#Tutorial/How-to

AIUber uses a control plane and data plane gateway to automatically convert its internal APIs into MCP tools, with 800+ MCP servers and 5,000+ tools hosted. The design includes an AutoCrawler that generates tool descriptions with an LLM, a default-disabled discover-not-expose security model, and techniques such as Omni MCP, Response Projection, and Code Mode to limit context bloat.

AIThe article argues that improving an AI setup can sometimes mean giving the AI fewer rules to follow, based on the author's experience across a million words of failed drafts. The source text provided is mostly paywall and subscription material, so no further specific figures, products, or benchmarks can be verified.

AIOpenRouter's shell and bash tools, along with those from OpenAI and Anthropic, run an agent's commands in provider-managed sandboxes during the same API request, so developers don't provision or patch containers. OpenRouter's tools are in beta, with sandbox time billed at $0.0001 per second and a 30-second minimum for a new or sleeping container. The article compares the four providers and notes that self-run sandboxes remain better for custom base images, GPU work, or multi-hour sessions.

AIGoogle Cloud Tech promotes a course on designing hierarchical agent trees and deterministic workflow agents. It also covers choosing a hosting environment that keeps AI agents secure, scalable, and production-ready.

AIGuillermo Rauch says his new project has a hand-written README for human readers, while its internal documentation is written in AI-style English for agents. He argues that blogs, tweets, and READMEs are human communication and should be written by people to connect with other readers.

AIPerplexity's Computer can build custom vertical AI apps, such as one that guesses an image's location using 3D and satellite views. The example app was built with the Perplexity SDK for web search, local place lookups, and visual clue extraction, and it uses Cesium for the 3D globe and satellite imagery.

AIBoris Power says Dots are happiest when reducing backlogs and task lists. Thibault Sottiaux adds that setting inbox zero as an active goal for his Dot helped him reach it for the first time.

AIThe author spent over half an hour using Claude to produce a company logo animation that is now roughly usable. The post reflects surprise that motion graphics and video work can now be generated directly through code by AI.

AIKling AI used its Kling 4.0 model to produce "The Beat," a short film built around a 30-second continuous shot and surpassing 5 million impressions across social platforms. The model's native 30-second generation, Omni Reference supporting up to 15 multi-modal references, Multi-Keyframe control for up to 10 keyframes, and 10-bit HDR output shaped the film's continuity, consistency, and color. The post walks through these features shot by shot.

AILangChain says its coding agent costs fell significantly for a second straight month after adopting three steps. The steps are cost visibility through LangSmith tracing, per-user cost caps via its LLM gateway, and harness optimization such as model routing in its open-source OpenSWE cloud agent harness.

AITeknium says the process for setting up Hermes with Discord should now be less confusing and less painful. The post gives no specific steps, version numbers, or technical details.

AIPerplexity's Computer can now generate inline visualizations when users ask it to "Visualize" a topic, producing interactive widgets and animations within the thread. The feature is best used on Standard or High effort, and an example given is an inline 3D cutaway of a jet engine.

AICohere says it refined training data using two approaches: Best-per-Language Forward Translation and Post-Edit Driven Preference Distillation. The post is part 4 of a thread and explains why these methods were chosen, but the source text does not give further detail.

AIPixVerse shared a link to a marketing page for getting its plugin. The post provides no details on the plugin's features, supported platforms, or pricing.

AIPixVerse says users can describe a character to their AI agent and use the PixVerse plugin to generate a full design sheet. The post provides no further details on features, pricing, or availability.

AISebastian Raschka released round six of his Reasoning from Scratch series, introducing Reinforcement Learning with Verifiable Rewards (RLVR) and Group Relative Policy Optimization (GRPO) with an implementation. The video covers accuracy and format rewards, DeepSeek-R1 training, and GRPO versus PPO, then walks through a training loop and evaluates checkpoints on MATH-500.

AI继续随手做视频：100 秒搞懂 homebrew Translation: Continuing with casual videos: understand Homebrew in 100 seconds.

AITypeSafe AI links to documentation describing how its confidence scores are calculated. The post itself gives no details about the methodology or any figures.

AIHamel Husain announced a final open lesson of the year on how to crack AI evals interviews, covering common traps and what companies look for. The session, on Tuesday, Oct 6 at 8:30am PT, also covers structuring a take-home or report, and assumes basic evals knowledge.

AIReplit chat now generates interactive charts when users ask Replit Agent to visualize data. Users can also choose GPT-6.1 Sol from OpenAI or Claude Sonnet 5.5 from Anthropic when building with Agent, or stay in auto mode. Jev is available through Replit AI Integrations for classifying content, routing requests, and scoring leads without managing API keys.

