It depends. For example, if you translate using a Gemini model and then switch to another, you’ll be creating a new word cache. In my experience, I prefer to maintain three routes: two with the same model, and I’ve now activated a Gemini Flash Lite for new content. So far, no issues.
eisammy
(Sammy)
2
Gerelateerde topics
| Topic | Antwoorden | Weergaven | Activiteit | |
|---|---|---|---|---|
| Discourse AI Failing to translate large number of posts and topics | 8 | 230 | 10 november 2025 | |
| AI exceeds LLM token thresholds randomly and unpredictably | 3 | 63 | 6 mei 2026 | |
| Could we use LLMs to improve translations? | 0 | 390 | 20 november 2023 | |
| I need help to configure LLM DeepSeek R1 0528 - free for Automatic translations with Discourse AI | 34 | 616 | 4 januari 2026 | |
| AI translation backfill not working after all settings configured | 35 | 639 | 17 november 2025 |