惯性聚合 高效追踪和阅读你感兴趣的博客、新闻、科技资讯
阅读原文 在惯性聚合中打开

推荐订阅源

B
Blog
D
Docker
J
Java Code Geeks
腾讯CDC
Blog — PlanetScale
Blog — PlanetScale
G
Google Developers Blog
M
MIT News - Artificial intelligence
L
LangChain Blog
T
The Blog of Author Tim Ferriss
P
Proofpoint News Feed
MyScale Blog
MyScale Blog
博客园 - Franky
GbyAI
GbyAI
Hugging Face - Blog
Hugging Face - Blog
aimingoo的专栏
aimingoo的专栏
Last Week in AI
Last Week in AI
OSCHINA 社区最新新闻
OSCHINA 社区最新新闻
博客园 - 聂微东
N
Netflix TechBlog - Medium
B
Blog RSS Feed
Y
Y Combinator Blog
阮一峰的网络日志
阮一峰的网络日志
奇客Solidot–传递最新科技情报
奇客Solidot–传递最新科技情报
Google DeepMind News
Google DeepMind News

Hacker News - Newest: "AI"

AI can't read an investor deck AI as an attorney? Student uses ChatGPT, Gemini to sue UW over alleged racial discrimination Hacking MCP Servers in AI Systems – The Rug Pull: Tool Changes After Approval GitHub - MeepCastana/KubeezCut: Free Web based video editor Can AI judge journalism? A Thiel-backed startup says yes, even if it risks chilling whistleblowers Coming soon: 10 Things That Matter in AI Right Now DARPA built an AI to fact-check enemy weapons claims What explains heterogeneity in AI adoption? When AI Meets Muscle: Context-Aware Electrical Stimulation Promises a New Way to Guide Human Movements - Department of Computer Science AI Changed How We Build. It Did Not Change What Matters. Linux rules on using AI-generated code - Copilot is OK, but humans must take 'full responsibility for the… Meta spins up AI version of Mark Zuckerberg to engage with employees Code Mode: Let Your AI Write Programs, Not Just Call Tools | TanStack Blog GitHub - Delavalom/graft: Go framework for building AI agents. Type-safe tools, multi-provider (OpenAI, Anthropic, Gemini, Bedrock), zero vendor SDKs. India's TCS tops estimates, says new AI models did not dent services demand Gen Z's fading AI hype Strong feeling: we are in a folded AI reality GitHub - machinarii/total-recall-catalog: A reference catalog of latest knowledge retrieval, memory & RAG systems GitHub - mensfeld/code-on-incus: Give each AI agent its own isolated machine with root, Docker, and systemd. Active defense detects and stops threats automatically.. Quantization, LoRA, and the 8% Problem: Benchmarking Local LLMs for Production AI Iran war: We spoke to the man making Lego-style AI videos that experts say are powerful propaganda Powell, Bessent discussed Anthropic's Mythos AI cyber threat with major U.S. banks GitHub - immartian/bellamem: Persistent belief-graph memory for AI agents. Retrieves decisive context by importance — not recency, not RAG, not /compact. recursive-mode: The Repo-Native Operating System for AI Engineering After the attack on Sam Altman's home, will AI CEO's go on the offensive? The biggest advance in AI since the LLM Opus 4.6 vs GPT 5.4 One Prompt Unity World Generation Test “AI polls” are fake polls Client Challenge Can AI be a 'child of God'? Inside Anthropic's meeting with Christian leaders
POLIS — the control plane for coding agents
lucius_gc · 2026-06-15 · via Hacker News - Newest: "AI"

[ Local-first · git-native · MCP ]

Coordinate your coding agents like one team.

Run Claude Code, Codex, Gemini and Cursor against one repo. Every task has an owner, every handoff has evidence, and the team measurably stops repeating its own mistakes — in git, across every vendor.

$uvx polis-protocol init

  TELEMETRY / REPEAT-ERROR RATE−88%

70%0% MEMORYLESS 65%POLIS 8%

SINGLE AGENT / UNMANAGED SWARMPOLIS · ACCUMULATES + RE-INJECTS

[ 01 ]The problem// FAILURE MODES

01.A — COLLISION

Two agents, one file, at once.

Claude and Codex both open src/auth/login.py. One silently overwrites the other; work is lost, or the afternoon goes to untangling a merge. A plain repo leaves coordination to luck — and collisions grow with every parallel worker you add. This is the failure that scales worst.

01.B — AMNESIA

They forget.

Every session starts at zero. The same gotcha, re-learned every time.

01.C — SILOS

They're isolated.

Switch vendor, lose the context. No shared memory across tools.

[ 02 ]Proof, measured honestly// REPRODUCIBLE

CONTRACTOPENED CLAIMED +FILES RESERVED SETTLEDWITH EVIDENCE LESSON +GUARDRAIL NEXT TASKPRE-LOADED RE-INJECTED INTO MATCHING FUTURE TASKS

−88%

Repeat errors · 65% → 8%

Polis records each failure as a lesson or guardrail and re-injects it into matching future tasks. The repeat-error rate falls 88% below a memoryless setup — each failure class recurs at most once. A lone agent can't draw that curve; it never accumulates.

# reproduce it yourself
$ polis bench --mode learning

0

Collisions · deterministic

Before touching code, an agent reserves the files. An overlapping reservation is rejected outright — no model judgement, no race. The guarantee a single agent or an unmanaged swarm structurally cannot give.

$ polis reserve src/auth --as claude
$ polis reserve src/auth/login.py --as codex
REJECTED // HELD BY claude

[ 03 ]Operating sequence// ONE _polis/ FOLDER

SEQ.01 — FOUND

Scaffold the polis

Create the workspace; register your agents as citizens.

$ uvx polis-protocol init

SEQ.02 — ROUTE

Open & assign work

Contracts get an owner, acceptance criteria, and a transparent routing reason.

$ polis contract open …
$ polis route --explain

SEQ.03 — COMPOUND

Settle & learn

Settled work files a lesson; the next matching task starts pre-loaded with it.

$ polis contract settle … OK

[ 04 ]Operating envelope// WE BENCHMARKED OUR OWN CLAIMS

[ Reach for Polis when ]

  • +2+ agents touch one real repo and collisions are a risk
  • +You switch between vendors and lose context each time
  • +You want the team to stop repeating mistakes — provably
  • +You need an auditable record of who did what, and why

[ Skip it when ]

  • One well-prompted agent already does the job
  • Your capability cards are accurate and tasks never drift
  • You want a hosted runtime — Polis coordinates, it doesn't execute

[ 05 ]Install// < 5 MINUTES

$uvx polis-protocol init

$pipx install polis-protocol

$polis status