#Engineering

Tessl Blog discussed key design decisions for building cross-company AI agent memory systems.

Tessl Blog published key design decisions for building cross-company AI agent memory systems, proposing to store statements rather than data blocks, explicitly express time and missing states, and determine permissions before model execution.

From Standalone Coding Tools to Development Platforms: How Trust Affects the Adoption of AI Code Assistants

Engineering teams' trust in AI code assistants determines their scope of use, ranging from viewing code differences to full authorization for merging. Trust is built through rapid validation mechanisms. Development platform costs increase with the intensity of AI agent work, with about 80% of the budget consumed by 20% of heavy users, requiring an evaluation of the effective cost per unit of work. Successful teams start with auxiliary tasks and gradually expand the scope of AI, rather than applying it directly to core systems.

llm-d 1.0 Released: Strengthening Open Source AI Inference Production Environment

The llm-d project announces the release of version 1.0, which is a Kubernetes-native distributed inference service network that supports deploying any model's inference stack on any accelerator in any cloud. This version enhances multi-tenant quality of service, zero-downtime operations, and agent-aware services to achieve continuous performance in common production operations. Through techniques such as prefix cache-aware routing and KV cache offloading, llm-d 1.0 can capture 97% of available cache reuse, reducing the cost of large-scale AI services.

Lovable Enterprise 10 October Feature Update: Supports local cloud deployment, brings key encryption, and EU reasoning

Lovable Enterprise now supports deploying applications and data in user-built AWS or Azure cloud accounts, encrypting chats and project history with the 'Bring Your Own Key' feature, and introducing an EU reasoning option that confines AI request processing within the EU. The Enterprise version also introduces the 'Organization' feature, allowing central IT teams to manage identity authentication, SSO/SCIM configuration, and cross-workspace auditing centrally, while also supporting a workspace policy approval mechanism to control application release processes.

AnyLanguageModel 1.0 is released: supporting local model advancements on Apple platforms for a year.

AnyLanguageModel 1.0 is released, supporting local model advancements on Apple platforms for a year. New support added for cloud models such as OpenAI Chat Completions, Anthropic Messages, and Google Gemini. Local model support includes llama.cpp, MLX, and Core ML. Tool calling and guided generation features are expanded. Cloud models have the same functionality as local models, and API keys support dynamic acquisition through closures.

How does Claude design protein binders for scorpion neurotoxins?

Claude autonomously generated and screened 318,484 protein designs in 64 hours, selecting 180 for testing, and collaborated with Adaptyv Bio and Twist Bioscience to experimentally validate 211 designs, of which 17 met the binding criteria. All design data has been made public. Experts consider this the first AI design attempt for scorpion neurotoxins, which could accelerate drug discovery for neglected diseases.

PyTorch 2.15 brings FP8 and faster LLM decoding to the MPS backend.

The Hugging Face PyTorch team introduces updates to the MPS backend in PyTorch 2.15, adding the tensor torch.float8_e4m3fn and F.scaled_mm, with FP8 tensors occupying half the space of BF16.

How do the open standards of the Coral NPU unify edge AI and achieve portable, energy-efficient intelligence?

Coral NPU has released a complete 32-bit architecture, including new matrix execution units, supporting up to 1 TOPS performance and 10mW average power consumption; launched the Coral Compiler v1.0 based on IREE/MLIR.

Arm used Google AI Edge Model Explorer to add visual graph debugging features to custom edge compilers.

Arm leveraged the hierarchical graph visualization and plugin architecture of Google AI Edge Model Explorer to develop open-source adapters supporting formats such as TOSA, VGF, and PTE, helping developers more easily inspect edge model conversion processes.

How does Browser Harness allow Claude Code and similar tools to execute tasks through a real Chrome browser?

Browser Harness achieves a score of 60.4 in matching evaluation using 2.1M median input tokens, matching Playwright MCP and Chrome DevTools MCP, becoming the browser control tool with the lowest cost per task at $0.042. Playwright MCP and Chrome DevTools MCP are faster but use more tokens.

Hugging Face launches TorchTPU: Native PyTorch backend support for TPU

Hugging Face has released TorchTPU, making TPU a native backend device for PyTorch. Transformers, Diffusers, and Kernels can now run directly on TPU. Users only need to select a model from the Hugging Face Hub and specify device_map="tpu".

Meta introduces GenRecs Tokenization to reshape ad recommendations with a stable model vocabulary.

