Qoder Blog6565The 7×24 autonomous feedback processing system built by Qoder CLI and HARNESS ENGINEERING compresses the time for root cause analysis of problems from 30 minutes to 2 minutes.
Berkeley AI ResearchGRASP is a new gradient-based world model planner that achieves temporal parallel optimization by elevating trajectories to virtual states, explores by directly adding randomness to state iterations, and provides clear signals for actions by reshaping gradients, while avoiding fragile 'state-input' gradients generated by high-dimensional visual models, making long-term planning possible.
Prime Intellect Blog6565Prime Intellect takes FrontierSWE to the Environments Hub, an ultra-long temporal open-source coding benchmark developed by Proximal, which includes challenges such as optimizing compilers or training SOTA protein prediction models, with an average task duration of 11 hours and almost unsolvable.
LangChain BlogLangChain uses Deep Agents CLI and custom skills to migrate inline code examples in documents to testable standalone files, continuously verifying and automatically fixing failed examples. The relevant skill definitions are in the .agents/skills/docs-code-samples/SKILL.md file.
Moonshot AI · Hugging Face new modelsKimi K2.6 is an open-source multimodal intelligent agent model that has made significant progress in long-term encoding, encoding-driven design, proactive autonomous execution, and group task orchestration. It has 1 trillion parameters, a context length of up to 256k tokens, achieving a score of 54.0 on the HLE-Full benchmark and 86.3 on the BrowseComp (agent group) benchmark, and supports 300 sub-agents executing 4,000 coordinated steps in parallel.
LangChain BlogDeep Agents Deploy Officially Released as an Open Source Alternative to Claude Managed Agents for Intelligent Agent Deployment, Supporting Any LLM Model, Achieving Model-Agnostic, Production-Ready Deployment via the `deepagents deploy` Command, Users Can Customize AGENTS.md Instruction Sets and Agent Skills, and Choose a Sandbox Environment to Ensure Memory Ownership is Not Locked.
Cognition BlogSWE 1.6 is the latest model built specifically for software engineering agents, providing general support on Windsurf with a speed of 950 tok/s and free for the next 3 months. Compared to SWE-1.5, SWE 1.6 improves by over 10% on SWE-Bench Pro by jointly optimizing user experience and reasoning fluency, significantly reducing behaviors like overthinking and redundant tool calls, making model interactions more efficient.
LangChain BlogOpen-source large language models GLM-5 and MiniMax M2.7 perform similarly to proprietary cutting-edge models (such as Claude Opus 4.6, GPT-5.4) in core intelligent agent tasks like file operations, tool usage, and instruction following, with reliable tool calls and consistent instruction adherence.
Microsoft AI NewsMicrosoft has launched three top-tier AI models: MAI-Transcribe-1, MAI-Voice-1, and MAI-Image-2, with MAI-Transcribe-1 starting at $0.36 per hour.
Prime Intellect Blog6565We collaborate with Browserbase to provide the best training experience for browser and computer using agents. Browserbase provides scalable browser infrastructure, supporting Microsoft's Fara-7B and Google's Gemini 2.5 CUA.
Dify Blog7575Dify provides a platform to build, manage, and deploy AI workflows without complex infrastructure, supporting applications such as connecting internal data, triggering events or running on schedule, and generating industry news summaries.
LangChain BlogCompanies like Stripe, Ramp, and Coinbase have independently developed internal coding agents that adopt similar architectural patterns, including isolated cloud sandboxes, curated toolsets, Slack first calls, rich boot context, and sub-agent orchestration.
Prime Intellect BlogPrime Intellect's platform covers intelligent agent RL training for cutting-edge open-source models, globally deployed agent inference, sandbox environments optimized for reinforcement learning, and open-source library verifiers like verifiers and prime-rl that tie everything together.
Berkeley AI ResearchThe SPEX algorithm identifies key interactions of LLMs through signal processing and coding theory, analyzing the impact of features, data, and model components with only a small amount of disturbance, achieving high fidelity in sentiment analysis tasks even with thousands of features; The ProxySPEX algorithm leverages model hierarchical structure characteristics, reducing the number of disturbances by 10 times while maintaining performance.
