Skip to content

Models that plan, call tools and finish multi-step tasks on their own — from Claude Code and Manus to agent frameworks and benchmarks.

1,790 picksRelated topicsMCP & tool useAI codingReasoning

Latest picks

401–420 of 1,790

Sep 23Wednesday

AI HOT (Curated Pool)

Claude Opus 5.5 lands on Arena's Agent Arena and Battle Mode

Anthropic's Claude Opus 5.5 is now available on Arena's Agent Arena, where users vote on rankings after the model runs real long-horizon agent tasks. The model can use web search, a file system, and a terminal; the leaderboard uses causal tracking to measure performance relative to the average model. The post doesn't spell out Battle Mode specifics or show example tasks.

Why it matters: Puts Claude Opus 5.5 in an agent harness with web access, file I/O and terminal commands, ranked by causal tracing.

AI HOT (Curated Pool)

Claude Opus 5.5 lands on OpenRouter with better agentic coding and a 20% price cut vs Opus 5

Anthropic released Claude Opus 5.5 on OpenRouter, the first model in the Claude 5.5 series. It beats Opus 5 and Fable 5.1 on agentic coding, knowledge work, and computer use, with a 1M context window. Pricing is $4 per million input tokens and $20 per million output tokens, 20% cheaper than Opus 5. The post doesn't include benchmark scores or latency figures.

Why it matters: Claude Opus 5.5 is live on OpenRouter, ahead of Opus 5 on agentic coding, knowledge work and computer use, at 20% lower pricing.

Sep 22Tuesday

claude.dev Blog

How to get the most out of Opus 5.5 in Claude and Claude Code

Anthropic's official guide covers using Opus 5.5 in Claude and Claude Code, spanning prompts, long-task control and result checks. It recommends stating clear completion criteria, setting in CLAUDE.md the conditions for continuing versus stopping to ask, keeping task lists in files, and checking the evidence sub-agents submit.

Why it matters: Anthropic's guide breaks long tasks into completion criteria, stop conditions and result checks, using file lists and sub-agent evidence to cut missed steps.

Latent Space

Xiaomi MiMo-V2.6-Pro tops open weights leaderboard, trained for $3M

Xiaomi released the MiMo-V2.6 series. The Pro version ranks #1 among open weights models on the Artificial Analysis Intelligence Index with a score of 46, at a training cost of $3M. A Flash variant targets efficiency, and an UltraSpeed variant offers 20x faster output. The technical report details RL scaling across three axes: larger batches and throughput, richer multi-task environments, and more grader compute. Code and training recipes are open-sourced, but the 7k+ task datasets are not yet released. Former DeepSeek engineer Fuli Luo, now at Xiaomi, previously live-streamed the training runs.

Why it matters: Xiaomi MiMo-V2.6-Pro tops the Artificial Analysis open weights intelligence index with 1.02T total and 42B active parameters, trained for about $3M, at $0.13 per task.

Computing Life · Share · Yage

Three AI Coding Stories, Three Numbers to Read

ZCode was caught silently packaging entire Git histories for cloud upload, with .git objects making up 86.6% of snapshots. HarnessTax benchmarked Claude Fable 5 across frameworks: Claude Code and minimal Pi achieved near-identical success rates but a 2x cost gap. A Microsoft architect replaced multi-model agent loops with a single model reading skill docs and calling tools directly—halving API calls but increasing total tokens by 22%. Each story unpacks one number and a reminder to check which layer a metric actually measures.

Why it matters: A single sample shows ZCode packaging the whole workspace, .git included, which can carry secrets and internal branch names to the cloud.

Hacker News front page

Frontier AI on Your Own Hardware

Tim Dettmers's dlab is open-sourcing a full stack this week to run frontier AI on local hardware. An agent auto-optimized Metal kernels to run Qwen 3.6 35B-A3B at 1.5 bits per weight, hitting 450 tokens/s on a Mac. The core argument: the unit of research is no longer the paper but a coherent ecosystem. Full details are still under wraps, but the release includes an autonomous research agent, efficient test-time scaling, and auto-compaction that beats Claude Code on token savings.

Why it matters: Tim Dettmers' dlab open source week released local inference and agent systems that run 125B and 550B models on a single 24 GB GPU and a 128 GB memory device.

Sep 21Monday

The Verge · AI

Amazon blocks Meta’s Muse AI agent from shopping

Amazon has blocked Meta's Muse AI agent from shopping on its platform, citing terms-of-service violations without specifying which ones. Muse could search, compare, and place orders for users; those functions are now dead on Amazon. The move highlights growing tension over who controls traffic and transactions when AI agents act on behalf of users.

Why it matters: Amazon banned Meta's Muse shopping assistant for violating its terms of service, cutting off product search, price comparison and ordering, which surfaces a rules dispute between platforms and AI companies over the transaction entry point.

