Denoise · Twitter

The security conversation, led by actors like Anthropic and Google DeepMind, is happening in lock-step with agent development, indicating the industry is treating agent security as a foundational requirement.

Major labs are releasing formal red-teaming frameworks and disclosures for autonomous agents, focusing on vulnerabilities in orchestration and tool interaction.

• Anthropic@AnthropicAIrising

  Responsible disclosure on a Claude jailbreak chain we patched last week. Full write-up including our red team timeline.

• Google DeepMind@GoogleDeepMindrising

  New red team framework for prompt injection in autonomous agents. Covers cross-tool leakage, scanner evasion, and sandbox escape patterns.

• MalwareTech@MalwareTechBlogrepeated

  Autonomous agent running pentest flows against a real SaaS. First real-world run: fewer false positives than I expected on the vulnerability surface.

A direct competition is forming between Anthropic's terminal-centric Claude Code and the existing IDE-integrated Copilot/Codex ecosystem, with developer workflow as the battleground.

Anthropic's release of Claude Code 1.5 as a terminal-native agent dominates the conversation, with immediate benchmarks and user testimonials appearing.

• Anthropic@AnthropicAIrising

  Claude Code 1.5 is live. Terminal-native coding agent with full Claude Opus reasoning, file-ops sandbox, and session replay.

• Andrej Karpathy@karpathyrising

  The developer-experience shift from IDE to terminal agent is underrated. Coding workflows are about to look nothing like 2024.

• swyx@swyxrising

  Codex vs Claude Code terminal agent benchmarks. Pass@1 diverges more than I expected on the long-context editor tasks.

• DSPy@dspy_airising

  DSPy 3.0: prompt optimization via compile-time search over system prompt variations. Benchmarks inside.

• @levelsio@levelsiorising

  Switched my whole editor setup to Claude Code this week. Shipping faster than when I used Cursor + Copilot.

There is a clear convergence towards a standardized agent deployment stack, with OpenAI defining protocols and platforms like Vercel and LangChain providing the runtime and integration layers.

Key infrastructure providers like OpenAI, Vercel, and Replit are shipping orchestration and deployment primitives specifically for agents.

• OpenAI@OpenAIrising

  New agent SDK: protocol-level tool calling, deployment harness, and multi-worker orchestration primitives. Docs live.

• LangChain@LangChainAIrising

  MCP protocol integration thread. How to wire existing LangGraph agents into the Anthropic Model Context Protocol server spec.

• Vercel@vercelrising

  Edge runtime for agent workers is live. Spawn durable background agents from any serverless deployment.

• Alex Albert@AlexAlbert__rising

  When your security scanner finds nothing scary on an agent deploy, check the orchestration layer again. That's usually where the jailbreak sneaks through.

• Replit@replitrising

  New agent deployment harness. One command to go from local orchestration to hosted agent worker.

While agents dominate the discussion, foundational dataset releases from players like Mistral AI are a quiet but critical enabler for the next generation of model capabilities.

Mistral AI released a large, cleaned web OCR dataset, providing a foundational asset for training future multimodal models.

• Mistral AI@MistralAIrising

  Open dataset release: 100M-row web OCR dataset. Cleaned, licensed, ready to train.

The simple vector-search RAG pattern is being challenged by more complex architectures from mem0ai and LlamaIndex, indicating a shift towards 'context engineering' as a distinct discipline.

The discourse is moving beyond large context windows to focus on structured memory systems and sophisticated retrieval logic for agents.

• Vaibhav Srivastav@reach_vbrising

  Tested the new 10M context memory window end to end. Surprising failure modes around rag retrieval cache invalidation, thread below.

• Greg Kamradt@GregKamradtrising

  RAG is dead, long live context engineering. My framework for when to cache, when to retrieve, and when to just dump memory into the prompt.

• mem0@mem0airising

  Memory layer for agents: differentiating working memory from the subconscious store. Vector index isn't enough anymore.

• LlamaIndex@llamaindexrepeated

  Knowledge graph retrieval walkthrough: when semantic vector search misses, graph hop beats it every time.

The pattern of autonomous orchestration is not confined to developer tools; product companies like Notion and Linear are shipping it as user-facing features, suggesting a broader trend.

Workspace automation features from Notion and Linear mirror the agent trend, applying autonomous task completion to business workflows.

• Notion@NotionHQrising

  Notion workspace automation is out of beta. Auto-fill tables, chained updates across databases, and a new audit log surface.

• Linear@linearrising

  Linear now auto-triages incoming issues. Quiet launch, but already our favorite workspace feature of the year.

• Temporal@temporaliorepeated

  Orchestrating agents with durable workflows: replayable, resumable, and multi-worker by default. Walkthrough from our infra team.

• James Clear@jamesclearrepeated

  The best habit tracker is the one you actually open. Three open-source alternatives worth trying.

Prompting is industrializing. The work by Weights & Biases shows a move towards treating prompt optimization as a rigorous search problem, not an art form.

Efforts are shifting from sharing individual prompt tricks to systematic, large-scale benchmarking of system prompts across multiple models.

• dotey@doteyrising

  Five prompt tricks learned this week from reviewing 200 production prompts. Short thread.

• Weights & Biases@weights_biasesrising

  System prompt benchmarking at scale: we ran 40k variants across 6 frontier models. The efficient frontier is not where you think.

As agent capabilities advance, the bottleneck is shifting from model architecture to data quality. Jerry Liu's point highlights the emerging challenge of synthetic data poisoning.

The focus is on the critical need for high-quality dataset curation, specifically for filtering synthetic data used in agent training.

• Jerry Liu@jerryjliu0repeated

  Dataset curation for agent training: how we filter synthetic data that looks good but poisons generalization.