All AI updates

Wccftech reports that the unofficial PC port of 'Bloodborne' has achieved 1080p at 220 FPS on an RTX 4070 graphics card

The non-official PC port of 'Bloodborne' by Super Medo supports NVIDIA DLSS Frame Generation technology on the RTX 4070 graphics card, achieving stable performance above 220 FPS at 1080p resolution, which is over 7 times better than the original console version; with native 4K resolution enabled and DLAA, the average frame rate is about 40 FPS, and with DLSS 3 Frame Generation in quality mode, it exceeds 100 FPS, while in performance mode, it reaches about 130 FPS.

EXL explores the design principles of enterprise-level AI service frameworks

EXL research finds that a company's AI competitive advantage depends more on the engineering systems around the model rather than the model itself; business load constraints should be defined first, then select appropriate models and service architectures, rather than doing the opposite; reliable, cost-effective, and large-scale AI application delivery needs to be achieved by measuring bottlenecks, targeted optimization, and building scalable architectures.

How to use NVIDIA GPUDirect Storage in Python to read data into GPU memory

NVIDIA GPUDirect Storage can transfer data directly from storage devices to GPU memory. According to the 2025 Stanford AI Index, AI computing power doubles about every five months, and LLM training data size doubles about every eight months. GPUDirect Storage can improve data transfer efficiency.

Comparing Self-Hosted LLMs with Cloud APIs: How to Route Between the Two

Self-hosted LLMs allow you to control data storage location, suitable for sensitive workloads, but require bearing hardware, maintenance, and operational costs, while cloud APIs mostly handle these for you. A hybrid solution allows routing requests locally or in the cloud, without managing two separate systems.

How does n8n manage stateful and stateless contexts in AI agent construction?

n8n allows engineering teams to choose between stateful or stateless architectures in AI agent construction based on requirements. Stateful architectures achieve continuity by retaining information across requests or sessions but require additional infrastructure management for state; stateless architectures improve scalability and fault tolerance by processing each request independently. Stateful systems are suitable for scenarios that depend on previous interactions (such as conversations, multi-step processes), while stateless systems are more adaptable for applications like REST APIs that require rapid scalability and simple maintenance.

ns2jb announces: the Nintendo Switch 2 software hacking solution can modify games

Developer pepsipu introduced a Nintendo Switch 2 software cracking solution named ns2jb, which can run on the latest firmware without hardware modifications. The solution allows modification of game content, but it needs to be retriggered after a restart, and complete kernel-level control has not yet been achieved.

How U.S. Hunger uses Amazon Quick to connect leaders with data

U.S. Hunger directly explores organizational data with Amazon Quick, enabling leaders to share key performance indicator definitions and collaboratively analyze financial and non-financial information in Quick Spaces, supporting its operational efficiency growth of 500% annually.

Hugging Face introduces system-level performance analysis of TorchNeuron on AWS Trainium

Hugging Face introduced how to use TorchNeuron for system-level inference performance analysis on AWS Trainium, capturing clean traces with torch.profiler configured for the Neuron backend, and using key_averages() to identify time-consuming operations.

Patch the Planet: Global Security Vulnerability Response Coordination Platform Launch

Patch the Planet connects security researchers, maintainers, and incident responders to help address critical vulnerabilities in open-source projects.

Tessl Blog: Stop line-by-line code review, start verifying intent

Tessl Blog stops line-by-line code review and starts verifying intent. The team's merged PR volume is four times that of last year and almost all AI-generated, making review a bottleneck. The team shifts to reviewing intent before code generation (acceptance criteria, constraints, and edge cases), and transforms repetitive review comments into machine-executable rules (invariants), thus shifting the focus of review from the code itself to decision-making and rule ownership.

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

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.

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.

Comfy's blog promised to open-source its entire platform but failed to deliver, so let's help them.

LangChain blog: Frequently Asked Questions about Agent Evals

The LangChain blog introduces how to use Agent Evals to test AI agent behavior, including analyzing behavior through trace logs, building test datasets containing inputs and expected outputs, running offline benchmark tests (such as Terminal-Bench) and online real-time evaluations, as well as using four types of evaluators: code inspection, LLM scoring, and manual review. Offline evaluations are used to test new prompts or models and catch regression issues, while online evaluations are used to monitor production quality and discover dataset gaps.

How to evaluate AI agents: Beyond sensory checks.

Evaluating AI agents cannot rely solely on perception checks, as agents may fall into retry loops or produce hallucinatory responses that still appear normal, leading to soaring cloud costs and token usage. A repeatable evaluation process should be established, starting with defining key user journeys (CUJ), using simulated user testing, and employing multiple layers of checks such as unit tests, deterministic metrics, LLMs as judges for scoring standards, and integration tests. Combining manual review tracking with automated validation can detect latent regressions early in development and expand the evaluation framework as agent capabilities grow.

How LangChain Deep Agents Manage Context Windows Through Middleware

LangChain Deep Agents manage context windows through middleware, preventing unnecessary information from entering and filtering existing content. It employs techniques such as offloading (saving large tool results and user messages to files), summarization (compressing old messages), skills (loading on demand), sub-agents (separating noisy tasks), and long-term memory (preserving learning across sessions). These techniques are implemented by inserting middleware at critical points like model calls and tool calls, allowing users to use them without writing code.

Building AI Morning News Summaries with You.com, Jev, and n8n

Jev answers three questions for each news article to filter out truly important developments, You.com node searches for daily news and deduplicates, You.com Research writes short summaries for each topic and posts via Slack, the entire process costs less than four cents, effectively avoiding interference from irrelevant information.

What is browser fingerprinting? Its working principles and limitations.

Browser fingerprinting identifies users by collecting browser features such as user agent strings, language, screen size, available fonts, and canvas rendering, hashing them to generate a unique identifier for user tracking, fraud prevention, bot detection, etc. Passive fingerprinting uses HTTP headers, IP addresses, and TLS handshake features, while active fingerprinting collects data such as screen size, text measurement, graphics rendering, and audio processing via JavaScript. Websites can combine multiple methods to identify users, but browser updates or privacy protection can change the results.

Cohere discusses the choice of shared or dedicated inference for Embed & Rerank workloads.

When analyzing Embed & Rerank workloads, shared inference is suitable for batch processing (such as e-commerce indexing) to improve cost-effectiveness, while dedicated inference is better for re-ranking with a high number of candidate documents (such as fine-tuning search results); the choice should be based on request characteristics (batch processing/single query/candidate count), traffic patterns (continuous/bursty), and utilization, rather than purely price comparison.

Simon Willison uses GPT-6 Astra High to build new blog features through voice

Simon Willison interacted with GPT-6 Astra High via voice to build the Newsletters page of his blog, implementing a subscription list indexing feature, including weekly free Substack and monthly exclusive updates for sponsors. He used the Codex voice chat mode of the ChatGPT desktop application to complete the model, migration, view code, template, and database import functions in a local development environment and integrated the website search engine.