Dify Blog6565Dify Introduces Creator Center and Template Marketplace, Where Creators Can Upload Workflow Templates, and Users Can Discover and Adopt Them with One Click. Creator Center Supports Template Submission and Management, Template Marketplace Provides Categorization, Tags, and Creator Browsing, Template Detail Pages Include Visual Preview and Guided Setup, Supporting Organization Account Management Permissions.
Dify Blog6565Dify Cloud is upgrading the free trial experience, Message Credits now support four models: OpenAI, Claude (Anthropic), Gemini (Google), and Grok (xAI), and can be used without configuring an API Key; The Explore page has added a featured template trial function, providing 5 message credits covering scenarios such as file translation, personalized memory assistant, and patient information collection, without plugin configuration.
Cognition BlogSWE-1.6 achieves 11% higher scores on SWE-Bench Pro, but exhibits overthinking and self-validation issues, running at a speed of 950 tok/s. The model improves RL algorithms and expands infrastructure training, increasing computational volume by two orders of magnitude, currently opening early access to a small number of users to collect feedback.
Replit Blog6565Replit has launched the Pro plan at $100 per month, offering features such as Agent mode, tiered discount credit limits, and priority support, suitable for professional developers; the core plan price has been reduced to $20 per month, with new collaboration features allowing up to 5 people to collaborate, and original Teams users will be automatically upgraded to the Pro plan.
Anthropic Research5858Anthropic proposed a persona selection model to explain AI's human-like behavior, suggesting that large language models learn personas from text during pre-training and adjust rather than change their essence during post-training. This model can explain Claude's anti-Alignment behavior when trained to cheat, implying that developers need to focus on the psychological aspects of the personas behind the behavior rather than just judging the behavior itself, and recommending the introduction of more positive AI role models.
LangChain BlogLangChain has improved its coding Agent's performance on Terminal Bench 2.0 from 52.8% to 66.5%, rising from Top 30 to Top 5, achieved solely by enhancing the harness engineering.
Andrej Karpathy released an art project named microgpt, a single-file containing only 200 lines of pure Python code, which can train and infer GPT models without dependencies. The project implements all algorithmic content from dataset processing, tokenizer, automatic differentiation engine to GPT-2 style neural network architecture, Adam optimizer, training and inference loop. The code can be obtained from GitHub gist and karpathy.art, and has been released as a triptych.
Dify BlogDify guides on how to design workflow-ready LLM application prompts by defining clear optimization goals, constructing prompts that include task descriptions, examples, and context, and separating system rules from user input. System prompts contain permanent constraints (such as roles, formats, and safety boundaries), while user prompts contain requests for specific content (such as documents and questions). It requires the model to output structured results (such as JSON) and provide evidence to support scoring to reduce hallucinations and improve the usability of the output in downstream steps.
Prime Intellect BlogPrime Intellect Lab releases an end-to-end model training platform that integrates Environments Hub, hosting training and hosting evaluation, supporting large-scale agent reinforcement learning, reasoning, and evaluation without managing GPU clusters or algorithm details. The platform is built based on environments, including task datasets and executors, and has completed over 3000 reinforcement learning runs through private testing.
Qoder Blog6565Qoder uses RL-optimized model Qwen-Coder-Qoder to build Agent architecture.
Browser UseBrowser Use released the open-source browser automation benchmark BU Bench V1, containing 100 hardcore browser tasks, Claude Fable-5 scored the highest at 80.0%, leading GPT 5.5 by 12 points; Browser Use Cloud (bu-ultra) scored 78.0%, with a speed of approximately 14 tasks per hour. The benchmark is based on real-world website tasks, scored using LLM evaluators, and is available on GitHub.
LangChain BlogThe LangChain Deep Agents SDK manages limited memory of AI agents through three compression techniques: offloading large tool results (>20,000 tokens) and inputs (>85% context window) to the file system, and using LLM to generate session summaries. The SDK triggers compression on Claude Sonnet 4.5 in terminal benchmark tests, retaining complete records through filesystem search and summaries, supporting frequent compression to optimize performance.
Factory NewsFactory introduces Agent Readiness tool, which evaluates the support of codebases in eight technical pillars and five maturity levels by running the /readiness-report command, and provides specific improvement suggestions. The tool aims to address performance differences caused by codebase environment issues in AI coding agent deployment, supporting three interaction methods: CLI, Dashboard, and API, and can quickly improve basic configuration file and document missing issues through automation repair features.
