Denoise · Twitter

The discourse is maturing from generic model safety to specific agent attack surfaces, with Anthropic and Google DeepMind leading public documentation.

Major labs are publicly disclosing red-teaming frameworks and patched jailbreaks for AI agents, signaling a focus on autonomous system 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 new competitive front between Anthropic's Claude Code and OpenAI's offerings is the terminal-based agent experience, not just IDE autocompletion.

Anthropic launched a terminal-native coding agent, sparking debate on a fundamental shift away from traditional IDE workflows toward agentic development.

• 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 stack is forming: OpenAI/Anthropic provide primitives, LangChain provides frameworks, and Vercel/Replit provide the runtime.

OpenAI's new agent SDK arrived alongside dedicated deployment targets from Vercel and Replit, creating a full stack for agent orchestration.

• 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.

The primary contribution from open-source players in the multimodal space remains foundational dataset creation, a prerequisite for capable models.

MistralAI released a large-scale, open web OCR dataset for training vision models.

• Mistral AI@MistralAIrising

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

A consensus is forming around multi-layered memory systems (e.g., working vs. long-term store), moving beyond single vector indexes.

The conversation is elevating from simple RAG to 'context engineering,' with new frameworks for sophisticated agent memory management.

• 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 software patterns are becoming integrated into SaaS, with orchestration tools like Temporal providing the underlying durable execution model.

Mainstream workspace tools like Notion and Linear are shipping agent-like automation features for tasks like data entry and issue 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.

Prompt engineering is maturing into a data-driven discipline, with platforms like Weights & Biases enabling optimization across thousands of variants.

Attention is shifting from anecdotal prompt 'tricks' to systematic, large-scale benchmarking of system prompts to find optimal configurations.

• 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.

For advanced agent training, the key bottleneck is shifting from raw compute to the quality and safety of synthetic training data.

Practitioners are focused on the challenge of curating high-quality synthetic data for training agents, highlighting filtering and generalization issues.

• Jerry Liu@jerryjliu0repeated

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