Denoise · Twitter

The conversation is shifting from theoretical exploits to production-grade security practices, with @AnthropicAI and @GoogleDeepMind leading the standardization effort.

Major labs are formalizing agent security through responsible disclosures and the publication of red team 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.

A platform shift is underway from IDE plugins to standalone agents, with @AnthropicAI's Claude Code and commentary from @karpathy solidifying this as the new paradigm.

Terminal-native coding agents are emerging as a new developer platform, accompanied by frameworks for systematic prompt optimization.

• 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 infrastructure layer for agents is being built out by @OpenAI, @vercel, and @replit, creating a competitive ecosystem around the agent runtime.

The focus is on standardizing agent deployment and orchestration, with new SDKs, protocols, and managed runtimes being released.

• 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 foundational OCR dataset, while a singular event, signals continued investment in the data pipelines required for advanced multimodal models.

A quiet day, marked only by the release of a large-scale public dataset for web OCR training.

• Mistral AI@MistralAIrising

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

The term 'RAG' is fragmenting into more specialized approaches, with @GregKamradt pushing for context engineering and @mem0ai advocating for distinct memory layers.

The discourse is evolving from simple RAG to more complex 'context engineering' and stateful, 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.

AI is becoming an invisible utility layer in products from @NotionHQ and @linear, moving beyond explicit chat interfaces to drive background automation.

Workspace productivity tools are embedding AI to automate routine tasks like issue triage and database updates.

• 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 industrializing, with platforms like @weights_biases providing empirical data to replace intuition in prompt design.

The emphasis is on moving from artisanal prompt writing to systematic, large-scale benchmarking and optimization of system prompts.

• 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, but the point raised by @jerryjliu0 on synthetic data quality highlights a critical, often overlooked, aspect of building reliable agents.

Discussion touches on the nuances of data curation, specifically filtering synthetic data to improve agent generalization.

• Jerry Liu@jerryjliu0repeated

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