Don't Classify, Hallucinate! Using Vector Embeddings to Match LLM-Generated Tags
Score
69提供新颖的标签匹配思路，具有启发意义。
内容清晰，有示例，但篇幅较短，深度有限。
可直接用于实际标签系统，可操作性强。
发布日期为2026年8月14日，但相关技术仍然有效。
Simon Willison是知名开发者博客作者，信息可靠。
Base 77 × T2 Source weight ×0.9 = 69
Curation line 70Below curation line
Why selected
Highly practical, with concrete methods and examples, offering strong reference value.
AI commentary
「The essence of this post is reverse thinking: instead of asking the model to classify, let it be creative and then use vector search to converge. This is especially useful for content platforms maintaining large tag taxonomies. I particularly appreciate the tip of including tag shape examples in the prompt, which greatly improves the mapping of hallucinated tags.」
Quick overview
Simon Willison shares a clever technique for tagging blog posts: instead of asking an LLM to choose from an existing list of tags, let the model freely "hallucinate" possible tags, then use vector embeddings to match those hallucinated tags to the closest real tags in the existing corpus. This solves the problem of having too many tags to feed directly into an LLM, and includes an example prompt to help the model generate tags in a similar shape. It offers a new approach to content classification and tag management.
- When there are too many tags to feed directly into an LLM, let the model "hallucinate" tags first.
- Use vector embeddings to match hallucinated tags to the closest existing tags in the corpus.
- Doug Turnbull's example prompt includes examples of the tag shape to help the model generate more useful tags.
- This approach applies to any scenario needing to map free text to a controlled vocabulary.
Full text
Doug Turnbull has a neat solution. Tell the model to output tags without any details of the existing vocabulary, then use vector embeddings against the existing corpus to find the concrete tags that are closest to the ones the model imagined might fit!
His example prompt suggests including an example of the shape of your tags to help the model make a more useful guess:
Your task is to create novel, never seen before, furniture, home goods, or hardware classification that best fit a search query.
Product classifications might look like:
Furniture / Living Room Furniture / Coffee Tables & End Tables / Coffee Tables
Décor & Pillows / Decorative Pillows & Blankets / Throw Pillows
Furniture / Bedroom Furniture / Dressers & Chests
Kitchen & Tabletop / Kitchen Organization / Food Storage & Canisters
School Furniture and Supplies / School Furniture / School Chairs & Seating / Stackable Chairs
Baby & Kids / Toddler & Kids Bedroom Furniture / Kids Beds
Here's the query to generate classifications for:
brown coffee table
Tags: search, ai, generative-ai, llms, embeddings, doug-turnbull
Related items
FeaturedDeepSeek V4 Doubles Token Share on OpenRouter, Driven by Agentic Workloads
DeepSeek V4 在 OpenRouter 上的代币份额翻倍，智能体工作负载成主要驱动力
The rapid adoption of DeepSeek V4 signals a strong market preference for high-performance, low-cost inference models, especially as agentic use cases reshape AI deployment.
91
FeaturedEnabling Two Settings Triples ARC-AGI-3 Benchmark Scores
启用两项设置使ARC-AGI-3基准测试分数提升三倍
This finding is crucial! It shows that model performance depends not only on training but also on inference-time configuration. For AI engineers and researchers, this is a must-know optimization direction. Teams deploying models on resource-constrained devices in particular could find a low-cost way to boost capabilities.
91
FeaturedGPT-5.6: Fusing Frontier Intelligence with Frontier Efficiency
GPT-5.6：前沿智能与前沿效率的融合
This news is worth watching as it marks a shift from pure parameter scaling to efficiency competition. For AI developers and business decision-makers, GPT-5.6 means higher performance at lower cost, especially for long-context or agentic tasks previously hindered by inference expenses. OpenAI's move may redefine what 'frontier' means.
91
FeaturedLFM2.5-Encoders: New Models for Fast Long-Context Inference on CPU
LFM2.5-Encoder：面向CPU快速长上下文推理的新模型
This blog post catches my eye because it directly solves the pain point of running long-context LLMs on CPU. For teams or individual developers without high-end GPUs, the LFM2.5-Encoder series offers a ready-to-use open-source solution. Highly recommended for those working on RAG, document search, or code analysis—now a standard server can handle million-token documents.
91
FeaturedGPT-Red: OpenAI Automates Red Teaming via Self-Play to Boost Model Robustness
GPT-Red：OpenAI通过自我对弈实现AI红队自动化，提升模型鲁棒性
GPT-Red marks a milestone from human to automated red-teaming—essential for safety engineers and alignment researchers. While reducing cost, it also raises ethical questions about automated attacks, worth pondering for everyone in AI governance.
91
FeaturedOpenAI Launches GPT-5.5 Bio Bug Bounty Program
OpenAI推出GPT-5.5生物漏洞赏金计划
This program deserves attention as it pioneers the extension of AI bug bounty to biosecurity, offering a new research direction for the security community and a practical training ground for AI risk governance. It is particularly important for model safety researchers, biosecurity experts, and practitioners concerned about dual-use AI risks.
91
FeaturedvLLM Introduces Native-Speed Transformers Modeling Backend for Enhanced Inference Performance
vLLM推出原生速度Transformers建模后端，大幅提升推理性能
This update is critical for AI engineering teams: eliminating format conversion speeds up model iteration, and 2-5x speedup directly reduces GPU costs. If you're building LLM online services or batch inference, this is practically a must-read technical update.
90
FeaturedGoogle DeepMind Introduces SL2T, a Sign Language-to-Text Model for Deaf Users
Google DeepMind 发布手语转文本模型 SL2T，助力聋人用户
This news matters not only as a technical breakthrough but also as a sign that AI is beginning to address the needs of marginalized groups. For developers, the architecture and technical approach of SL2T merit deep study; for accessibility advocates, it's a key case for advancing industry standards.