Today News Research Fields Stacks Market Analytics

⌘K

This week

Get the morning digest

The top stories in the fields you follow, at 08:00 your time.

Latest in AI and developer tools

Today's trail

Pulse

Top picks

Today's trail

Rising topics

Rising tools

ByteTrail · AI and developer-tools intelligence

News Research Stacks For AI agents API

Fields · this week

Evals577 Agents423 Multimodal421 Frontier LLMs326 Computer vision274 Recursive self improvement266 Inference & serving234 Training & fine-tuning216 Agents & indirect prompt injection204 Clinical reasoning170 Neural operators164 Robotics151 Forecasting time107 Image & video generation107 Code models97 All 32 fields

This week in Evals

Multi-step SWE: Can Coding Agents Keep Building on Their Own Code Over Long Horizons?Nov 4
Scientist World: Grow a Research World for AI-ScientistsNov 5
XStack: A Benchmark for ML Repo MigrationNov 5

More in Evals · 577 this week

Most active this week

neural operators · physics informed neuralneural operators52 this week
agents · toolagents46 this week
coding agents · coding agentagentsNew41 this week
indirect prompt injection · prompt injectionagents41 this week
gpu memory · gpusInference & serving40 this week
recursive self improvement · airecursive self improvement38 this week
pose estimation · camera poseMultimodal33 this week
agent collaboration · multi agentrecursive self improvement33 this week
code generation · language models llmsagents29 this week
policy gradient · optimal policylinear bandits28 this week

Rising tools

Soup+1411% downloads · 17.4k/wk+1410.7%
better-auth+111% downloads · 1.6M/wk+111.4%
agent-native+95% downloads · 79.6k/wk+94.7%
TanStack AI+93% downloads · 1.8M/wk+92.9%
openclaude+176% downloads · 5.8k/wk+176.1%
OpenUI+117% downloads · 722.9k/wk+116.9%
mcp-remote+60% downloads · 1.3M/wk+60.3%
remotion+105% downloads · 160.7k/wk+105.1%

updated 7m ago

Last hour Today

Pulse · cryptobriefing.com

cryptobriefing.com · Nov 7

Oxford study finds frontier AI agents struggle to coordinate with strangers

Oxford researchers find frontier AI agents struggle to coordinate with strangers, but shared plain-language rules can improve cooperation

Top picks this weekarXiv

arXiv

Nov 4

Multi-step SWE: Can Coding Agents Keep Building on Their Own Code Over Long Horizons?

AI Long-horizon benchmark for coding agents building on their own code.

Hugging Face

Nov 2

Kimi K3.1 Pro is an open-weight, natively multimodal agentic model, and our most capable 3T-class model to date. Post-trained from Kimi K3 with large-scale joint reinforcement learning across hundreds of downstream domains, it is the first model in the K3.1 series. With a…

Read moreLikes 1.6k

GitHub

Nov 3

KKKKhazix/agent-autoloop

让你的命令行 Agent 在后台自己接活、自己跟进到底；平时不烦你，遇到拿不准的事才发卡片找你拍板。

Read moreStars 3.9k

Hacker News

Nov 2

Astra can read and write weights to improve Qwen

AI Model weight reading/writing for fine-tuning

Read moreHN points 2.9k

Lobsters

Nov 7

OpenBSD top(1) adds flag to show chroot, pledge and unveil status

Comments

moonshotai/Kimi-K3.1-Pro

All arXiv Hugging Face GitHub Hacker News

Latest Top this week

GitHub

Mar 26

Sanjidh090/Lipi-Ghor-bn-882-SSTT

Lipi-Ghor (লিপিঘর, meaning "House of Scripts") is a large-scale Bengali speech dataset designed for automatic speech recognition (ASR), speaker diarization, and spoken language research. It is one of the largest open Bengali speech corpora with aligned speaker, transcription,…

Read moreStars 1

Hugging Face

GitHub

Mar 25

D2I-Group/TSFLab

Agent-first time-series forecasting platform: 190+ reproduced models, fair benchmarks, rolling real-time tracks, and a public leaderboard.

Read moreStars 66

GitHub

Mar 20

FreedomIntelligence/HuatuoGPT-3

HuatuoGPT-3: RL-Only Domain Adaptation from Base Models via Off-Policy Seeding

Read moreStars 29

1…717671777178…7196

Mar 26

facebook/sam3.1

Mask generation model · checkpoint · 189.4k downloads · 1.4k likes

Read moreLikes 1.4k