Skip to content
Live
#Tutorials
Oct 10Sat
  1. Cohere Blog

    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.

Oct 9Fri
  1. Simon Willison65

    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.

  2. Comfy Blog70

    How to use MiniMax H3 to generate real-time video on a single GPU

    Using the FastVideo FastH3 V2 checkpoint, it generates 15-second 448×256 resolution video on a single RTX 5090 GPU through optimizations like four-step sampling, sparse attention, small text encoders, small checkpoints, and fused FP4 MLP. VRAM requirements are reduced from 80GB to <30GB; this custom Comfy node is open-sourced and can be deployed by requesting GPU and models via Comfy API.

Oct 8Thu
Oct 7Wed
  2. AWS Machine Learning Blog

    AWS Design Six-Week Plan helps non-technical professionals build AI prototypes to bridge the AI knowledge and capability gap

    The AWS Design Six-Week Plan helps non-technical professionals build AI prototypes to bridge the AI knowledge and capability gap. Four non-engineering background customers' professionals developed the first-place WealthWise multi-agent AI financial advisory tool within six weeks using this plan. The plan employs pair mentoring and production-level tools like Amazon Bedrock, requiring participants to follow five principles: prioritize learning over winning, hold daily stand-ups, start with a minimum viable product (MVP), actively seek guidance, and maintain fun.

Oct 6Tue
Oct 5Mon
  1. MIT Technology Review · AI65

    How to bring predictive analytics into the age of AI agents

    Enterprise AI is no longer debating whether predictive models can surpass statistical predictions; the key is how to make predictive systems make autonomous decisions without deviating from business goals. Real-time training and scalable data sources are turning AI from passive hindsight into practical foresight, elevating predictive analytics to new heights. AI is making the term 'analysis' gradually replaced by 'agent,' with everything becoming AI.

Oct 3Sat
Oct 2Fri
  1. GitHub Blog · AI & ML

    AI is changing the way developers work, these three skills are worth strengthening

    Developer workflows are changing due to AI, with skills beyond coding—such as guiding AI, evaluating outputs, communicating trade-offs, and making technical decisions—becoming increasingly important. Three key skills developers should strengthen are learning to guide AI rather than just using it, not trusting AI's first answer and evaluating it, and leveraging AI to solve broader problems.

Sep 27Sun
Sep 26Sat
Sep 25Fri
  1. Browser Use

    What is Chrome DevTools Protocol (CDP)

    Chrome DevTools Protocol (CDP) is a low-level protocol used to inspect and control Chromium-based browsers, exposing browser functions such as JavaScript execution, DOM inspection, network monitoring, and page rendering through structured messages.

Sep 23Wed
  1. Together AI Blog

    How to train your own Jev model for $17

    Together AI released a guide on how to fine-tune the Jev classification model using the Qwen3.5 4B model and a Hugging Face dataset of 38,340 items, with a training cost of about $17 and a duration of about 25 minutes; after deployment, it can be used for inference via an API endpoint (e.g., ENDPOINT_NAME), suitable for scenarios such as intent recognition for e-commerce customers.

Sep 22Tue
  1. OpenHands Blog

    How to Self-Host AI Models: Complete Setup Guide

    Self-hosted AI models allow organizations to directly control the reasoning runtime environment, deployed model weights, and service operation methods, suitable for scenarios involving sensitive data, pursuing cost-effectiveness under continuous utilization, model customization, and controlling the model lifecycle. By deploying open-source weight model checkpoints on local workstations, private servers, or controlled cloud infrastructure, and using reasoning runtime service models such as vLLM, Ollama, or llama.cpp, applications can call self-hosted endpoints just like calling managed model APIs.

Sep 21Mon
  1. OpenHands Blog

    What is model-agnostic in AI? A practical guide

    Model-agnostic AI reduces direct dependency of applications and workflows on a single model, handling differences in authentication, request formats, model identifiers, etc. between different providers through an abstraction layer. OpenHands's model evaluation shows no single best model, its workflow supports use of different models for planning, implementation, debugging, and review, making model selection a continuous workload decision rather than a one-time vendor choice.

Sep 19Sat
  1. Hamel Husain75

    How to evaluate code agents?

    Use public benchmarks to evaluate code agents handling multiple tasks, such as SWE-bench and HumanEval; for narrow workflows, adopt product-specific evaluations; build private benchmarks containing organizational internal difficult tasks; identify issues through engineer reviews and error analysis and transform them into tests; Anthropic recommends starting with clearly specified tasks and stable environments with verifiable results, gradually adding extra checks like code quality or user interaction.

  2. Hamel Husain75

    How to debug LLM evaluators to align with human reviewers?

    Collect at least 50 passing and 50 failing human-labeled examples through error analysis to identify discrepancies between LLM judge and human labels for repair clues. Common issues include missing context or ambiguous instructions. Manually inspect a few inconsistencies first, then attempt automated prompt adjustment, such as using the GEPA algorithm to adjust judge prompts and measure their consistency with human labels. The most common error is letting the LLM judge capture too many types of errors at once. It is recommended to create separate judges for each failure type.

