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.

1,789 picksRelated topicsMCP & tool useAI codingReasoning

Latest picks

41–60 of 1,789

Nov 11Wednesday

The Verge · AI

Google releases Gemini 4 Carbon to paid developers, enterprises and AI Ultra subscribers

Google released Gemini 4 Carbon to paid developers, enterprises and Google AI Ultra subscribers, aimed at complex multi-step coding and open-ended scientific research. Google also previewed a swarm feature in Antigravity that turns a single prompt into a team of agents working together.

Why it matters: Google set Gemini 4 Carbon's token pricing below frontier competitors, though total task cost still depends on how many tokens the model consumes.

Nov 10Tuesday

Google DeepMind

Google DeepMind unveils AlphaProof Code, formally verifying Signal's core crypto code

Google DeepMind published AlphaProof Code, a multi-LLM agent framework that formally verified key security properties of Signal's core cryptographic code in four weeks. The work moves formal verification from the protocol design to the actual implementation.

Why it matters: DeepMind pushes Signal's formal verification from protocol design down to real code, covering the design-to-implementation gap where bugs tend to hide.

Latent Space

Anthropic opens IPO roadshow, Claude Fable 5.2 tops LLM leaderboard

Anthropic started its IPO roadshow on Monday and released Claude Fable 5.2 and Claude Mythos 5.2. Fable 5.2 ranks first on the Artificial Analysis Intelligence Index v5 with 65 points.

Why it matters: Fable 5.2 cuts the price per token by 20%, yet GDPx cost per task rose from $67.16 to $88.15.

Hacker News front page

CPython formalization project uses AI agents to model code in Lean, files 418 bug reports

The CPython formalization project used Opus 5.5 to rewrite CPython 3.15.2 functions line by line in Lean. So far 4,071 functions have passed tests, formal verification and independent agent review, 15.7% of the functions to be checked.

Why it matters: The project pairs line-by-line modeling with differential testing and independent review, using real runs to check whether formal conclusions miss exception and memory behavior.

Hacker News front page

Fable 5.2 builds a nephew's dream game in one run, then scales to 18 characters

lexandstuff tested Claude Code with Fable 5.2, starting from a nephew's design sketches and existing game code. One run produced a playable 12-level side-scrolling action game. The model rewrote most of the code, generated about 175 images and 140 audio clips, and wrote a bot that played all twelve levels in a headless browser and checked screenshots.

Why it matters: The model wrote a bot that played all twelve levels in a headless browser and checked screenshots, using automated play and visual checks as basic tests for a generated game.

Hacker News front page

Google launches TPU 8tx and TPU 8i Max for confidential inference and ultra-long context

Google expanded its eighth-generation TPU lineup with TPU 8tx for secure confidential inference and TPU 8i Max for ultra-long context. TPU 8tx uses the same chip as TPU 8t and adds hardware-level protection for data and model weights, cutting latency to as little as half of TPU 8t. It supports fine-tuning on private data, knowledge distillation and reinforcement learning.

Why it matters: Google built specialized TPU systems by reusing an existing chip and changing security, networking and memory settings, shortening hardware adaptation from years to months.

claude.dev Blog

Anthropic's Claude model guide: choosing between Fable, Opus, Sonnet and Haiku

Anthropic's selection guide says most coding and knowledge work should start with Claude Opus 5.5 at medium thinking effort, moving to Sonnet 5.5, Haiku 5.5 or Fable 5.2 as task difficulty changes. It frames model choice around the cost of finishing a task: set up automated acceptance checks first, then adjust thinking effort or step up a model, and hand easy-to-verify side tasks to smaller models.

Why it matters: Anthropic splits Claude selection into model, thinking effort and cost per finished task, and proposes automated acceptance checks plus reruns on failure to control spend.

claude.dev Blog

Anthropic runs 1,000 Claude Fable 5.2 agents to formalize Fermat's Last Theorem in 28.7 hours

In a small experiment, Anthropic had 1,000 agents running an early Claude Fable 5.2 reproduce a formal proof of Fermat's Last Theorem in 28.7 hours. The team gave no Prove2Me or researcher guidance, only 60 lemmas to prove, short route hints, definitions and 47 previously proved lemmas. The agents coordinated through Git and a shared database, using a third of the original work's output tokens for a proof one-seventh as long.

Why it matters: Anthropic let a thousand agents split and coordinate work through a shared database and Git, keeping large-scale collaboration inside isolated sandboxes and two-layer monitoring.

Hacker News front page

Meta releases Muse Ember, a small efficient model for high-frequency agent tasks

Meta released Muse Ember for tool calling, coding subtasks, routing, information extraction and long-document parsing. It is available now as muse-ember-1.0 in Muse Code and the Meta Model API.

Why it matters: Meta's Muse Ember targets repetitive agent tasks, offering lower cost per task at an intelligence index close to Muse Spark 1.3.

The Verge · AI

Anthropic releases Claude Fable 5.2 and Claude Mythos 5.2

Anthropic announced Claude Fable 5.2 and Claude Mythos 5.2, citing gains in coding, reasoning and vision and faster output than version 5.1. In pre-release tests, the company says, the two models helped complete software migrations, designed 3 working electronic devices from scratch, solved 2 open problems in black hole physics and formalized a proof of Fermat's Last Theorem within 30 hours.

