karl
|
f84fe0a3f2
|
Add bounded exact-byte document extraction protocol and transport
|
2026-10-13 14:49:21 +02:00 |
|
karl
|
99076d4b13
|
Define concrete document parser isolation rollout and invariants
|
2026-10-13 14:42:40 +02:00 |
|
karl
|
c8e611081f
|
Verify preview admission bounds under contention and worker unwind
|
2026-10-13 14:38:24 +02:00 |
|
karl
|
ec75a52cf7
|
Clarify remaining native playback validation scope
|
2026-10-13 14:34:46 +02:00 |
|
karl
|
f59c7ffb6e
|
Record Linux native preview and desktop suite results
|
2026-10-13 14:34:28 +02:00 |
|
karl
|
6c34962ced
|
Offer explicit retry after media preview loading failures
|
2026-10-13 14:29:49 +02:00 |
|
karl
|
f7f67afff9
|
Allow explicit retry of failed native preview preparation
|
2026-10-13 14:27:58 +02:00 |
|
karl
|
370db7e791
|
Bound native media preview capabilities and source range reads
|
2026-10-13 14:22:19 +02:00 |
|
karl
|
4b0b5ebfd9
|
Apply image preview limits to detected format instead of extension
|
2026-10-13 14:10:45 +02:00 |
|
karl
|
6ed3366d03
|
Publish Windows 0.1.2 download and verified release evidence
|
2026-10-13 14:07:15 +02:00 |
|
karl
|
268637b4ae
|
Record isolated CPU package checks for desktop 0.1.2
|
2026-10-13 14:04:56 +02:00 |
|
karl
|
7c7cecb5ab
|
Reject incomplete AI completions before showing generated answers
|
2026-10-13 13:59:22 +02:00 |
|
karl
|
8c005f5f57
|
Record current Google CPU incremental and prepared reader checks
|
2026-10-13 13:57:23 +02:00 |
|
karl
|
66bf7d7b47
|
Keep real model benchmark validity checks active under optimization
|
2026-10-13 13:54:33 +02:00 |
|
karl
|
d568bdb2b1
|
Measure genuine CPU query startup first input and warm latency
|
2026-10-13 13:53:03 +02:00 |
|
karl
|
6e7616b6d3
|
Record actual 100k lexical index performance on Windows CPU
|
2026-10-13 13:51:21 +02:00 |
|
karl
|
59908adfa6
|
Validate gated Google retrieval and record unchanged localization quality
|
2026-10-13 13:49:23 +02:00 |
|
karl
|
af04cec27c
|
Measure complete CPU gated transcription and component costs
|
2026-10-13 13:47:23 +02:00 |
|
karl
|
f827df11c6
|
Verify VAD allocation limits and decoder overshoot contracts
|
2026-10-13 13:44:06 +02:00 |
|
karl
|
7a6ab9fc6a
|
Measure real CPU VAD on complete frozen media pool
|
2026-10-13 13:41:57 +02:00 |
|
karl
|
bc47e14971
|
Add bounded CPU VAD diagnostic with real model contract tests
|
2026-10-13 13:39:04 +02:00 |
|
karl
|
37bb6a6e0e
|
Record CPU VAD build and audited timestamp failure traps
|
2026-10-13 13:35:45 +02:00 |
|
karl
|
4a7c4acdcb
|
Prepare inspected static Metal runtime inventory for macOS staging
|
2026-10-13 13:26:16 +02:00 |
|
karl
|
07bbcb76e8
|
Reject stale native runtime build provenance before release staging
|
2026-10-13 13:04:58 +02:00 |
|
karl
|
8f5b3ef155
|
Publish verified Ubuntu 24.04 headless preview and user setup guide
|
2026-10-13 12:48:02 +02:00 |
|
karl
|
baf59ba452
|
Preserve Linux archive failures and require current query-role runtime
|
2026-10-13 12:41:27 +02:00 |
|
karl
|
a8080f061f
|
Support reproducible XZ Linux archives without changing runtime contents
|
2026-10-13 12:31:17 +02:00 |
|
karl
|
193ab08f62
|
Evaluate frozen relevance hypothesis once on held-out Google CPU queries
|
2026-10-13 12:23:31 +02:00 |
|
karl
|
e7245fe15e
|
Freeze calibration-derived document and code relevance hypothesis
|
2026-10-13 12:17:37 +02:00 |
|
karl
|
06eec103f6
|
Document published Windows 0.1.1 and verified release artifacts
|
2026-10-13 12:14:48 +02:00 |
|
karl
|
ac02da724e
|
Record optimized WSL verification of GLib iterator backport
|
2026-10-13 12:05:46 +02:00 |
|
karl
|
d6c20a5268
|
Publish optional Windows CLI download and agent setup guidance
|
2026-10-13 12:02:09 +02:00 |
|
karl
|
3427abfd0f
|
Verify genuine Google CPU hybrid MCP from Windows archive
|
2026-10-13 11:59:33 +02:00 |
|
karl
|
3a336ca948
|
Verify extracted Windows CLI through actual MCP search and citations
|
2026-10-13 11:57:08 +02:00 |
|
karl
|
2be6b3d2b4
|
Support optional CLI and MCP in Windows source archives
|
2026-10-13 11:55:16 +02:00 |
|
karl
|
4e277a107f
|
Validate shared-engine lexical performance harness on Windows
|
2026-10-13 11:51:25 +02:00 |
|
karl
|
fb8b45dcc9
|
Prevent duplicate desktop model sessions and record calibration evidence
|
2026-10-13 11:43:20 +02:00 |
|
karl
|
8498c5401c
|
Record published Windows download and local installation
|
2026-10-13 11:28:24 +02:00 |
|
karl
|
eabb1fbb54
|
Publish first usable Windows release instructions and validation
|
2026-10-13 11:20:23 +02:00 |
|
karl
|
8ef874c609
|
Backport official GLib iterator safety fix for Linux desktop
|
2026-10-13 10:35:50 +02:00 |
|
karl
|
43c43ebdc9
|
Add shared-engine calibration-only relevance diagnostics
|
2026-10-13 10:25:35 +02:00 |
|
karl
|
4e60038c2f
|
Freeze independently reviewed relevance calibration corpus
|
2026-10-13 10:15:32 +02:00 |
|
karl
|
b6dd973a88
|
Record native semantic activation timing retest
|
2026-10-13 10:12:25 +02:00 |
|
karl
|
981991bac0
|
Add configurable native glass window backgrounds
|
2026-10-13 10:12:25 +02:00 |
|
karl
|
19d949fd13
|
Measure semantic activation refresh independently from download and idle time
|
2026-10-13 09:56:34 +02:00 |
|
karl
|
9aae3f8216
|
Prepare text search during media setup and retain query sessions through promotion
|
2026-10-13 09:27:40 +02:00 |
|
karl
|
af6ce29125
|
Validate complete speech decode windows and retain rejected ASR output
|
2026-10-13 09:03:20 +02:00 |
|
karl
|
e28e20af38
|
Preserve explicit code candidates and expose verified model asset milestones
|
2026-10-13 08:47:41 +02:00 |
|
karl
|
6e05227f53
|
Record real Google mixed retrieval baseline and remaining quality failures
|
2026-10-13 08:36:31 +02:00 |
|
karl
|
af7a40c183
|
Prepare bounded speech diagnostics and document mixed routing risks
|
2026-10-13 08:26:01 +02:00 |
|