Denoise · Twitter

The security focus is shifting from single-prompt model vulnerabilities to systemic risks in agent orchestration and tool interaction, a concern shared by @AnthropicAI and @GoogleDeepMind.

Major AI labs are publishing red-teaming frameworks and responsible disclosures for complex agent 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.

The frontier of AI coding tools is moving from in-editor assistants to standalone, stateful terminal agents, a fundamental paradigm shift articulated by @karpathy and benchmarked by @swyx.

Anthropic's Claude Code 1.5 release has catalyzed a discussion on terminal-native agents replacing IDE-based 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.

OpenAI's agent SDK and Vercel's edge runtime signal convergence towards durable, orchestrated agents as a new core cloud primitive, moving beyond stateless function calls.

A wave of releases from OpenAI, Vercel, and Replit sketches out the emerging standardized stack for deploying and orchestrating 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.

A quiet day for this category, with the only notable event being a foundational data release from Mistral AI rather than new on-device techniques or multimodal models.

Mistral AI released a large, cleaned web OCR dataset for public use in training models.

• Mistral AI@MistralAIrising

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

The conversation is shifting from 'retrieval' to 'context engineering,' with actors like @GregKamradt and @mem0ai advocating for multi-layered memory architectures over simple vector retrieval.

Developers are designing more sophisticated memory systems for agents, questioning the sufficiency of basic RAG.

• 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 the AI infrastructure layer focuses on agent primitives, established SaaS products are shipping tangible, high-level automation features, showing two layers of the same trend.

Workspace automation continues to be a major feature push for SaaS platforms like Notion and Linear.

• 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 organizations like @weights_biases running massive experiments to map the efficient frontier of prompt design.

The focus is on systematic, large-scale benchmarking to find optimal system prompts, moving beyond anecdotal tricks.

• 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 conversation around agent training data emphasizes quality over quantity, flagging the risk of synthetic data that looks plausible but poisons model generalization.

A single tweet from @jerryjliu0 highlights the critical challenge of curating high-quality synthetic data for training agents.

• Jerry Liu@jerryjliu0repeated

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