Denoise · Twitter

Actors like @AnthropicAI and @GoogleDeepMind are formalizing agent security, moving it from a theoretical concern to an operational discipline.

Focus is on red-teaming, responsible disclosure, and vulnerability scanning specifically for autonomous agent systems.

• 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.

The battleground is shifting from IDE plugins (Copilot) to standalone agents (Claude Code), with @karpathy and @swyx signaling a major UX change.

A major push towards terminal-native coding agents is underway, with new releases from major labs and benchmarks from the community.

• 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.

A consensus is forming around agent orchestration, with @OpenAI, @LangChainAI, @vercel, and @replit all building solutions for a similar set of problems.

Infrastructure providers are shipping primitives and deployment targets specifically tailored for AI agents' execution and orchestration.

• 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 the agent stack gets most attention, @MistralAI continues to release foundational open datasets, building a different kind of competitive moat.

A single major release of a large-scale, open OCR dataset for model training highlights ongoing work in foundational data.

• Mistral AI@MistralAIrising

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

@GregKamradt, @mem0ai, and @reach_vb signal a move beyond simple vector search towards hybrid memory systems designed for agentic reasoning.

The discourse shifts from simple RAG to more sophisticated 'context engineering' and structured memory architectures 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.

While not explicitly 'agents,' @NotionHQ and @linear are converging on autonomous workflow features, applying agent-like patterns to productivity SaaS.

Workspace automation tools are independently adding AI-powered features for triage and data entry, mirroring agent-like behavior.

• 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 practice of prompting is maturing from anecdotal 'tricks' (@dotey) to systematic, data-driven optimization (@weights_biases).

Attention is on systematic, large-scale benchmarking and the distillation of effective prompt patterns from production data.

• 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.

The focus from @jerryjliu0 on data poisoning reveals a critical, less-discussed dependency for building reliable next-generation agent models.

A single tweet highlights the critical challenge of curating high-quality synthetic data for training robust agent models.

• Jerry Liu@jerryjliu0repeated

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