this repository. Pushes stay reliable throughout, so read them, and the contributor counts derived from them, as the real signal. Data health has the measurements.
Top contributors
Pushes, PRs, issues, reviews and comments — stars and forks excluded, so this is contribution rather than popularity
Recent activity
Latest issues, pull requests and releases
- Issue#17Gomfa2024-07-13 01:19Enable multi-needle tests for Claude
- Issue comment#18Gomfa2024-07-04 18:46Extended exhaustive test runs
- Issue comment#18Gomfa2024-07-01 19:23Extended exhaustive test runs
- Issue#18Gomfa2024-07-01 19:23Extended exhaustive test runs
- Issue#12Gomfa2024-06-29 02:09Execute exhaustive test runs of AwarenessCLI and gpt-4o, analyze results
- Issue comment#17Gomfa2024-06-28 20:07Enable multi-needle tests for Claude
- Issue#17Gomfa2024-06-28 19:43Enable multi-needle tests for Claude
- Issue comment#12Gomfa2024-06-26 22:14Execute exhaustive test runs of AwarenessCLI and gpt-4o, analyze results
- Issue comment#12Gomfa2024-06-26 22:13Execute exhaustive test runs of AwarenessCLI and gpt-4o, analyze results
- Issue comment#12Gomfa2024-06-26 22:11Execute exhaustive test runs of AwarenessCLI and gpt-4o, analyze results
- Issue#11Gomfa2024-06-24 19:52Get the visualization code working over a small test run
- Issue#16Gomfa2024-06-24 19:22Change the needles to read "the password is <password>"
- Issue comment#15Gomfa2024-06-20 00:12Utilize --create-trainings and archive the resultant trainings.jsonl for awareness test runs
- Issue#16Gomfa2024-06-20 00:08Change the needles to read "the password is <password>"
- Issue#15Gomfa2024-06-20 00:05Utilize --create-trainings and archive the resultant trainings.jsonl for awareness test runs
- Issue#13Gomfa2024-06-19 22:26Understand and produce multi-needle test
- Issue#14Gomfa2024-06-19 21:53Bucket results by test configuration in the awarity_results directory
- Issue#14Gomfa2024-06-19 19:38Bucket results by test configuration in the awarity_results directory
- Issue#7Gomfa2024-06-13 02:59Write corpus fragments to disk for AwarenessCLI's consumption
- Issue#10Gomfa2024-06-13 02:59Call into local AwarenessCLI from the tool
- Issue comment#13Gomfa2024-06-12 23:55Understand and produce multi-needle test
- Issue#13Gomfa2024-06-12 23:55Understand and produce multi-needle test
- Issue#6Gomfa2024-06-12 15:51BLOCKING: AwarenessCLI should be able to return responses as a json file
- Issue comment#8Gomfa2024-06-10 22:28Add AwarenessCLI to project via requirements.txt
- Issue#8Gomfa2024-06-10 22:28Add AwarenessCLI to project via requirements.txt
Totals cover only the window loaded into ClickHouse and count events, not GitHub's lifetime totals — 0 stars here means stars gained during the window, not the repo's star count.