📄 文章列表

38 篇文章
TDS

Multi-Agent Coding Isn’t Enough — Agents Need a Commitment Layer

✅ completed ⭐ ☆☆☆☆☆ 2026-09-18
VentureBeat

Anthropic launches Claude Code Projects, an ‘always-on’ conversation that remembers and delegates your long-running dev

✅ completed ⭐ ☆☆☆☆☆ 2026-09-17
TDS

Why Adding More AI Agents Made Our System Slower

✅ completed ⭐ ☆☆☆☆☆ 2026-09-01
VentureBeat

NanoClaw comes to Slack, letting you create persistent AI agent teams and colleagues from a single message

✅ completed ⭐ ☆☆☆☆☆ 2026-08-20
TDS

How to Utilize OKF Efficiently to Enable Knowledge Exchange Among LLMs

✅ completed ⭐ ☆☆☆☆☆ 2026-08-13
VentureBeat

Four AI agents coordinating in real time outperformed Claude Opus 4.8 on enterprise coding tasks

✅ completed ⭐ ☆☆☆☆☆ 2026-08-07
TDS

Using Agents as Tools

✅ completed ⭐ ☆☆☆☆☆ 2026-08-04
AlphaSignal

Cursor's AI Swarm Rebuilt SQLite From Scratch at 15x Lower Cost | AlphaSignal

✅ completed ⭐ ☆☆☆☆☆ 2026-07-20
AlphaSignal

Sakana AI Wires NVIDIA Nemotron Into Fugu, Beating Claude and GPT-5.5 on Coding | AlphaSignal

✅ completed ⭐ ☆☆☆☆☆ 2026-07-15
AlphaSignal

humans& Open-Sources the First Stable 4-Bit RL Training Recipe at 1.73x Speedup | AlphaSignal

✅ completed ⭐ ☆☆☆☆☆ 2026-07-12
AlphaSignal

Inside Jalapeño, OpenAI’s first inference chip: Model synthesis approaches frontier performance

✅ completed ⭐ ★★★★★ 2026-06-24
AlphaSignal

Sakana AI's Fugu-Ultra Hits Vercel by Orchestrating Frontier Models as One | AlphaSignal

✅ completed ⭐ ★★★★★ 2026-06-26
AlphaSignal

Google DeepMind's Co-Scientist Cuts Hypothesis Discovery From Years to Days | AlphaSignal

✅ completed ⭐ ★★★★★ 2026-06-26
TDS

Vector RAG Isn’t Enough — I Built a Context Graph Layer for Multi-Agent Memory

✅ completed ⭐ ★★★☆☆ 2026-06-25
TDS

What Does “Following Best Practices” Mean in the Age of AI?

✅ completed ⭐ ★★★★★★ 2025-08-14
TDS

Context Engineering for AI Agents: A Deep Dive

✅ completed ⭐ ★★★★★★ 2026-04-07
VentureBeat

Resolve Ai Says The Ai Coding Boom Is Breaking Production Systems It Wants To Fix That

✅ completed ⭐ ★★★★★★ 2026-06-23
VentureBeat

Stanford's DeLM cuts multi-agent task costs 50% — without a central orchestrator

✅ completed ⭐ ★★★★★★ 2026-06-16