Anthropic Research5050Scientists have achieved significant progress in biological illustration, computational biology, and protein understanding benchmarks using Claude 4.5, a model now available to top researchers worldwide via API for free, and has built custom systems that go beyond literature reviews or coding assistance. In the lab, Claude serves as a collaborative partner throughout the research process, compressing projects that usually take months into hours using various tools, and discovering large-scale data patterns that humans might overlook, eliminating bottlenecks in knowledge-intensive tasks, and even enabling entirely new research approaches that traditional methods cannot adopt.
Qoder Blog00The Qoder NEXT model upgrades editing capabilities from code completion to prediction, achieving more precise intelligent editing through ActionRL preference alignment technology. The model's context length reaches 128k, with a parameter size of 175B, demonstrating excellent performance in the SWE-bench reasoning benchmark, a 3.5x speed increase, and supporting open-source API interfaces.
Anthropic ResearchFeatured6767Anthropic's research team developed an agent based on Claude Code custom commands, which infers the properties that code should satisfy by reading type annotations, docstrings, and comments, and then uses Hypothesis to write property tests, discovering hundreds of potential bugs in over 100 popular Python packages such as NumPy, SciPy, and Pandas.
Why it matters: Anthropic uses Claude agents to automatically write property tests to find bugs in packages like NumPy, SciPy, Pandas, and provides the efficiency after manual review and merged fixes
Berkeley AI ResearchBerkeley AI research proposes an information-driven imaging system design framework, which quantifies the object's discrimination capability through mutual information measurement. It has been validated in four fields: color photography, radio astronomy, lensless imaging, and microscopy that information estimation can predict decoder performance. The optimized mutual information design scheme achieves end-to-end optimal results while reducing memory and computational load.
Dify BlogThe Dify team will visit Europe by the end of 2025, exchanging with partners in London, Berlin, Oslo, Lisbon, and Paris, observing different scenarios of Dify's deployment in local servers in German historical towns, building new tools on individual developers' computers, and scaling applications in complex global enterprise infrastructure.
Anthropic Research5858Anthropic partnered with the Pacific Northwest National Laboratory (PNNL) to use the Claude model to quickly simulate network attacks in a simulated water treatment plant network, proving that AI can accelerate defense drills, completing attack reconstruction in just three hours instead of weeks; Claude Sonnet 4 demonstrated resourcefulness in testing by bypassing the Windows UAC security feature through predefined tools and identifying alternative techniques to achieve the goal.
Liquid AI BlogLiquid AI has released the LFM2.5-1.2B model family, with its pre-training extended to 28T tokens and significantly improved post-training performance through reinforcement learning, showing excellent performance on knowledge, instruction following, math, and tool use benchmarks. This series includes Base, Instruct, Japanese, Visual Language, and Audio Language models, all of which are open-source and available on Hugging Face and LEAP. The audio models are 8 times faster than their predecessors and natively run on vehicles, mobile devices, and IoT devices.
Prime Intellect BlogRecursive Language Model (RLM) allows large language models to proactively manage their own context, check and transform input data via Python REPL, and call sub LLMs.
Qoder Blog6565FeatureQoder introduces a prompt enhancement feature, allowing developers to avoid prompt engineering. This feature boosts developer usage by 3.5 times and supports context length extension up to 8k tokens.
Qoder Blog6565ProductQoder CLI released, bringing Qoder's AI capabilities to every terminal.
Qoder Blog00ProductSmart Context Control released, optimizing large model usage through intelligent context management, saving costs. This tool supports 8k context length, priced at $3.5 per million tokens, currently provided as a closed-source API.
Qoder Blog1717Qoder generates dynamic shared documents through code, its Agent SDK supports cloud and local deployment, with a context window of up to 128k, priced on a pay-as-you-go basis.
Anthropic Research5858After upgrading the Claude Sonnet 4.0/4.5 models, Anthropic's Project Vend's second-phase AI store 'Vendings and Stuff' has significantly improved its profitability, largely eliminating negative profit weeks, and has opened new stores in New York and London.
.png%3Fv%3D522e7362d902&mode=card&exp=1794873600&sig=595aae7d3626ce49)
