autocomplete

作者开源了一个类 Cotypist/Granola 的桌面应用 LokalBot，利用本地 Gemma 4 E2B（6bit 量化）基于自有会议记录实现约 50ms 延迟的打字自动补全，并在 782 个预测点上对比 Cotabby 取得略优表现。

OpenAI announces that composer predictions in Codex are now in beta for Pro users, allowing Codex to suggest the next message based on conversation context and the user's writing style.

This paper proposes a compression scheme for byte-level tokenization using an autocomplete model to remove predictable bytes from input sequences, reducing sequence length while maintaining machine translation performance across diverse languages.

LokalBot is a fully local macOS app that runs AI models on-device for meeting transcription and summarization, autocomplete in any app, and day tracking, with full privacy and no cloud dependency.

An opinion piece arguing that reliance on AI autocomplete tools is degrading developers' skills and critical thinking, highlighting the hidden costs of mandated AI assistance in software development.

The article explains how the author achieved p99 zero-millisecond perceived latency for autocomplete on 240 million domain names by prefetching suggestions on keyDown and caching, with a fast API built on Tranco and CZDS data.

A user discusses building a small autocomplete model (25M parameters) as a learning project, mentions hardware constraints (32GB VRAM), data requirements (~100M tokens), and seeks advice on datasets and data formatting for autocomplete-style training.

This paper introduces RelGT-AC, a relational graph transformer architecture tailored for autocomplete tasks in relational databases. The model extends the RelGT architecture with column masking to prevent trivial solutions, a unified task head for multiple prediction types, and a TF-IDF text encoder to leverage lexical signals, achieving significant improvements over baselines on RelBench v2 benchmarks.

Personal update on hardware water damage recovery, showcasing MLX-VLM serving Qwen3-4B-Instruct locally on an RTX6000 Pro at ~300 tok/s for autocomplete and git commit generation via Zed IDE.

A technical guide on setting up local LLM autocomplete (Qwen2.5-Coder-7B) and agentic coding (Qwen3.6-35B-A3B) on a single 16GB GPU with 64GB+ RAM using llama.cpp, including commands and performance benchmarks.