GenRecs Tokenization enhances conversion rates by 0.35% for advertisers by representing items like ads and products with a stable semantic vocabulary, combined with Meta's Generative Ad Model (GEM) and adaptive ranking model. This technology leverages the world knowledge of pre-trained large models to enable recommendation systems to understand preferences of new items or users with no historical interaction, accelerates learning through shared concepts, achieves cross-activity transfer, and improves performance as large model scale increases, forming a feedback loop for performance improvement.

How Meta engineers improve the reliability of AI agents by streamlining routers.

Meta engineers built a lean router with 1,300 lines to assign over 20 workflows to 14 specialized AI agents, with the router itself not performing any domain-specific tasks, significantly improving the efficiency and accuracy of data pipeline agents.

ContextCue project explores how AI can improve collaboration and context understanding in distributed teams

prime-rl v0.10.0 released: Improving training speed, introducing new RL loss IPO, and unifying the evaluation stack

prime-rl v0.10.0 has been released, defaulting to the new RL algorithm IPO to improve the stability of asynchronous RL and optimize performance. It supports new models such as Qwen3.8 Flash, and increases training throughput by 1.15 times (based on the torchtitan platform) through MoE optimization and custom kernels.

Build a 'never silent' voice agent using ADK and Gemini 3.8.

Using ADK and Gemini 3.8, non-blocking voice interaction is implemented through streaming tools and asynchronous functions, reducing the first response time of the sales report workflow from 14.4 seconds to 1.2 seconds, supporting zero silence, progress updates, and parallel conversations.

Together Post-Training: Flexible and efficient model fine-tuning service

Together AI has launched Post-Training services, supporting the construction of custom models through reinforcement learning and supervised fine-tuning without complex infrastructure. The service provides flexible training loop definition capabilities and optimizes the underlying system and infrastructure to improve model quality and training speed. It supports mainstream open-source models such as Muse Spark Open, GLM 5.3, Kimi K3, and Qwen 3.8-27B, running on dedicated GPU resources to ensure efficient and numerically consistent training.

What is a browser agent? Its working principle and applicable scenarios

The browser agent operates web pages through AI models to achieve goals. After the user describes the task, the agent automatically opens pages, navigates, selects operations, and checks results to continue. It is particularly suitable for uncertain workflows that require flexibility and decision-making, composed of three parts: the model (decides actions), the suite (provides context, tools, and loops), and the browser (manages website sessions). Main uses include data extraction, research, form filling, etc., but there are drawbacks such as inconsistent results, task failure, website blocking, prompt injection, and unpredictable costs.

NVIDIA RTX Spark laptops are officially launched, featuring Blackwell RTX GPUs and an AI platform.

NVIDIA RTX Spark laptops are now available, equipped with Blackwell RTX GPUs, up to 128GB unified memory, and the full NVIDIA AI platform, starting at $2399. They are launched by ASUS, Dell, HP, Lenovo, Microsoft, and MSI, bringing powerful local AI, content creation, and gaming capabilities to portable devices. NVIDIA held global launch events, including one in Berlin, where founder Jensen Huang made a surprise appearance.

How Dify Chooses AI Agent or Workflow

Dify supports selecting AI Agent or Workflow based on whether the task is repetitive, whether judgment is needed, and whether there is a clear result. Agents are chosen by the model selection tool or action, while Workflows are defined by developers. The Hybrid mode combines both. In Dify, Agents are suitable for repetitive tasks requiring explanation of requests and selection of the next step, while Workflows are suitable for SOPs with fixed steps, where Agent nodes can be embedded to handle flexible steps within the Workflow.

Meta How to Build Forum Applications with Native AI Engineering

Meta uses AI agents to participate in the construction of engineering processes for Forum applications, viewing AI as a participant in the engineering process rather than an auxiliary tool. This experiment measures success by production-ready outcomes rather than lines of code, using a Human-On-The-Loop model to allow AI to autonomously execute planning, implementation, testing, and validation, with engineers responsible for setting goals, supervision, and acceptance.

Cohere North helps utility companies solve AI capability and control challenges.

The Cohere North platform can be deployed within the secure boundaries of utility companies to solve AI capability and control challenges. The platform supports processing sensitive data such as engineering documents and asset history in a controlled environment without data leakage. North ensures that companies maintain control over the authorization and responsibility of AI agents through built-in access control, audit visibility, and configurable workflows, making it suitable for the security, data, and operational requirements of utility companies.