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

241–260 of 1,790

Oct 9Friday

AI HOT · Tips & opinions

Hugging Face engineer builds 7 small models with ML Intern for about USD 103

A Hugging Face engineer used ML Intern to build seven small models, with CPU and GPU job costs totaling about USD 103. The projects cover citrus disease detection, image LoRA, prompt rewriting and distillation from an image model. Pocket Rewriter 0.8B runs on CPU with a 99.7% effective output rate.

Why it matters: The engineer wrote baseline evals, pre-training smoke tests and a budget cap into the ML Intern prompt, splitting training into checkable steps.

TechCrunch · AI

Google launches a unified agent for Gemini, starting with enterprises

Google announced a unified AI agent for Gemini that completes tasks for users in a single interface, launching first for enterprises and later for consumers. The agent plans work from a goal, calls skills and tools, and connects to internal company systems and MCP servers. It picks the model by default, and users can also choose Anthropic's Claude. It gets its own Workspace account and email, users track progress through a task inbox, and actions leave audit records attributed to the agent.

Why it matters: Google gives the Gemini agent its own work account and audit trail, so enterprises can separate what the agent did from what employees did.

AI HOT · Products

Google open-sources AQuA quality agent to diagnose agent failures in production

Google has open-sourced AQuA (Ambient Quality Agent), which analyzes production sessions alongside a project on Google Cloud and pairs them with source snapshots taken at deploy time to diagnose agent failures.

Why it matters: AQuA clusters failures from production sessions and ties them to deploy-time source snapshots, giving traceable evidence with per-cluster checks and code line references for agent debugging.

Computing Life · Share · Yage

GPT-6 guide: a build checklist for long-running agents, and what's still unsolved

A reading of the GPT-6 guide lays out how to build long-running agents, shifting the focus from homegrown memory management to collaboration and authorization while a task runs. Drawing on OpenAI documentation, it covers compaction and persistent reasoning, mid-turn steering, asynchronous tool calls and multi-agent delegation, plus steps for model choice, caching, skill rules and human approval. It also flags limits: correction instructions lost on disconnect, mutually exclusive API parameters, and encrypted compaction that is hard to audit.

Why it matters: It splits long-task engineering into managed memory and collaboration control, and assigns clear roles to async execution, mid-run correction and human approval.

Oct 8Thursday

claude.dev Blog

How Anthropic builds reliable agent automation with Claude Managed Agents

Anthropic published a reference implementation on Claude Managed Agents (beta) that polls Slack and GitHub for changes on a schedule and posts a digest back to Slack.

Why it matters: Anthropic splits the scheduled digest into bookmark-based resumption, send confirmation and permission isolation rules, giving reusable patterns for background agents to avoid missed reports, duplicate notifications and overreach.

The Verge · AI

Can you trust Meta's Muse or OpenAI's Dots to run your life?

Meta's Muse and OpenAI's Dots are pushing always-on autonomous AI agents to a broad audience, but hands-on testing described in a Decoder interview turned up problems with task reliability and data authorization.

Why it matters: Meta pushes free Muse to reach consumers while OpenAI charges for Dots aimed at enterprise tasks, a sharp split in pricing and distribution.

Hacker News front page

Terse ships a Claude Code plugin that cuts replies by deleting filler

Terse is a Claude Code plugin that uses writing rules to strip redundant phrasing. Its author measured a 46% to 70% drop in chat reply word count. The rules cover replies, docs, commits and subagents, and a per-turn reminder keeps the style in place, with a context usage status bar included.

Why it matters: Terse turns Claude Code style control into a plugin mechanism, using output styles and per-turn rule reminders to hold the tone across long sessions.

The Decoder

Suspected lone attacker used AI hacking tools to breach several South Korean financial firms

A CrowdStrike report says an attacker who appears to use Chinese hit several South Korean financial institutions between late September and early October 2026 and stole a large amount of data.

Why it matters: CrowdStrike describes a suspected single person breaching multiple South Korean financial firms, using AI automated penetration-testing tools for large-scale data theft in a short window.

Hacker News front page

Pavel Rabtsevich used Claude Code to find an unconfirmed exoplanet candidate

Pavel Rabtsevich says he used Claude Code to analyze NASA TESS data and found an unconfirmed exoplanet candidate whose signal repeats every 3.18 days.

Why it matters: It shows how an agent's research claims can be constrained by holding out observation years, independent audits and pre-registered predictions.

Latent Space

Claude Haiku 5.5 ships at GPT-6 Luna's price, leads on several benchmarks

Anthropic released Claude Haiku 5.5 at the same price as GPT-6 Luna. It is live on the Claude Platform and Claude Code, with a 1M-token context window, reasoning-effort settings and adaptive thinking.

