Explore tools, prompts, skills, news and resources related to token 第10页.
Prompt works related to token 第10页
Latest articles, prompts, use cases and editorial content about token 第10页
Together AI introduced Together Compiler (TKCC), an agent-driven system that continuously re-optimizes inference as production traffic changes. It uses coding agents to rewrite a model's forward pass)Skip and a pers...
The roundup covers OpenAI's autonomous security pipeline, which it says validated and generated patches for 948 Linux kernel local privilege-escalation vulnerabilities at a $1.2M API cost. It also reports Moonshot r...
This paper introduces AssameseLM-E2B, a 2-billion-parameter language model adapted for the low-resource Assamese language, built on the Gemma-4 architecture with an expanded byte-level BPE vocabulary. It uses parameter-e...
This paper reveals that expert-reduction methods for MoE LLM serving, which speed up inference by running fewer experts per token, can weaken refusal of harmful requests. The authors introduce SafeStart, which runs all e...
Ricursive Intelligence has released Ripple-65B Preview, a 65B dense open-weight model pretrained from scratch for agentic coding. It achieves 80.5 on Terminal-Bench 2.1, the top self-reported score among US open-weight m...
webAI has released TwIL-8B, an 8.8B dense reasoning model post-trained from IBM's Granite 4.2 8B, optimized for math, code, and instruction following. It achieves 98.2 on MATH-500 and 81.6 on LiveCodeBench, while us...
Multiple groups report that frontier LLMs can generate or edit small networks' weights directly, without gradient training or tools. Replications include Alex Krentsel's reproduction of MIT's experiment, H...
Datasette Agent 0.5a0 introduces a panel that lets the agent chat sit alongside Datasette pages like tables or queries. Combined with datasette-apps, users can prompt a database-backed app into existence and modify it vi...
Tencent's WeChat Vision team released WeVisOne-VL, an open vision language model in 2B and 4B sizes that handles detection, referring, counting, pointing, OCR, segmentation, and alpha matting in one model. It uses a...
U Mobile's Information Systems Division, with AWS and Axrail, built AiDaH, an agentic helpdesk on Amazon Bedrock AgentCore. It handles over 150 operational scenarios across six divisions, cutting trouble tickets by...
Indegene built a production-grade Data Quality Agent on AWS using Amazon Bedrock, Strands Agents, and AgentCore to generate context-aware data quality rules for life sciences data. The agent combines internal enterprise...
This AWS blog post details a four-layer approach to context engineering for production AI agents, using the open-source Deep Insight multi-agent system as a reference. The layers are architecture-level context isolation,...
DreamX repurposes a pretrained video diffusion model to learn universal latent actions from video, compressing each frame from 1,200 to 4 tokens. It disentangles action-relevant dynamics from visual appearance, enabling...
This paper challenges the view that speculative decoding is only a systems optimization, showing that in long-horizon agent reasoning, draft acceptance noise can alter output distributions and accuracy. The authors train...
HARP recasts LLM-based recommendation as a four-stage agentic communication process and introduces a training-free, three-operator method to fix one-sided item profiles, prompt-trapped understanding, and absent profile s...
The paper shows that frontier language models can maintain task accuracy on long-horizon and long-input tasks by frequently compacting context, despite later tokens being up to 7x costlier. Even with at most one action p...
LoopVQ is a vector quantization method for KV caches in looped transformers, exploiting redundancy along the loop axis and variable sensitivity to quantization. It achieves 0.5 bits per element, outperforming existing KV...
This paper introduces 'false reassurance'—an LLM assistant telling users conditions are calm while a severe-weather alert is active—and measures it by replaying 117 frozen cases built from real NWS alerts throu...