Evidence for deploying compressed, governed AI.

Showing all 8 write-ups, newest first.

1. R-008
   10 October 2026 · Benchmark

   We compressed VoiceChat by 74% and made it run in real time on one card.

   NVIDIA’s VoiceChat is a speech model that can call tools while it talks. Tileward’s TWX4 build is an 11.5 GB file against 44.4 GB. It picked the right tool on 55 of 80 spoken requests, level with the original’s 52, and chooses the original’s next word 95% of the time. With Tileward’s serving changes VoiceChat runs in real time on one card. The build runs from unpacked weights, so its speed and memory there match the original’s.

   Model compressionQuality
   Experiment

   11.5 GB

   of file, against 44.4 GB as published

   55 of 80

   right tool on spoken requests, against 52 for the original

   72 ms

   for each 80 ms frame with our serving changes, against 114 ms for NVIDIA’s open code

   Take a look →
2. R-007
   8 October 2026 · Benchmark

   We shrank PersonaPlex by 62% to run at 20ms a frame.

   NVIDIA’s PersonaPlex speech model is 16.7 GB as published. Tileward’s TWX4 build is 6.3 GB, needs 20 ms for each 80 ms frame against about 40 on one laptop, and picks the original’s next word 96% of the time. A standard 8-bit conversion stays closer, at 8.2 GB.

   Model compressionQuality
   Experiment

   6.3 GB

   of weights, against 16.7 GB as published

   20 ms

   of compute for each 80 ms frame, against about 40

   96%

   of the time, the same next word as the original

   Take a look →
3. R-006
   6 September 2026 · Benchmark

   Keep most of the answer rate on 95% less context (19×).

   From a 1,986-question LOCOMO set, Tileward Context answered 55% of answerable questions with 1,499 tokens each; full transcripts answered 63–67% with 28,365. A separate model judged every answer, and on unanswerable questions Context made up an answer far less often.

   Conversation memoryLOCOMOToken costQuality
   Experiment

   769 / 41

   questions won and lost against keeping the newest turns

   95%

   less context than sending everything (18.9×)

   55% vs 63–67%

   questions answered, against sending the whole transcript

   Take a look →
4. R-005
   4 September 2026 · Benchmark

   Give agents useful context, not the whole backlog.

   Across 104 AgentBench tasks, Tileward Context solved 37 with 523,028 context tokens; full history solved 24 with 1,651,372. The 68% (3.2×) reduction is stable, but 14–19 tasks can flip between identical runs, so the repeated ordering matters more than a fixed 13-task margin.

   Agent workflowsAgentBenchToken costQuality
   Experiment

   37 / 24

   tasks solved with Context / full history, of 104

   68%

   less context than sending everything (3.2×)

   14–19

   tasks the same setup flips against itself

   Take a look →
5. R-004
   31 August 2026 · Benchmark

   Improve recall without losing correct answers.

   On 140 scored LongMemEval-S questions, one recall upgrade moved the same store and model from 67 correct to 81: 14 wrong-to-right flips and no reversals. This is one self-judged run, and the upgrade itself remains undisclosed.

   Conversation memoryLongMemEvalQuality
   Experiment

   +10.0

   points on LongMemEval-S, paired

   14 / 0

   questions fixed / broken

   9→16

   LongMemEval-S temporal-reasoning, of 40

   Take a look →
6. R-003
   28 August 2026 · Benchmark

   A smaller model should not become a different model.

   Across two model families, compression did not create new drift in sensitive record-copying behavior. Model selection mattered far more, while a paired knowledge test measured the actual trade-off at 0.40 MMLU points.

   Model compressionMMLUQuality
   Experiment

   26 of 30

   starved tokens shared across families

   0.0

   embedding difference after compression

   −0.40

   MMLU points, paired p = 0.021

   Take a look →
7. R-002
   28 August 2026 · Governance

   Put policy in front of the model, not inside the prompt.

   A pre-inference gate turns a policy from advice to an enforceable, auditable decision. We tested it with 2,251 requests written to evade the rule and 50 benign controls. The payoff is a boundary your team can test before depending on it.

   GovernanceQuality
   Experiment

   2,251

   adversarial cases

   50

   crossed the gate

   5 of 50

   benign controls refused

   Take a look →
8. R-001
   25 August 2026 · Benchmark

   Stop paying every agent to reread everything.

   Across six multi-agent problems, Tileward Context cut billable tokens by 72.1% against broadcast context, including ingest, and produced the strongest code in the run. Wide research fan-out exposed a retrieval boundary, so test that shape first.

   Agent workflowsToken costQuality
   Experiment

   ≈ 72.1%

   reduction in billable tokens

   0.968

   coding, best of four

   5.33

   research panel, last of four

   Take a look →

No research write-ups match that filter yet.