Denoise · Twitter

The focus on agent security from day one by @AnthropicAI and @GoogleDeepMind signals a maturing industry where safety is co-developed with capability, not bolted on later.

Major AI labs and security researchers are publicly disclosing agent vulnerabilities and releasing red-teaming frameworks.

• 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 releases from @AnthropicAI and @dspy_ai, combined with commentary from @karpathy, show a convergence on the terminal as the new de-facto interface for agent-driven development.

Anthropic's launch of Claude Code 1.5, a terminal-native agent, is driving conversation about a fundamental shift in developer workflows away from traditional IDEs.

• 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 clear pattern of convergence is visible, with @OpenAI, @LangChainAI, and @vercel all building infrastructure around agent orchestration, establishing the agent as a core compute primitive.

Major platforms including OpenAI, Vercel, and Replit are shipping SDKs, protocols, and runtimes specifically for building and deploying autonomous 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.

@MistralAI's release of a 100M-row dataset reinforces its strategy of providing foundational open resources to compete with closed-ecosystem players.

Mistral AI continued its pattern of supporting the open-source community by releasing a massive, cleaned dataset for web OCR.

• Mistral AI@MistralAIrising

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

The discourse from @reach_vb, @GregKamradt, and @mem0ai shows the toolchain is evolving beyond vector search to support stateful, multi-layered memory architectures for agents.

With massive context windows now available, the conversation is shifting from simple RAG to 'context engineering' to manage complex memory and caching challenges.

• 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 auto-triage from @linear and automation in @NotionHQ mirror the agent trend, while @temporalio explicitly connects its durable workflow engine to the agent orchestration problem.

Workspace automation tools are becoming more intelligent, while durable execution frameworks are positioning themselves as ideal for agent orchestration.

• 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 work from @weights_biases on systematic prompt benchmarking shows the discipline is maturing from a manual craft to a more data-driven, empirical science.

Prompt engineering is shifting toward systematic, large-scale benchmarking to discover non-obvious performance patterns.

• 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 insight from @jerryjliu0 reveals that behind agent performance gains lies a crucial but often invisible data infrastructure challenge: filtering synthetic data effectively.

A practitioner highlighted the critical need for careful synthetic data curation when training agents to avoid poisoning generalization.

• Jerry Liu@jerryjliu0repeated

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