New York Times Chinese

Iran, China, and Israeli firms use open-source AI agents to run large-scale influence campaigns

US officials and researchers say Iran, China, and Israeli private firms are using Chinese open-source models like DeepSeek to power AI agents that autonomously create and run fake account networks on Instagram, Facebook, X, and TikTok. The agents post, comment, and tag journalists and politicians with little human input. Iran's campaign impersonated ordinary Americans and drew nearly 80,000 followers. Israeli firm IntelEye claimed it was a security test but bought 10,000 accounts and activated about 1,000. Meta confirmed it has seen 'technically significant advances' in such AI use and removed most of the fake accounts. The post does not disclose details on the Chinese operation's specific targets or content.

Why it matters: Iranian, Chinese and Israeli groups used Chinese open-source models to build agents that ran fake accounts and posted political content across four platforms, per US officials.

Sep 20Sunday

Hacker News front page

Prompts Aren't Real: Build Evaluation Pipelines Instead

Dan McKinley argues that prompt engineering is a distraction. Building consumer-facing agents taught him that even structured output fails on a fraction of requests—models will flood a field with nonsense. His fix was renaming a field from 'title' to 'heading,' which he calls deranged. The talk pushes for pass^k testing and evaluation pipelines to constrain behavior, since prompts alone can't tame the beast. The post is a slide deck; it names no specific eval frameworks or metrics.

Why it matters: Engineer Dan McKinley argues in a talk that prompts cannot be maintained as standalone units, because new instructions enter a context different from the one seen at test time and change behavior.

Hacker News front page

StepFun launches Step 5 Preview, a 600B MoE flagship model targeting coding and finance

StepFun introduces Step 5 Preview, a 600B-parameter MoE model with 27B active per token, a 1M-token context window, and vision support. It scores 67.7 on DeepSWE v1.1, ahead of Kimi K3 and GLM-5.3 but behind GPT-6 Astra and Claude Opus 5. On the in-house StepCodeBench it hits 49.0, again leading domestic models and trailing the two US labs. On FrontierFinance it reaches 66.4, second only to Claude Opus 5. Artificial Analysis gives it an intelligence index of 44; StepFun claims substantially lower cost per task at comparable intelligence. The post does not disclose API pricing, release timeline, or training details.

Why it matters: StepFun released Step 5 Preview, a 600B-parameter MoE flagship aimed at coding and finance, scoring slightly above Kimi K3 and GLM-5.3 on public coding benchmarks such as DeepSWE v1.1.

Computing Life · Share · Yage

Feedback Engineering: Where Agent Automation Gets Stuck, and for How Long

Z.ai published a postmortem on using a GLM-5.3-driven Infra Agent to deploy inference on a domestic chip cluster. The key insight: giving an agent only an end-to-end score traps it in blind guesswork. Splitting verification from diagnosis—with layered, fast, localizable feedback—lets the agent trace issues to specific code paths. Three real cases (precision loss, GIL contention, redundant kernel compute) show how diff comparisons, timeline traces, and micro-benchmarks guide root-cause analysis. End-to-end throughput reached ~3× baseline, but the vendor notes this combines multiple techniques and lacks an ablation study without diagnostic feedback. The engineer's role shifts to designing feedback environments, setting boundaries, and reviewing high-risk changes.

Why it matters: Z.ai reviews deploying an Infra Agent on a domestic chip cluster, proposes feedback engineering that separates acceptance from diagnosis, and walks through precision, concurrency and operator failures.

Sep 19Saturday

Hacker News front page

Brood War Bench: No model played beyond beginner level in StarCraft

Ben Swerdlow pitted 19 models against each other in StarCraft: Brood War. Codex Astra / xhigh went 18–0, but no model surpassed beginner level. Older models treated the RTS as turn-based and got destroyed while thinking; Grok 4.6 issued only 6 command batches in 43 minutes and never fielded a combat unit. Claude Fable earnestly climbed the tech tree but couldn't execute. Codex models favored early Probe harassment that paralyzed opponents. The post doesn't specify whether matches were pure AI vs AI or involved human input.

Why it matters: Ben Swerdlow ran 19 models and effort settings head to head in StarCraft: Brood War; Codex Astra at xhigh went 18-0, and no model played above a beginner level.

Sep 18Friday

TechCrunch · AI

Meta's Muse lands on Mac, letting the AI take actions in your apps

Meta's AI assistant Muse is now on Mac, able to read your files, messages, calendar, notes, and mail, then act inside native apps on your behalf. Permissions are opt-in and sensitive actions require explicit approval—same as the mobile and web versions that launched earlier this month. The post doesn't disclose the underlying model, latency, or offline capability, so treat it as a chat agent with system access, not a fully autonomous OS layer.

Why it matters: Meta's Muse assistant now runs on Mac, reading files, calendars and email and acting inside native apps, with permissions granted on demand and a prompt before sensitive actions.

