Denoise · Twitter

@AnthropicAI's Claude Code 1.5 release, supported by @karpathy's observations, solidifies the move to terminal agents as a distinct and impactful developer experience shift.

New product releases and user testimonials indicate a concrete shift towards AI-powered terminal-native coding agents becoming a practical part of developer workflows.

• Anthropic@AnthropicAIrising

  Responsible disclosure on a Claude jailbreak chain we patched last week. Full write-up including our red team timeline.

• 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.

• @levelsio@levelsiorising

  Switched my whole editor setup to Claude Code this week. Shipping faster than when I used Cursor + Copilot.

@OpenAI, @vercel, and @replit are converging on providing core primitives for agent deployment and multi-worker orchestration, defining a new critical layer of AI infrastructure.

Major players are releasing SDKs and platforms to support the deployment and orchestration of autonomous AI agents, establishing a new infrastructure layer.

• OpenAI@OpenAIrising

  New agent SDK: protocol-level tool calling, deployment harness, and multi-worker orchestration primitives. Docs live.

• Vercel@vercelrising

  Edge runtime for agent workers is live. Spawn durable background agents from any serverless deployment.

• Replit@replitrising

  New agent deployment harness. One command to go from local orchestration to hosted agent worker.

• Temporal@temporaliorepeated

  Orchestrating agents with durable workflows: replayable, resumable, and multi-worker by default. Walkthrough from our infra team.

• Jerry Liu@jerryjliu0repeated

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

The development of tools like DSPy 3.0 by @dspy_ai and large dataset releases by @MistralAI indicate a structured approach to prompt optimization and data quality as key performance drivers.

Efforts are focusing on optimizing prompts and curating high-quality datasets to improve AI model performance, generalization, and benchmark integrity.

• Mistral AI@MistralAIrising

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

• DSPy@dspy_airising

  DSPy 3.0: prompt optimization via compile-time search over system prompt variations. Benchmarks inside.

• Notion@NotionHQrising

  Notion workspace automation is out of beta. Auto-fill tables, chained updates across databases, and a new audit log surface.

• 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.

@reach_vb and @GregKamradt highlight advanced context engineering and the limitations of traditional RAG, pointing towards new architectures for effective agent memory management.

Discussions on agent memory extend beyond simple RAG, exploring more sophisticated context management, caching, and recall mechanisms to address emerging 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.

• LangChain@LangChainAIrising

  MCP protocol integration thread. How to wire existing LangGraph agents into the Anthropic Model Context Protocol server spec.

• 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.

• Jason Liu@jxnlcorepeated

  Vector db beauty contest. Ran 50k RAG queries against 6 vendors. Results inside, free.

@GoogleDeepMind and @AlexAlbert__ are defining new attack vectors and mitigation strategies for agent jailbreaks and security exploits at the orchestration layer, beyond application code.

The focus is on developing red teaming frameworks and identifying vulnerabilities specific to autonomous agents and their orchestration layers, including prompt injection.

• Google DeepMind@GoogleDeepMindrising

  New red team framework for prompt injection in autonomous agents. Covers cross-tool leakage, scanner evasion, and sandbox escape patterns.

• 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.

• 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.

@linear's auto-triage feature demonstrates practical AI integration into existing workflows, contrasting with the successful, focused personal tools highlighted by @BenAAndrew.

Specific applications are integrating AI to automate tasks within existing workflows, while individual developers continue to ship focused, smaller tools.

• Linear@linearrising

  Linear now auto-triages incoming issues. Quiet launch, but already our favorite workspace feature of the year.

• James Clear@jamesclearrepeated

  The best habit tracker is the one you actually open. Three open-source alternatives worth trying.

• Ben Andrew@BenAAndrewrepeated

  The sourdough app I shipped in 48 hours is now my most-used side project. Source and write-up linked.