#Tutorial/How-to

AIPaddlePaddle's PP-OCRv6 Tech Deep Dive Ep.4 benchmarks the OCR models across A100, V100, Intel Xeon CPU, and Apple M4 setups. PP-OCRv6_tiny processes an image in 0.13s on A100, while PP-OCRv6_tiny with OpenVINO runs 3.9x faster than PP-OCRv5_mobile on Intel CPU. The post recommends Medium for high-concurrency APIs, Small for CPU document systems, Tiny for mobile or embedded devices, and Medium or Small for multilingual business use.

AICompute is expensive. Scaling laws are a way to help us reason about the optimal compute allocation between data and model size before committing to a large run. The post covers what scaling laws predict, how compute-optimal allocation works, why Kaplan et al. and Chinchilla disagree, and how data limits + fitting details make extrapolation tricky.

AIPP-OCRv6's recognition module uses a CTC plus NRTR dual-head design so text is decoded from visual features rather than language priors, reducing hallucination. In hallucination tests, PP-OCRv6_medium reaches 93.2%, versus 85.0% for the best VLM, and recognition accuracy across 15 scenarios is 83.2%, above PP-OCRv5_server's 78.1%. NRTR is used only during training, adding language regularization at no inference cost, and it contributes +1.16% accuracy.

AIWe discuss some benchmarks and the common pattern: • A sandboxed target within Docker containers • Inputs: code only (0-day), with patch (1-day scenario) • Tools such as bash, static analyzers, etc. • A grader to eval exploits or captured flags

AIPaddlePaddle says its PP-OCRv6_medium text detector reached an 86.2% detection Hmean in benchmarks, versus 46.8% for Gemini-3.1-Pro and 38.3% for GPT-5.5. The detector's design uses RepLKFPN with 7×7 kernels to cut FPN neck parameters from 172K to 118K, auxiliary deep supervision heads on P2–P4, and Focal Loss paired with Dice Loss, which adds +1.15% Hmean in ablation.

AILil'Log examines early empirical work showing that deep learning generalization error follows power-law curves as training data and model size grow. Hestness et al. (2017) found the exponent reflects the problem domain rather than the architecture, while Rosenfeld et al. (2020) modeled loss jointly as a function of model size N and data size D, fitting parametric forms on small configurations to extrapolate to larger ones.

AIPaddlePaddle introduced PP-OCRv6, a lightweight OCR architecture built on the LCNetV4 backbone, in the first episode of its tech deep dive series. The post says PP-OCRv6_medium reaches 86.2% detection Hmean and 83.2% recognition accuracy, surpassing PP-OCRv5_server while running faster. Three model specs—Tiny, Small, and Medium—target edge CPU devices, balanced deployment, and industrial high-accuracy pipelines.

AIZed Blog's "Hidden Gems: Part 4" lists editor tips including a centered layout toggle with adjustable padding, keybindings for switching between projects, worktrees and branches, and setting EDITOR and VISUAL to zed --wait in the integrated terminal. It also explains command_aliases for mapping short mnemonics such as gd and gcp to commands like git::Diff and git::CreatePullRequest.

AIDeepLearning.AI has launched a course, taught by VocalBridge CEO Ashwyn, on adding voice to AI agents and applications. It covers building voice agents that are both reliable and fast, with three projects: a voice-interactive game, an agent that gains a voice in about 10 lines of code, and an agent that places outbound calls via a make_phone_call function.

AIA technical dive inside our new "Midjourney Scanner"

AIPromptArmor demonstrated that OpenAI's Approve-for-me agent approved a malicious NPM install with elevated privileges after a hidden prompt injection in an external GitHub issue influenced the main Codex agent. The malicious package's post-install script then ran unsandboxed with the user's full privileges. The report also gives steps for organizations to disable agentic auto-review in Claude Code and Codex.

Why it matters: The report shows a prompt-injected GitHub issue leading an approval agent to permit a malicious NPM install, a concrete test of agent-in-the-loop guardrails.