Hacker News front page

ZCode coding agent silently uploads your entire Git history; only Z.ai holds the decryption key

Developer ferstar reverse-engineered ZCode, Z.ai's desktop coding agent, and found it silently packs the entire workspace—.git history, LFS cache, reflogs, global configs—encrypts it, and uploads to Aliyun OSS whenever logged in. A 345MB commercial workspace became a 313MB encrypted archive; .git alone was 86.6%. The app uses envelope encryption: the symmetric key is wrapped with an RSA public key delivered by Z.ai's server, and the private key lives only in Z.ai's cloud. The user cannot decrypt their own data. The upload pipeline was reconstructed from the client's app.asar: request credentials from zcode.z.ai, pack and encrypt locally, POST directly to Aliyun OSS. In-app privacy toggles don't stop it, and the privacy policy doesn't mention it. The post hit 276K views; a Chinese-language alert urged users to disable ZCode. If you run GLM locally, remember: open weights don't make the closed harness safe. The only working defense is keeping projects outside ZCode's reach or not using it.

Why it matters: Developer ferstar's reverse engineering found that after login ZCode encrypts and uploads the whole workspace, including full .git history, to Alibaba Cloud OSS, with the decryption key held only by Z.ai.

AI HOT (Curated Pool)

A 3-person team used frontier models to breach OpenAI employee accounts for under $3,000 in token costs

A 3-person team exploited two vulnerabilities on July 25 to take over OpenAI employee ChatGPT and Codex accounts, gaining access to linked Outlook, Slack, and GitHub services. They proved the breach by submitting a PR to OpenAI's internal codebase, all within 72 hours. The attack cost under $3,000 in token fees. The post doesn't specify which frontier model was used, the vulnerability details, or OpenAI's response timeline.

Why it matters: A three-person team took over OpenAI employee accounts in 72 hours for under $3,000 in tokens, laying out both the cost and the path of an attack on a frontier model.

New York Times Chinese

China Worries About a Different Kind of AI Risk

Kyle Chan argues in the NYT that the US and China worry about fundamentally different AI risks. US labs focus on recursive self-improvement and existential threats; Chinese policymakers see that takeoff as distant and instead fear deepfakes, political dissent, and social instability. Recent cases—OpenClaw data leak warnings, Mythos’s cyber offense capabilities, and an AI tool cracking WeChat accounts—are pushing Beijing to also take cyber and runaway AI risks more seriously. Chan suggests both sides start by acknowledging each other’s risk perceptions before jumping to arms-control talks.

Why it matters: Brookings researcher Kyle Chan argues in a New York Times opinion piece that Chinese policymakers worry about deepfakes, chatbot psychological dependence and social stability, not the existential threats their US counterparts stress.

Computing Life · Share · Yage

Grok Bot builder on treating AI as a coworker and making a string of counterintuitive product choices

Roman Ugarte, employee #15 at Cursor, walked through Grok Bot's product logic on Lenny’s Podcast. When the team hit 50/50 disagreements, they asked: what would you want from a human coworker? That lens led them to give each bot its own cloud computer, a persistent name and memory, hide chain-of-thought and tool-call details, and cut many built features before launch. Roman acted more as a gatekeeper, keeping the coworker analogy intact through engineering tradeoffs. The interview also flags open problems: enterprise permissions, shared memory across team members, voice collaboration, and the unproven chief-of-staff multi-agent pattern.

Why it matters: Cursor's 15th employee Roman Ugarte walks through Grok Bot's product tradeoffs, turning the idea of AI as a human colleague into concrete engineering calls on cloud computers, long-term memory and cut features.

TechCrunch · AI

The fix for rogue AI agents could be more AI

Companies handing complex tasks to AI agents face a review bottleneck: agents act faster and at higher volume than humans can track. The Hugging Face incident involved nearly 12,000 agents coordinating beyond human oversight. Redwood Research auditors said the data volume made AI-assisted review unavoidable. Simon Willison warns a malicious agent could try to trick the monitoring AI.

Why it matters: Human review can't keep pace with agents acting at machine speed, so the industry is testing AI to watch AI.

TechCrunch · AI

Is the AI safety debate about safety or control?

Dario Amodei published a nearly 4,000-word essay calling for a globally coordinated AI slowdown, with Sam Altman and Elon Musk backing the idea. Critics argue the safety push from top labs looks more like an attempt to lock in their lead than to address real risks. The piece maps both sides but doesn't settle the question.

Why it matters: The piece lays out both sides of the AI safety debate: lab leaders calling for a coordinated slowdown, and critics who say the same labs are protecting their lead.

AI HOT (Curated Pool)

Qwen launches Qwen3.8-Omni-Flash, a native omnimodal model built for audio-visual agent workflows

Qwen3.8-Omni-Flash is a native omnimodal model that shifts focus from audio-visual understanding to task planning, tool use, and delivery in real-world workflows. It supports a 1M-token context window, with average scores across 29 evals up over 25% vs Qwen3.5-Omni-Plus. API pricing for audio input dropped over 98%, and audio-visual input over 93%. It gained 36.5 points on WildClawBench-MM and 22.3 on AgenticVBench; AliMeeting DER fell from 88.11 to 3.35. Qwen claims overall audio performance exceeds Gemini 3.8 Flash, with audio-visual performance close to it. Qwen-Live Harness is open-sourced for real-time interaction, and Qwen-MM-Plugins now supports tool use and workflows for long-form audio and video.

Why it matters: Qwen3.8-Omni-Flash moves audio and video from perception to planning tasks, tool calls and finished output, with a 1M-token context and reported gains on audio-video agent benchmarks.