#Tutorial/How-to

AIAugment Code's Solutions Architecture lead used the Cosmos agentic orchestration platform to build a live pilot-health view that combines product usage, GitHub and PR activity, Salesforce deal data, and customer call transcripts. Each account's health and board-level one-liner was checked against the customer's own stated success criteria, such as a 30% PR merge-time reduction. The article says the view refreshed from current Salesforce data and was designed to avoid inflating usage numbers through session lineage reconciliation.

AIGoogle Search and Google Maps can now be used in the same Gemini API call with Gemini 3.5 Flash and 3.6 Flash. Custom functions and MCP servers can be added to the same request through Tool Combination. The author says Gemini handles the search, place lookup, and function call in one interaction without extra roundtrips from the developer's side.

AI…performance is critical. More details to start building:

AIMy cofounder @pwendell wrote about how we and other tech companies are starting to manage this resource now, by routing everything through an AI Gateway. This enables centralized analysis (e.g. we found settings we can change on Claude Code and Codex to lower cost a lot), smart routing, and “pushing down” control to our engineers so they can set budgets on individual tasks and prevent surprises.

AIDatabricks published an analysis of four techniques it used to reduce internal AI spend while growing adoption, with savings of up to 90% in some scenarios. The techniques are shifting defaults to cheaper models such as GLM, automated task-level model routing, per-user spend visibility with adaptive budgeting, and pruning context bloat. The author, Ali Ghodsi, reposted Databricks co-founder Patrick Wendell's summary and recommended it.

AIit’s a WAY better experience. rn agents behave too much like the world is going to stay static. this unhobbles them quite a bit and gets them to talk/act more like AGIs.

AIEach video includes its prompt. Try one with LongCat-2.0, put your own spin on it, and share what you create! 🚀 API → 💬 Discord →

AIKimi Slides handles the entire slide-building process: - Clear structure and research, powered by Kimi K3 - Cohesive design, including polished charts and SmartArts - Editable and ready to download Let us know what you'd like to see next in the comments!

AIOpenRouter has released Ori Eval, an agent-driven tool that runs your app's prompts against candidate models and returns a comparison table of catch rate, latency, cost per PR, and pass/fail results. The tool asserts on called tools and grades open-ended answers with an LLM judge, pinning the harness and model during each run. Its evals are code files that can run in CI to block regressions and re-run when new models ship.

AIFireworks AI ran controlled SFT experiments on Qwen3.5-9B comparing LoRA with full parameter fine-tuning across three synthetic verifiable tasks. The post argues that a FullFT advantage can come from data coverage, learning-rate tuning, or adapter rank, and it recommends testing these in that order before switching methods. Under a fixed multi-task budget, FullFT kept a 4.29-point lead over the best LoRA recipe tested, while matched data exposure favored LoRA.

AI…create model/dataset repos, store data in Buckets, or even kick off GPU-backed Jobs!

AILiquid AI doubled the LFM2 tokenizer's vocabulary from 65K to 128K without retraining from scratch, extending the original BPE merges and initializing new embeddings as the mean of their sub-tokens. The expanded tokenizer needs 4.0× fewer tokens for Thai, 2.6× fewer for Vietnamese, and 2.4× fewer for Hindi, which the source says yields roughly 2.2–3.7× faster on-device decoding for these languages with no reported quality loss on previously supported languages. LFM2.5-8B-A1B and the expanded tokenizer are available on Hugging Face with open weights.

AIFireworks AI describes fine-tuning Qwen3-Embedding-8B on private (query, positive) pairs using bidirectional InfoNCE loss through its Training SDK, then serving the model via an OpenAI-compatible embeddings endpoint. The post reports that around 150 training steps was enough, that rank-32 LoRA landed within about one point of full-parameter fine-tuning, and that gains were largest where the base model struggled, while tasks like CoSQA and FiQA2018 showed flat results.

AIFireworks AI has made Kimi K3 available for Multi-LoRA serving and training in private preview through Fireworks Serverless Training. The post explains how small LoRA adapters can be trained on K3 and served with live merge or multi-LoRA deployment, and it reports two example tasks, Countdown and Frozen Lake, with reward curves.

AITrilogy released an AI Cybersecurity Playbook built around Kimi K3, served on Fireworks through an OpenAI-compatible API. The playbook pairs deterministic tools for indexing, parsing, and deduplication with Kimi K3 for reachability, impact, and remediation judgment, followed by a separate verification stage.

AI…in that world. Opus worked overnight to create a renderer, savegame parser, and boat/plane/truck/bus simulator:

AIEthan Mollick's guide says ChatGPT and Claude are the main choices for real work, since their agent modes can act on a computer. He separates agent modes that run on the company's computers from those that access the user's own computer. He recommends keeping approval settings on for sending, spending, or deleting, because of prompt injection risk. He also notes that Gemini currently lags for agentic work, though its Notebook and video tools are useful.