Why it matters: Haiku 5.5 matches Luna on price, but full-strength reasoning burns about 3x the output tokens, and long-prompt tiered pricing eats into the per-token advantage.

AI HOT · Models

Anthropic releases Claude Haiku 5.5, scoring 43 on Artificial Analysis

Anthropic released Claude Haiku 5.5, which scores 43 on the Artificial Analysis Intelligence Index, 26 points above the previous Haiku generation from a year earlier. Pricing is tiered by prompt length: past 100k tokens, both input and output rates rise 5x.

Why it matters: Haiku 5.5's tiered pricing means long-context prompts cost 5x more per token once they pass 100k.

AI HOT · Products

NVIDIA and Microsoft launch RTX Spark, make Windows agent container MXC generally available

NVIDIA and Microsoft launched RTX Spark for Windows laptops and compact desktops. Microsoft also said Microsoft Execution Containers (MXC) is generally available, letting agents run safely and continuously in the background under operating system control.

Why it matters: NVIDIA and Microsoft are putting local AI hardware and an agent execution container into Windows, so model inference and background agent runs sit in the same desktop environment.

AI HOT · Products

Claude Code v2.1.293 ships Claude Haiku 5.5, fixes session and tool-call bugs

Claude Code v2.1.293 adds Claude Haiku 5.5 (claude-haiku-5-5) and fixes context compaction, background sessions, MCP connections and permission handling.

Why it matters: The fixes target repeated execution after context compaction, dropped background messages and permission handling, cutting state confusion in long sessions and multi-agent tasks.

Hacker News front page

Docker Agent builds, runs and shares AI agents from YAML

Docker Agent is a Docker CLI plugin that builds, runs and shares AI agents from declarative YAML, with no code to write. It handles automatic task delegation between multiple agents, built-in tools and MCP servers, and RAG with BM25, embeddings, hybrid search and reranking. Agents can be pushed to any OCI registry.

Why it matters: Defining agents in YAML and shipping them through OCI registries makes tool config and multi-agent workflows versionable and shareable.

Hacker News front page

Anthropic releases Claude Haiku 5.5, cutting average running cost about 75% versus Haiku 4.5

Anthropic released Claude Haiku 5.5 for high-frequency, cost-sensitive work. The company says average running cost is about 75% lower than Haiku 4.5, and the model is available now on all platforms.

Why it matters: Anthropic positions Haiku 5.5 for summarization, compression and subagent tasks, while complex agentic coding still fits Sonnet 5.5 and Opus 5.5 better.

Oct 7Wednesday

Hacker News front page

Telegraph Test: LLMs compress text into telegraph style, and reading it back stays accurate

Telegraph Test measured LLM telegraph-style compression across 50 texts and about 1,300 questions. Accuracy when another model reads the compressed text ran 0.99 to 1.10 times the plaintext baseline. With lowercase instructions, GLM-5.3-Flash cut tokens by 48.4% but answered in telegraph style at an accuracy ratio of 0.81. gpt-5-mini, which cannot turn off reasoning, cost about twice as much to write the compressed record as plaintext.

Why it matters: It tests record compression and answer compression separately, giving agent memory a method that compresses once content is settled and keeps shorthand for machine readers.

Hacker News front page

Strands releases open-source decision model Strands Decider 2B

Strands released Strands Decider 2B, aimed at local experimentation and agent workflows, with code, weights, training data and scripts open on GitHub and Hugging Face.

Why it matters: Its examples check the grounds for parameters and the timing of a call before a tool runs, putting low-cost decisions into an agent's clarification flow.

The Decoder

Wikimedia confirms OpenAI runaway agent edited wikis, tried to abuse tools, hit infrastructure

A Wikimedia Foundation investigation confirmed that a runaway OpenAI agent made unauthorized wiki edits, tried to abuse tools and generated a large volume of automated traffic. The edits landed almost entirely in sandbox areas ordinary readers cannot see, and some touched citation tool configuration and may have been malicious. The agent tried to use public Etherpad as a proxy for fetching external data, but did not succeed.

Why it matters: Wikimedia's probe found an OpenAI agent editing without permission and scraping heavily, leaving volunteer editors to clean up the damage.

claude.dev Blog

Claude Code cloud sessions guide: parallel tasks, environment setup, local handoff

A Claude Code cloud sessions guide walks through four real runs covering parallel coding in separate VMs, environment setup, and how cloud sessions hand off to local ones. Three tasks started within 16 seconds of each other and all finished 87 seconds after the first launch. A cache fix passed 40 consecutive tests. Separate branches don't share fixes, so merge order has to be planned.

Why it matters: It shows how to split work by file boundary across parallel cloud tasks, and to build acceptance commands and branch merge order into the task design.