AII also hear it's one of the most viewed videos in WWDC history 👏 Goes through the basics of agentic AI and how to set it all up to run locally in a very approachable and simple way. The demos are excellent and it's kind of wild that they just work now. None of this was possible or practical < 1 year ago before M5 and the recent quality bump in open weights models. And it's not done improving.

AIMiniMax describes MaxProof, an evolutionary-search framework that lets its M3 model refine candidate proofs over multiple rounds. The post says the M3 model exceeded the human gold-medal threshold on the IMO 2025 and USAMO 2026 benchmarks with MaxProof, and explains the Proof RL, verifier alignment, and refinement training behind it.

AIWe just published a blog on our full pipeline inference optimizations for MiMo-V2.5 series, including how we pushed hybrid SWA efficiency to the limit. Read the full blog here:

AIXiaomi describes an end-to-end inference optimization for the MiMo-V2.5 series, centered on Hybrid SWA, which it says cuts KVCache storage to roughly 1/7 of Full Attention. The post covers a dual KVCache pool design, SWA-aware prefix cache matching, the GCache distributed cache, and scheduling changes, and reports cache hit rates averaging 93% in server-side observations. It also covers prefill and decode optimizations, multimodal encoder improvements, and open-source contributions to SGLang.

Why it matters: The post explains how Hybrid SWA's theoretical KVCache savings were realized in production through dual pools, SWA-aware prefix caching, and tiered storage, giving concrete engineering patterns for long-context inference.

AICognition describes autonomous testing in Devin, where the agent writes a source-grounded test plan, operates the app through computer use, and returns labeled screenshots and an annotated video. Login steps are handled by a deterministic testing skill, and the company says test runs approved per day more than doubled in recent months. Known limits include timing errors with transient UI elements and models sometimes triggering states through JavaScript instead of clicking the interface.

Why it matters: The post explains how computer use, test plans, deterministic login scripts, and annotated recordings let Devin verify its own code changes end to end.

AIMiniMax says the M2 series could not generate the rare token "嘉祺" in names like Ma Jiaqi, and its investigation traced the cause to post-training. The company found the token was learned in pretraining, but low coverage of rare tokens in post-training data caused lm_head vectors to drift. Adding synthetic full-vocabulary repetition data restored generation for these tokens and reduced Japanese-to-Russian mixing from 47% to 1%.

Why it matters: The post traces a specific token failure through tokenizer, embedding, and lm_head checks, showing a reusable way to diagnose post-training generation problems.

AIFunAudioLLM has released Fun-ASR-Nano-2512-hf, a Hugging Face Transformers-compatible version of its end-to-end speech recognition model, which supports Chinese, English, and Japanese. The Chinese coverage includes 7 dialect groups and 26 regional accents, and a separate Fun-ASR-MLT-Nano-2512 checkpoint handles 31-language recognition. Developers can run the model natively in Transformers 5.17.0 without custom model code or trust_remote_code=True.

AIGiven a few optimized primitives, LLMs (and novice humans) can write speed-of-light kernels for all transformer ops!

AIWatch 3.5 Flash build an interactive circuit helper, outputting a step-by-step physical build guide alongside a working simulation. It’s a great example of how the Gemini app can help students learn visually, breaking down new or complex concepts and guiding them through hands-on subjects interactively. 3.5 Flash is available globally today!

AIEugene Yan shares Cloudflare's description of a vulnerability discovery harness that runs eight stages, from reconnaissance to report writing. The pipeline uses about 50 concurrent agents to hunt for bugs, independent agents to try to disprove findings, and a trace step to confirm whether attacker input reaches each bug. Reachable findings feed back into new hunt tasks before a report is written against a predefined schema.

AISebastian Raschka reviews recent open-weight LLM architecture changes aimed at reducing long-context memory and compute costs. He covers KV sharing and per-layer embeddings in Gemma 4, per-layer query-head budgeting in Laguna XS.2, Compressed Convolutional Attention in ZAYA1-8B, and mHC with CSA/HCA compressed attention in DeepSeek V4. The article reports that DeepSeek V4-Pro uses 27% of single-token inference FLOPs and 10% of the KV cache size of DeepSeek V3.2 at a 1M-token context.