AIPrime Intellect's post gives a quick start for querying z-ai/glm-5.3 through its inference service, using the command prime inference chat with a sample haiku prompt. Developers can alternatively point any OpenAI-compatible SDK at

AIvLLM changed its KV cache layout to block-major BLHNC, cutting transfer descriptors about 10x and halving mean KV transfer time on NVLink. The original slowdown came from fragmented KV layout that split one 200K-token request into 32K tiny copies, making NVLink slower than InfiniBand.

AIPrime Intellect reports that DEP8 provides about 5x the prefix-cache capacity of TEP8 on the same GPUs. The post argues that fast KV retrieval alone does not ensure fast first tokens, since cached KV often sat ready while requests waited to join a batch. Halving the prefill budget reduced median queue wait time and time to first token (TTFT).

AIPrime Intellect says long-context agent serving depends on retaining history, scheduling new work, and moving cached state efficiently. It optimized three paths separately: prefill topology and scheduling, compressed KV with a fused attention kernel, and a transfer-friendly cache layout.

AIVercel has added Jev to the AI SDK for Python, and the team tested it in two experiments: detecting whether typed text is Python or English, and writing Python one decision at a time. The main post is a short endorsement praising a writeup about Jev and Python.

AIBaseten tested the MetaInfer skills-only approach by having Claude Code build an inference engine, VibeQwen, for Qwen-3.6-35B-A3B in NVFP4 on a single B200. On single-stream text, VibeQwen decoded 90% faster than a tuned vLLM 0.25.1 deployment (1,792 vs. 943 TPS) and cut time to first token from 28 ms to 12 ms, with a 71% throughput gain at concurrency 32. The author notes this was an outcome-focused run that allowed some numerically different outputs as long as accuracy stayed at or above the BF16 baseline.

Why it matters: The post tests a skills-only inference engine method on a real model and states the speed and accuracy constraints used, helping readers judge how far such automated optimization can be trusted.

AIAnthropic's Lydia Hallie explains that mods are plugins with special functions that let custom code run inside Claude Code, working like middleware. She notes users can simply ask Claude to write them.

AIAnthropic's ClaudeDevs describes a "You should know" mod that spins off a sideagent to observe Claude's output. The mechanism is detailed in a newer blog post on getting started with Claude Code mods.

AIThe vLLM team integrated Helion, a PyTorch-native kernel DSL, into vLLM's linear backend, using per-shape autotuning to select among Standard GEMM, Split-K, and Swap-AB variants. On NVIDIA Hopper GPUs, the Helion backend outperformed the default CUTLASS and DeepGEMM backends across the evaluated models, with more than 10% throughput gains for some workloads. The work focuses on FP8 and INT8 quantized GEMM.

AIThe Linux Foundation Education has launched a PyTorch Certified Associate (PTCA) Certification Pathway that combines four self-paced learning modules with the PTCA exam. The pathway includes 15–17 hours of self-paced learning and hands-on labs covering tensors, data handling, model development, and performance optimization. The source recommends additional hands-on practice before taking the exam.

AIHamel Husain says it is baffling that people keep their laptops open for long-running work instead of using SSH into a machine or Codex's remote feature with a Mac mini. He argues that after being stuck in this situation more than three times, continuing it is crazy.

AILlamaIndex says its LlamaParse agentic parsing tier turned the BEA's Q2 GDP-by-state infographic, which lacks a text layer, into a 52-row table. The post presents this as the tool faithfully recording data from an image-only document by default.

AIFine-tuning NVIDIA Nemotron 3.5 ASR cut word error rate on Najdi and Hijazi Saudi Arabic from 55% to 30%. Check out our new tutorial and learn how to adapt it for other dialects and languages:

AI…shared context repo any harness can read 2/ half a day of research in 5 min 3/ evals that test our product the way agents use it 🎧:

AIYour AI agent uses PixVerse to generate the video!

AIIn this DevEx program sprint, we tested agent governance on Gemini Enterprise from the ground up—using standard external accounts and zero internal shortcuts to find + fix developer friction fast ↓

AIA: Binary labels force clearer thinking and more consistent labeling, and involves significantly lower complexity to operationalize.

AIAirbnb CTO Ahmad Al-Dahle, who joined from Meta in January, says 60% of the company's code is now AI-authored and pull-request throughput per engineer is up about 1.6x. Roughly half of Airbnb's support tickets are now resolved purely by AI, which the company tested with synthetic data before production. Airbnb's internal context graph Everest helped speed up the grocery delivery and airport pickup services, which took eight to nine months and about six weeks to build, respectively.

AIingi_erlingsson wrote down how he reads a moodboard: the feeling first, then color, tone, and camera, then @armandgw made it a Krea Agent skill. learn how below👇