AITOPAI热报
Products

Thoughtful Things 推出 Engram 采样器，用 AI 变幻音频生成新音色

Engram is a sampler that turns broken AI hallucinations into music

Official accounttheverge@Terrence O’Brien
Blog/Media
Read the original
Why we picked it

众筹里的 Engram 是台 AI 采样器，能把随便一段音频扭曲成新音色，和 Suno 那种一键出歌完全是两个路子，玩音乐制作的可以看看。

音乐初创公司 Thoughtful Things 在 Kickstarter 上为首款乐器 Engram 发起众筹。

Image · theverge
Body

Engram 是一台采样器兼 groovebox，内置 AI 会扭曲输入的音频，甚至凭空幻觉出全新音色。官方强调它不是 Suno 那类一键出歌的设备，而是面向声音设计的创作工具。

Original · theverge

Engram is a sampler that turns broken AI hallucinations into music

Music startup Thoughtful Things has just launched the Kickstarter campaign for its first instrument, Engram. It's a sampler and groovebox that uses AI to mangle incoming audio and even hallucinate completely new sounds. This isn't Suno in a box, though. This isn't a "push-button, get-song" device, aimed at creating something that sounds ready for top-40 […]

Industry Coordinates & Source Verification

This report is categorized under AITOP's "Products" desk, focusing on US frontier AI labs and Silicon Valley technology leaders. Within our cross-regional analytical framework, it directly maps to AI developer toolchains, coding agents, and engineering workflows. Key entities and technical topics under continuous tracking include Engram, Thoughtful Things, groovebox, AI music.

Source attribution: curated from theverge (@Terrence O’Brien).

#Engram#Thoughtful Things#groovebox#AI music

Keep reading

Recent stories with the same tag or section
PapersBuildersSelected10:41
SlackTier Moves DeepSeek-V4.1 Engram Tables Off Host DRAM

The non-obvious insight is that per-layer prefetch slack, not raw bandwidth, decides whether lookup tables fit on NVMe, DRAM, or remote memory — static hot sets transfer poorly for agent traffic. Inference engineers running DeepSeek-V4.1 or similar n-gram-augmented models on SGLang can reclaim roughly 180 GiB of host memory and convert it into KV cache, directly lifting throughput. Compared with simply scaling up DRAM, the RDMA option lets one table copy serve two instances, cutting per-node memory cost.

#DeepSeek-V4.1#SGLang#Engram#inference optimization
arXiv cs.LG@Wen Huang, Jack LiuSource
PapersBuildersSelected09:30
GateRQ Quantizes DeepSeek Engram Memory Tables by Gate Weight

Frequency-based bit allocation is the wrong heuristic for conditional memory: gates, not access counts, predict which rows carry the facts that break when quantized. Engineers serving large hashed-memory models on vLLM get a drop-in path to 7.8x smaller GPU tables with near-baseline PopQA accuracy and no retraining. The method ties directly to DeepSeek-V4.1-Flash, where removing Engram costs 36.8 PopQA points, making memory-table compression a practical concern for anyone deploying that model.

#DeepSeek#Engram#quantization#inference optimization
arXiv: DeepSeek@Tianqi Chen et al. (7)Source
PapersBuildersSelected14:52
STAPLE Adds Sparse Embedding Modules to Pretrained Checkpoints

Sparse upcycling usually means expensive retraining from scratch, so a method that grafts new capacity onto an existing checkpoint could cut the cost of scaling older models. The nuance matters: this is a lightweight FFN modification, not a full Engram architecture, so results depend on how much quality the added token-indexed embeddings recover. Researchers and engineers fine-tuning open-source checkpoints should follow the paper for the training recipe.

#STAPLE#Engram#open-source models
Teortaxes@teortaxesTexSource