Denoise · Twitter

The conversation is shifting from theoretical prompt injection to practical, automated pentesting and orchestration-layer vulnerabilities, as highlighted by @GoogleDeepMind and @MalwareTechBlog.

Security research is focusing on autonomous agents, with major labs releasing red teaming frameworks and jailbreak disclosure write-ups.

• 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 primary competition in AI coding is consolidating around terminal-based agents like Anthropic's Claude Code, a trend validated by @karpathy.

Major players released terminal-native coding agents, sparking immediate adoption and benchmarking from the developer community.

• 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 clear convergence is happening as @OpenAI, @vercel, and @replit all race to provide the platform for deploying and managing agents.

The infrastructure layer for AI agents is rapidly maturing with new SDKs, deployment harnesses, and orchestration 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.

@MistralAI continues its strategy of releasing high-quality, foundational open datasets, this time targeting a core multimodal capability.

A single, large-scale open dataset for web OCR was released, targeting multimodal model training.

• Mistral AI@MistralAIrising

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

The focus is shifting from simple vector retrieval towards structured memory systems (@mem0ai) and explicit context management frameworks (@GregKamradt).

Developers are evolving RAG into more sophisticated context engineering to manage massive context windows and their failure modes.

• 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.

Non-AI-native tools like @NotionHQ and @linear are integrating agent-like automation, showing a broader trend of 'workflow agents' beyond developer tools.

Workspace automation tools are adding AI-powered features for auto-triaging and chained 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.

The craft of prompt engineering is being industrialized, with platforms like @weights_biases providing tools for large-scale A/B testing of system prompts.

The focus is on systematic, large-scale benchmarking of production prompts to discover effective, generalizable patterns.

• 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 quality of synthetic data, not just quantity, is emerging as a key bottleneck for agent training, a point emphasized by @jerryjliu0.

Discussion centers on the critical but difficult problem 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.