Sep 17Thu
  1. Dify Blog65

    How to build an e-commerce shopping agent with Dify's new Agent.

    Dify's new Agent can be used in e-commerce stores to help customers explore catalogs, understand product differences, and narrow down choices. It can also route high-value inquiries to team email. The initial version requires the Agent to first familiarize itself with the catalog, describe tasks through dialogue, search DOWSE's public product pages, and return product names, prices, brief descriptions, and links. After upgrading, the Agent can identify customer budgets, occasions, recipients, and preferences, recommend up to four verified products and explain the reasons, while also returning product images.

  2. Hamel Husain65

    What difficulties should be recorded that are not model errors?

    Any factors that make the product impractical should be recorded, including missing or damaged features unrelated to the model. Prioritize addressing issues rather than analyzing the causes of errors. For example, if customer service does not provide an order tracking link, it should be recorded even if the AI does not have this functionality. Identifying and prioritizing issues is the foundation of building evaluations, and some issues may be engineering or design flaws. Focusing on problems rather than root cause analysis helps write higher-quality annotations when viewing more data.

Sep 14Mon
  1. LangChain Blog71

    How to build paid media agents with LangChain

    LangChain publicly shares its construction method for paid media intelligence agents, which run on Slack, summarize ad platform and warehouse data weekly, and generate reports. Paid media increased from contributing 0 to 20% of the marketing pipeline within 6 months, and the cost per qualified lead decreased by 30% from June to August.

    Why it matters: LangChain publicly shares the complete engineering details of its paid media intelligence agents, including context hierarchy, on-demand tool discovery, and sub-agent isolation, which can serve as a reference for building long-running intelligent agents.

Sep 9Wed
  1. Mistral AI

    Mistral AI helps European energy operators migrate 40,000 lines of Fortran 77 code to C++

    Mistral AI helps European energy operators migrate 40,000 lines of Fortran 77 code to C++, the physics-intensive reservoir simulator lacks a test suite and centralized documentation. The project verifies the numerical correctness of the migrated code by building a consistency test harness, and uses an AI agent to organize documentation, ultimately adopting a human-supervised agent workflow to achieve modular migration, significantly improving code quality.

Sep 7Mon
  1. Browser Use

    What is a Headless Browser?

    A Headless Browser is a browser without a graphical user interface, controlled programmatically for automation testing, web scraping, etc. It has become popular due to the adoption of AI browser agents. Headless Chromium starts 60% faster than normal mode, uses 51% less CPU, and has a 42% lower peak RAM.

Sep 4Fri
  1. Dify Blog65

    Add automatic reminder function to Calendly using Dify Agent

    Users create an Agent on the Dify platform to connect Calendly and Gmail tools, achieving the function of automatically sending daily meeting reminder emails. The Agent uses Calendly MCP to obtain meeting schedules and participant information, and refers to preset email templates to send reminders through Gmail without modifying Calendly itself. This solution is suitable for SaaS products that only need to supplement a single workflow function.

Aug 25Tue
Aug 5Wed
Aug 4Tue
Jul 16Thu
  1. Qoder Blog0

    Qoder releases #CaseFarewell to "Vibe Coding": Evolution of team-level AI development practice with Harness governance and SDDAMAP framework application

    Qoder releases #CaseFarewell to "Vibe Coding", introducing the practice evolution of team-level AI development through Harness governance and SDDAMAP framework. The framework supports model inference with an 8k context length, a 3.5x speedup, and a parameter size of 175B, achieving 95.2 on the MMLU benchmark test, currently provided as a closed-source API.

Jul 14Tue
  1. Qoder Blog15

    CasePupu Supermarket and Qoder successfully held a corporate-level AI programming workshop together.

    CasePupu Supermarket and Qoder held a corporate-level AI programming workshop together, with over 150 developers participating in practical sessions with Qoder. The workshop focused on AI coding applications, demonstrating Qoder's integration capabilities in various scenarios such as IDE and CLI. Qoder provides enterprise pricing and Agent SDKs as development tools, supporting cloud agents and resource markets.

  2. Qoder Blog65

    The first AI Open Competition of Zhihang Group has concluded, with Qoder helping frontline employees build the supply chain risk control platform 'Baize' winning the championship, with risk control efficiency improved 96 times.

    Zhihang Group's first AI Open Competition has ended. Zhihang Group's frontline supply chain employees used Qoder to build the supply chain risk control platform 'Bai Ze' and won the championship, with risk control efficiency improved 96 times.

  4. Qoder Blog65

    Non-technical users Qoder Code create iOS apps

    Non-technical users used Qoder Code to build a personal iOS movie app in one day. Qoder is an app generation tool for non-developers, allowing users to create iOS apps without coding through a visual interface and AI assistance. The platform supports rapid prototyping and app development, lowering the technical barrier to app creation.

Jul 13Mon