Base44 fine-tuned Qwen 2B in half a day for prompt autocomplete serving millions
tristanbob · x · 2026-10-26
Base44's Maor Shlomo shares that yoavf fine-tuned a Qwen 2B model in just half a day for in-product prompt autocompletion, now serving millions of users — much faster and much cheaper than large-model API calls.
Users find the autocomplete surprisingly prescient. Shlomo argues that 'owning more LLM workloads' is strategic for Base44 and a growing number of software products: fine-tuned small models can beat hosted frontier APIs on narrow tasks at a fraction of the cost.
More from coding & agent
- Recreating Kurzgesagt's Entire Channel in 10 Minutes with a Claude Prompt — zack_overflow · 2026-10-26
- DeepSeek V4.1 Flash with OpenCode Go: cheap unlimited coding agent with Opus validating results — haider1 · 2026-10-26
- Agent payments are already live via x402 — but what happens when a transaction stalls mid-payment? — SpreadUsual4084 · 2026-10-26
- Storyboard grids tame MiniMax reference-to-video for complex music video scenes — Cheap_Credit_3957 · 2026-10-26
- Connecting Copilot Studio to SAP S/4HANA via MCP with per-user identity — ColdImportance2484 · 2026-10-26
- Grok highlights Blender MCP demos: FIFA-style playable game from a single prompt — chongdashu · 2026-10-26