Denoise · Twitter

The focus from @AnthropicAI and @GoogleDeepMind on agent-specific attack vectors implies a new class of security risks is emerging beyond traditional prompt injection.

Major AI labs are now publicly releasing red-teaming frameworks and vulnerability disclosures specifically for autonomous agents.

• 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 convergence of @AnthropicAI's product and @karpathy's commentary consolidates the terminal, not the IDE, as the primary interface for next-generation coding agents.

Anthropic's release of Claude Code 1.5, a terminal-native agent, dominates the conversation, signaling a significant shift in developer workflows.

• 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 de-facto stack is converging where @OpenAI provides the SDK, @vercel provides the runtime, and @LangChainAI provides the interoperability layer.

A full stack for agent deployment is rapidly emerging, with OpenAI, Vercel, and Replit all shipping new infrastructure primitives.

• 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 headlines, @MistralAI's foundational dataset release shows that the parallel track of curating data for future multimodal models remains critical.

Mistral AI contributes to the open-source community with the release of a large-scale web OCR dataset.

• Mistral AI@MistralAIrising

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

The work of @GregKamradt, @mem0ai, and @reach_vb reveals a growing consensus that vector retrieval alone is an insufficient memory model for capable agents.

The conversation is evolving from simple RAG to more sophisticated 'context engineering' and structured memory systems for stateful 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 approaches of @NotionHQ and @linear suggest a different product philosophy for agents: 'invisible' automation within existing workflows, rather than conversational, explicit agents.

Workspace automation tools from Notion and Linear are adding AI-powered features, mirroring the agent-driven trend in a business productivity context.

• 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 to benchmark 40k prompt variants refutes the 'magic prompt' narrative, pushing the practice towards a more rigorous engineering discipline.

The focus in prompt engineering is shifting from anecdotal tricks to systematic, large-scale benchmarking to find optimal configurations.

• 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 point from @jerryjliu0 on filtering synthetic data implies that data quality, not just quantity or model size, is becoming the key bottleneck for improving agent generalization.

The primary challenge discussed in agent training infrastructure is the curation of high-quality datasets to avoid performance degradation.

• Jerry Liu@jerryjliu0repeated

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