gemini creates google sheets from prompts
use gemini to build spreadsheets, generate formulas, and analyze data with natural language commands.
topic
tools
which tokens hybrid models predict better
a study comparing token-level predictions of a hybrid model and a transformer reveals where each architecture excels.
german court says google liable for ai errors
a german ruling holds google responsible for mistakes in its ai overviews, treating ai agents like human employees under the law.
tokenspeed-kernel: clean apis for multi-silicon llm inference
tokenspeed-kernel introduces a layered api and registry system to decouple llm inference runtimes from hardware-specific kernels, enabling portable and high-performance multi-silicon support.
spin up a vllm server on hugging face jobs in one command
launch a private, openai-compatible llm endpoint on hugging face infrastructure with a single command, paying per second with no server setup.
figma adds code layers and ai tools for design
figma's latest update brings code layers, animation support, and ai features to help teams iterate faster on the collaborative canvas.
open far-field asr benchmark reveals real-world gap
the ffasr leaderboard is the first open benchmark evaluating asr models under realistic far-field acoustic conditions, showing a large performance gap compared to near-field tests.
nemo automodel speeds moe fine-tuning 3.7x over transformers v5
nvidia nemo automodel builds on huggingface transformers v5 to deliver 3.4-3.7x higher training throughput and up to 32% less gpu memory for mixture-of-experts models with a single import change.
top local coding models for 2026
seven open-weight models that run on consumer gpus for private, fast, and capable local coding assistants.
cross-origin storage api cuts duplicate ai model downloads
a proposed browser api lets web apps share cached ai model and wasm files across origins using cryptographic hashes, reducing redundant downloads and storage.
deepseek-v4 serving throughput jumps 5x on gb300 with sglang
sglang and nvidia optimize deepseek-v4 inference on gb300 and blackwell ultra, achieving up to 5x higher throughput at same interactivity since day-0 launch.
why webmcp matters for browser agents
webmcp is an open standard that lets websites expose structured tools to browser-based ai agents, replacing guesswork with direct function calls.
shipping huggingface_hub weekly with ai and open tools
huggingface_hub now releases weekly using an open-source, ai-assisted pipeline with human oversight, cutting release time from half a day to minutes.
chatllm review: one subscription for many ai models
a review of chatllm by abacus ai, a multi-model ai workspace that combines chat, coding, document analysis, image generation, and automation under one subscription.
temporary cloudflare accounts for ai agents
cloudflare now lets you deploy workers projects without an account, using a temporary 60-minute deployment that anyone can claim later.
porting moebius inpainting model to browser with claude code
a 0.2b image inpainting model was converted from pytorch to onnx and deployed as a browser demo using webgpu, with help from claude code.
prompt injection as role confusion
research shows llms prioritize text style over content, enabling jailbreaks through role confusion.
sqlite-utils 4.0rc1 adds migrations and nested transactions
a new release candidate for the python sqlite toolkit brings schema migrations and savepoint-based nested transactions.