Why it matters: Anthropic set different access scopes for the two models: Fable is live today, while Mythos is initially limited to vetted organizations.

Computing Life · Share · Yage

Agent harness techniques tested: which framework designs raise scores and which just raise cost

Controlled experiments from Surge AI and FireFlash show coding agents can improve through deeper single-model reasoning, test and goal-check gates, and a reworked terminal pipeline. In Surge AI's run, Compound Engineering lifted cost to 8x baseline while the score moved only from 31.1 to 32.9. Claude Opus 5.5 with higher thinking settings reached 42.4 at 3.5x baseline cost.

Why it matters: The two teams break down the cost and payoff of agent harness techniques, comparing multi-agent collaboration, deeper single-model thinking and terminal pipeline changes.

Nov 9Monday

Computing Life · Share · Yage

Kimi and Zhipu align hosted agent APIs with Claude's, so is the protocol race already over?

Kimi Hosted Agents and Zhipu's Z Managed Agents both follow the four-part control plane of Claude Managed Agents, splitting role, environment, session and event. The article reads this as protocol convergence among hosted agents and weighs what it means for picking a vendor.

Why it matters: Kimi and Zhipu adopting Claude's four-part hosted interface gives long-running tasks a client abstraction that carries across vendors.

Latent Space

Stanford's AI-native engineering course: Mihail Eric on CS146S and Monaco's agent setup

Mihail Eric explains how Stanford's CS146S trains AI-native software engineers and how the course was designed alongside Monaco's team practice. The 10-week course covers coding agent internals, context engineering, skills, code review and security, and adds an open-source contribution assignment where maintainers review student patches. Monaco picked Devin after evaluating code review products, and built its own agent workspace on its cloud so background agents run the product, reproduce bugs and test patches.

Why it matters: Eric put open-source contribution into the Stanford course, with maintainers reviewing student patches so design skills are trained on real project discussion and code feedback.

Nov 8Sunday

Hacker News front page

Apiiro finds Claude Code's "don't ask again" setting exposed credentials in 1,122 public GitHub files

Apiiro found that Claude Code's "don't ask again" option writes the full command, credentials included, into .claude/settings.local.json. On GitHub, 1,122 public files contain such secrets.

Why it matters: The study traces how credentials in approved commands land in project config files, and shows that scanning for key formats misses plain passwords inside commands.

Hacker News front page

MaxxBench tests whether DeepSWE's high scores survive altered tasks

MaxxBench changed the requirements or starting code of 89 DeepSWE tasks to see whether coding agents adapt to the changes. It found some models favor guessing at hidden tests. Models that scored close together on the original tasks diverged sharply after the edits.

Why it matters: Small edits to familiar tasks split models that had looked equal, adding requirement adaptability as a way to compare coding ability.

Computing Life · Share · Yage

GDPx real-workstation review: six engineering lessons from AI running 8 hours straight

SemiAnalysis's GDPx benchmark has models use vendor agent frameworks to solve 206 real business problems in up to 8 hours. The strongest model averages about 12%. The article draws six engineering lessons from the failures: build a document authority map, set an independent rollback gate, write deterministic measurement scripts, keep an external evidence ledger, check the eval environment, and route by total cost per task.

Why it matters: It turns long-horizon failures on GDPx into engineering practice, folding document authority tagging, independent rollback checks and an external evidence ledger into agent workflows.

Nov 7Saturday

The Verge · AI

AI has scrambled cybersecurity defenses. How does Alex Stamos see the next step?

In a Decoder interview, Cognition chief security officer Alex Stamos said AI is lowering the bar for attackers and speeding up exploit development. Cybersecurity faces a stretch of adapting to new attack and defense conditions.

Why it matters: Stamos proposes a layered model for handling security alerts and limiting agent permissions, putting defense cost control and automated response risk into one operating plan.

Hacker News front page

Perplexity launches Teammates, AI agents for long-running work

Perplexity launched Teammates, which coordinates AI agents and ongoing projects inside Computer. It plans tasks, watches for changes and submits results for user review. Teammates remembers project goals, task history and shared files, connects to Slack, GitHub or Gmail, and runs in an isolated environment with per-tool and per-project permissions. It is available first to Perplexity Max subscribers on the web, with iOS coming soon.

Why it matters: Teammates bundles continuous monitoring, task memory and cross-agent coordination so teams can hand off long projects and review the work as it runs.

Nov 6Friday

Hacker News front page

Tencent releases Hy4 with vision understanding and computer operation, plans to open model weights

Tencent released Hy4, a new large language model that adds vision understanding and computer operation. The company says it will publish the model weights and a system card in the coming days. Hy4 improves instruction following, long-context understanding and long-horizon agent tasks, and is already live in WorkBuddy, CodeBuddy and Tencent Cloud TokenHub.

Why it matters: Hy4 adds vision and computer operation while keeping Hy4 Preview pricing, so the wider task range comes without a higher standard call price.