AIBen used ChatGPT as his construction consultant, helping Ben shape the structural design, source materials, and, crucially, translate his kids’ “wild ideas” into actual, buildable plans. Today, the treehouse is still evolving, and the family project keeps growing one Sunday - and one wild idea - at a time.

AIAndrej Karpathy describes using /voice to ramble for about 10 minutes, sometimes as a short interview, to give an LLM context that would be tedious to type. He says LLMs reconstruct these messy streams of thought remarkably well, often returning a cleaner version than the speaker started with, which improves shared understanding and reduces later corrections.

AIHere's my prompt for it: Manage my calendar for the week. Requirements: 1. <20 hours of meetings 2. Dedupe conflicting meetings. Look at past weeks to see what kinds of meetings I decline. Dinners don't count against the 20 hours. Build a skill that you refine. Ask me before updating invites. What do you use Cowork for?

AIThe article explains how reasoning models can offer multiple effort modes, separating training-time methods from inference-time controls such as system prompts and chat templates. It compares six open-weight models, including DeepSeek V4, Nemotron 3 Ultra, Kimi K2.5, GLM-5, Qwen3, and Inkling, noting that their reports disclose different levels of detail. It also shows how GPT-5.6's model selection and effort settings act as two separate scaling axes.

AISekhar and Katie Brandt built Foreguard, a free tool built with ChatGPT and Codex, to help families claim public benefits they are entitled to and plan private insurance coverage. The tool shows that modest budgets of $100 a month can create millions of dollars of day-one financial protection. The goal is to help families prepare earlier, before care decisions become urgent.

AIDeepLearning.AI has launched a short course, built with Cerebras, on building LLM applications that respond quickly using inference-optimized hardware. The course compares how GPUs, TPUs, and Cerebras' Wafer-Scale Engine handle the memory-to-compute bottleneck, which keeps model weights close to compute units to speed token generation. It covers real-time applications such as live translation and voice agents, plus habits for agentic coding.

AINow ChatGPT helps him run the business and build custom machines to automate the work behind it:

AI…Train your own LoRA 🎵 Use Stable Audio with Ableton 🎵 Build your own audio tools on top of the model … and more

AIBasic comfort with music tools and Python is helpful, but not needed.

AIJoin us for a free hands-on workshop in partnership with @MusicHackspace, exploring how you can use Stable Audio 3.0 to create custom audio applications and workflows.

AIStructural engineer James Costello, who oversees complex New York City high-rise demolitions, uses ChatGPT to review lengthy contracts, organize compliance documents, and create construction plans for his family-rooted firm DEMTEC. The post says the tool helps him move through these workflows faster and with more confidence, freeing time to grow the business and support his team.

AIWith her career at a crossroads, she moved to Atlanta, found a sewing machine in a friend’s attic, and taught herself a new craft. Inspired to design by her mother’s legendary disco style, Chan uses ChatGPT to help refine her sketches and bring her visions to life. She continues to create her own opportunities within the fashion industry, now dressing some of entertainment’s biggest names.

AIEmma Dahl wanted a historically inspired wedding dress that incorporated pearls from her grandmother's necklace, so she used ChatGPT over months to troubleshoot niche sewing and corset construction. The chatbot also helped her choose a sewing machine upgrade, the shape of her veil, and how to pack and travel with the orchids for her bouquet.

AIThen, we're going deep on how Claude Tag actually works. AI used to finish your sentence. Then, it wrote entire features. Now, Claude Tag can monitor your channels, do proactive work for you, the whole team can steer it, and it remembers what you told it last week. Register:

AIone of my new favorites is for sourcing candidates: - tell cc about the role and backgrounds i’m looking for - ask cc to kick off a dynamic workflow to find 100 candidates, and include linkedin, twitter, blog, podcasts, and one-line pitch for each - ask cc to make an artifact and email it to me. then, i lock my laptop and head out for the day - i review the list on the go once cc is done!

AIAndrew Ng describes three loops he uses to build 0-to-1 products with AI agents: an agentic coding loop, a developer feedback loop, and an external feedback loop. He says the agentic coding loop runs every few minutes, letting coding agents build, test, and iterate on software for around an hour without human intervention. The developer feedback loop operates over tens of minutes to hours, with humans steering product decisions because they hold a context advantage over AI systems.

AISebastian Raschka's tutorial shows how to build a fully local coding agent by pairing an open-weight LLM served through an inference runtime with an open-source harness that can read files, edit code, and run commands. He recommends Qwen-Code for Qwen3.6, citing Nvidia's Polar paper, which found Qwen models performed best in Qwen-Code. The Qwen3.6 35B-A3B model is about 22 GB to download and needs roughly 30–40 GB of RAM.