Denoise · Twitter

The security focus is shifting from prompt injection within a single model to exploits in the orchestration layer connecting agents to tools and external systems.

Major labs like Anthropic and Google DeepMind are publicly sharing red-teaming frameworks and disclosures for autonomous agent vulnerabilities.

• 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 competition between Anthropic's Claude Code and incumbents like Copilot is moving into the developer's terminal, a new front beyond the text editor.

Anthropic's release of Claude Code 1.5, a terminal-native agent, has triggered direct benchmarks and a wider discussion about displacing the IDE.

• 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 new agent-native infrastructure stack is converging around primitives for tool-calling, multi-worker orchestration, and durable execution (e.g., Temporal, LangChain).

OpenAI, Vercel, and Replit all released infrastructure components for agents, including SDKs, edge runtimes, and deployment harnesses.

• 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.

This category is quiet, with the only signal being a foundational dataset release from Mistral, which enables future work rather than demonstrating a new capability.

Mistral AI released a large, cleaned web OCR dataset to support the training of future multimodal models.

• Mistral AI@MistralAIrising

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

The conversation is maturing from 'RAG is dead' to how to architect sophisticated memory systems (e.g., @mem0ai) needed for stateful agents.

Developers are discussing frameworks beyond simple RAG, focusing on 'context engineering' and multi-layered memory systems 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 workflow automation seen in dedicated agent platforms is now appearing in mainstream SaaS, with Notion and Linear integrating chained updates and auto-triage.

Workspace automation tools like Notion and Linear are releasing agent-like features for auto-filling data and triaging issues.

• 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.

Prompt engineering is maturing into a data-driven discipline, with large-scale studies from players like Weights & Biases replacing smaller, anecdotal guides.

The focus is shifting from anecdotal prompt tricks to systematic, large-scale benchmarking of system prompts to find optimal performance.

• 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.

A quiet day, with a single thread from @jerryjliu0 highlighting the critical but often overlooked problem of data quality poisoning agent training pipelines.

Discussion centered on the difficulty of curating synthetic datasets for agent training, particularly filtering data that harms generalization.

• Jerry Liu@jerryjliu0repeated

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