Denoise · Twitter

The focus is shifting from prompt injection to systemic risks in agent orchestration, as highlighted by @GoogleDeepMind and @AnthropicAI.

Major labs are publishing formal red-teaming frameworks and disclosures for agent-specific 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.

Developer experience is fragmenting from the IDE-centric model towards terminal-first agents, a shift validated by @AnthropicAI and @karpathy.

The primary signal is the release of Anthropic's terminal-native coding agent, Claude Code 1.5, with immediate developer adoption and benchmarks.

• 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 convergence is happening around the agent control plane, with @OpenAI's SDK and @LangChainAI's protocol integration showing a move toward standardization.

A wave of releases from OpenAI, Vercel, and Replit focuses on agent orchestration, deployment, and interoperability protocols.

• 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 a quiet category today, @MistralAI's contribution of a large-scale public dataset continues to fuel open-source alternatives to proprietary multimodal systems.

MistralAI released a massive, cleaned OCR dataset for training multimodal models, a significant contribution to open-source efforts.

• Mistral AI@MistralAIrising

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

The simple RAG pattern is proving insufficient; actors like @mem0ai and @GregKamradt are pushing for more complex, layered memory systems.

Discussion moves beyond simple RAG, focusing on 'context engineering,' advanced memory architectures, and failure modes in massive context windows.

• 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.

Agentic automation is being integrated into existing SaaS products (@NotionHQ, @linear) in parallel with the development of standalone agent platforms.

Workspace automation tools like Notion and Linear are quietly shipping agent-like features for task management and triage.

• 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 practice of prompt engineering is maturing, moving from individual tips (@dotey) to industrial-scale optimization by platforms like @weights_biases.

The focus is on systematic, large-scale benchmarking of prompts rather than individual 'tricks' or anecdotal advice.

• 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.

As agent capabilities grow, the bottleneck shifts to data quality, with experts like @jerryjliu0 focusing on preventing data poisoning during training.

The single signal highlights the critical but often overlooked challenge of curating high-quality synthetic data for agent training.

• Jerry Liu@jerryjliu0repeated

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