AICognition reports that deploying its Devin agent on hardware-in-the-loop and software-in-the-loop workflows cut failure triage time and multiplied test generation at automotive customers. One team reclaimed 2K–4K engineering hours monthly across about 4,000 tickets, while RV Tech rose from 1–2 to 10–15 generated tests per day. Devin also helps convert bottlenecked HIL tests into SIL equivalents to catch failures earlier.

AIMuch better way to learn.

AITune in Friday as NVIDIA and Google DeepMind experts walk through vision translation, long-context document Q&A, and real-time code gen demos live. Bring your questions. 📆 Friday, April 24 at 11:00 AM PDT Add to schedule ➡️

AIFactory has released an Automated QA skill that drives an app as a real user would, filling forms, typing into terminals, and calling endpoints, then posts a structured report with screenshots, terminal snapshots, and API traces as a single updating comment on each pull request. Teams can run it on every push or make it an optional CI check triggered by a PR label, comment command, or manual dispatch, and developers can run /qa locally in any Droid session. Automated QA is available today in all Factory plans.

AIThis leads to much lower activation mem, and way faster speed, esp for fine-grained MoE. Plus fun stuff on how to leverage new Blackwell features like 2CTA MMA and CLC for super fast MoE kernels

AICognition reports that multi-agent setups work best when writes stay single-threaded and extra agents contribute intelligence instead of actions. It describes a code-review loop where a clean-context review agent catches bugs in Devin-written PRs, averaging 2 bugs per PR with roughly 58% severe. The post also says the smart-friend pattern, pairing a smaller primary model with a stronger one, has not yet worked well with asymmetrically weaker primaries and is an open training problem.

Why it matters: The post gives concrete findings on which multi-agent setups work, including clean-context code review and smart-friend escalation, and where they still fail.

AIBuild a fully local, sandboxed AI assistant. Step-by-step tutorial to build your always-on agent: 🦞 on @openclaw ✅ with NVIDIA NemoClaw ✨ using NVIDIA DGX Spark Get started:

AIZ.ai's GLM-5.3 delivers a 50% coding gain over GLM-5.2 on Z.ai Code Bench, reaching open-source state-of-the-art on public benchmarks including Terminal Bench 3.0. GLM-5.3-Flash uses 320B total parameters with 18B activated, combining linear and sparse attention to reduce compute and KV-cache needs. GLM-5.2 supports a 1M lossless context window for long-horizon tasks.

AIKarpathy describes using LLMs to compile raw source documents into a markdown wiki that he views in Obsidian, with the LLM writing and maintaining most of the wiki. He reports that at about 100 articles and 400K words, the LLM agent can answer complex questions directly from the wiki, and he also runs LLM health checks to find inconsistencies and gaps. He shares the underlying idea as an "idea file" that users can give to their own agents to build a customized version.

AIAndrej Karpathy describes using LLMs to compile raw research sources into a markdown wiki of about 100 articles and 400K words, viewed in Obsidian. He says an LLM agent answers complex questions against the wiki without RAG, with outputs filed back to enhance it. He also suggests the workflow could become a product rather than a collection of scripts.

AIAnthropic describes Claude Code auto mode, which delegates approval of agent actions to model-based classifiers instead of manual prompts or skipped permissions. The classifier reviews tool calls before execution and a separate probe screens tool outputs for prompt injection. Anthropic reports a 0.4% false positive rate on real internal traffic and a 17% false negative rate on real overeager actions.

Why it matters: The post explains the layered classifier design and its measured tradeoffs, showing how autonomous coding agents can cut approval fatigue without fully removing risk.

AIAnthropic's Labs team describes a three-agent harness with planner, generator, and evaluator agents for building full-stack applications over multi-hour autonomous coding sessions. The evaluator uses Playwright to test the running app against sprint contracts, and a retro game maker built with the harness worked end to end where a single-agent run's core feature did not. The author later removed the sprint construct and kept only the components still needed on Opus 4.6.

Why it matters: The post shows how a generator-evaluator loop, with explicit grading criteria and a tuned QA agent, turned a solo run's broken output into a working app, and how the harness was pruned as models improved.