Denoise · Twitter

A convergence is visible between Anthropic and GoogleDeepMind, who are both publicizing research into agent attack surfaces at the same time as agent capabilities are being released.

Attention is shifting to securing autonomous agents, with major labs releasing red teaming frameworks and disclosing agent-specific jailbreaks.

• 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.

@karpathy's framing of the IDE-to-terminal shift provides the narrative for the direct competition between Anthropic's new tool and the established Copilot/Cursor stack.

The release of Anthropic's Claude Code 1.5 establishes the terminal-native agent as a new product category, with early adoption signals.

• 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's a convergence on making agents deployable infrastructure primitives, with PaaS providers like Vercel and Replit building dedicated runtimes, and protocol-level efforts from OpenAI.

A wave of new tools for agent orchestration and deployment has arrived from OpenAI, Vercel, and Replit, signaling a battle for a new infrastructure layer.

• 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 agentic workflows dominate the discourse, this release from MistralAI shows that foundational work on curating large-scale, high-quality public data remains critical.

MistralAI released a massive open dataset for web OCR, contributing a foundational resource for training multimodal models.

• Mistral AI@MistralAIrising

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

Practitioners like @GregKamradt and tools like @mem0ai and @llamaindex are pushing beyond simple retrieval, indicating a market need for more sophisticated context management solutions.

The conversation around RAG is evolving into a more nuanced discussion of 'context engineering,' focusing on memory architectures and cache management.

• 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.

This trend shows a parallel path to agent adoption: instead of building new agentic systems, Notion and Linear are embedding autonomous capabilities directly into established user interfaces.

Major workspace tools like Notion and Linear are shipping sophisticated, agent-like automation features for existing productivity 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.

The contrast between @dotey's tactical advice and @weights_biases's large-scale benchmark report highlights the maturation of prompt engineering into a more rigorous, data-driven discipline.

The focus in prompt engineering is shifting from anecdotal tricks to systematic, large-scale benchmarking and optimization.

• 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.

@jerryjliu0's note serves as a crucial reminder that underlying the performance of all new agent systems is a difficult and often overlooked data curation problem.

A focus on high-quality data curation, especially filtering synthetic data, is highlighted as critical for training effective agents.

• Jerry Liu@jerryjliu0repeated

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