标签：#t

AI is great at writing tests fast, and good at writing tests that look real but verify the wrong...

AI is great at writing tests fast, and good at writing tests that look real but verify the wrong...

Native code switching, better diarization, more languages. Discussion | Link

Touted as a less-hookup-focused Grindr, Goose is an invite-only space for gay men. The problem is the people promoting it don’t seem real.

Connect your AI agent to postal mail Discussion | Link

Preserving authentic organic posting since the collapse. Discussion | Link

"We've got time into 2027 before we're getting nervous."

The incident could disrupt a key part of the defense company’s rocket motor business, which designs and tests prototype motors for military customers.

Record home battery installations unlock options for grids—and AI data centers.

Selling server infrastructure would put Meta in competition with Amazon and Google.

Turn 1 creative into every ad format, instantly Discussion | Link

An optimal ratio of 10-15 grams of larvae per gram of specimen minimized cleaning time with no bone damage.

SpaceX reportedly showed investors a "handset-like" AI device before going public. It could be another signal SpaceX wants to expand into wireless.

Vendor onboarding usually starts with one clean request and then turns into a messy thread. Procurement asks for a W-9, security asks for a SOC 2 report, finance asks for remittance details, legal asks for an executed agreement, and the vendor replies with four attachments across three messages because different people own different parts of the process. That is exactly the kind of workflow where a generic "AI email assistant" gets risky. You do not want a model improvising legal language, requesting bank details in the wrong channel, or forwarding a confidential report to the wrong internal alias. You want the agent to own the repetitive coordination while your application keeps the state machine, policy, audit log, and approvals. The pattern I reach for is a dedicated Nylas Agent Account: vendors@yourcompany.com . It is a real mailbox the onboarding agent owns. It receives the vendor's replies, detects what is attached, updates your vendor record, sends safe reminders, and escalates missing or sensitive items to a human. The agent is not borrowing an employee's inbox, and it is not scraping a shared procurement mailbox. It has a grant, an email address, webhooks, threads, folders, and the same Messages API you would use for any other mailbox. I work on the Nylas CLI, so the terminal examples below use the commands I would use while building and debugging this flow. I also include the raw API calls because the production version belongs in your service, not in a shell script. What the agent should own Start by drawing the boundary tightly. A vendor onboarding agent should own message handling and coordination, not business approval. Good responsibilities: Receive vendor replies at a stable address. Read message bodies and attachment metadata. Match a reply to an existing vendor record. Detect which onboarding items are complete, missing, expired, or unreadable. Draft reminders and status updates. Schedule handoff calls when the vendor asks for help. Escalate sensit

The actor and investor is joining forces with Morgan Beller, who was previously a GP at NFX, to invest in early-stage startups.

Building an AI agent is fun. Fixing its production latency when it's juggling live data, RAG, and text-to-speech? Not so fun. In the latest episode of the AI Agent Clinic, we sat down with developer Sami Maghnaoui to debug PlaybackIQ, a football / soccer agent he built to provide pre and post match analysis with text to voice, and minute-by-minute match insights with interactive UI. The app was awesome, but under heavy "match day" data loads, the wait times were killing the UX. Here’s how we fixed it: The Bottleneck: We implemented OpenTelemetry on the Agent Platform to trace exactly where the LLM calls and data retrieval were hanging up. The Scale: We shifted the deployment to Cloud Run to properly handle concurrent traffic. The Result: We managed to slash the agent's latency by 80%. If you're dealing with sluggish LLM response times in your own apps and want to see what a production-grade fix looks like, we recorded the whole teardown and rebuild. 🎥 Watch the teardown here: [ https://youtu.be/G7olcqETSn8 ] (Let me know in the comments what your go-to stack is for tracing LLM latency!)

“We will own nothing, it's truly sad.”

Every data grid demo looks incredible with twenty rows. The columns line up. The hover state is tasteful. The checkbox has confidence. Someone scrolls three inches and everyone quietly agrees that software has advanced. Then the real product arrives. Fifty thousand rows. Twenty columns. Editable money. A custom status cell. Filters. Sorting. Horizontal scrolling. A user who pastes something suspicious from Excel. A product manager asking whether the total row can stay pinned while the server is slow. That is when a table stops being a table and starts becoming infrastructure. So we built a benchmark. Not a perfect benchmark. Those do not exist. A useful one. What we measured The fixture is intentionally boring: 50,000 deterministic rows 20 fixed-width columns 1,200 by 600 pixel viewport two editable columns sorting filtering virtual scrolling production bundles fresh browser contexts raw samples committed to GitHub No network requests. No paid-only feature tricks. No images. No grouping. No heroic demo code designed to make one library look blessed by destiny. The report measures: JS gzip : reachable JavaScript after gzip Ready median : navigation until the grid adapter mounts and two animation frames pass Scroll settle : one scripted vertical and horizontal jump plus animation frames Mounted cells : body cells in the DOM after the scroll Interaction health : heap, long tasks, estimated FPS, dropped frames Live benchmark: https://vitashev.github.io/react-data-grid-benchmark/ Source and raw samples: https://github.com/Vitashev/react-data-grid-benchmark The part most benchmarks get wrong Not every grid exposes the same surface. For example, MUI X Data Grid Community uses 100-row pagination for this workload. That is a valid product boundary, but it is not the same as continuously virtualizing 50,000 rows. So the ranked tables include only compatible continuous-scroll libraries. MUI remains in the fixture and raw data, but not in the leaderboard. That makes the benchma

CodeTrace-AI v1.0.1 — Stop Reading Code. Start Understanding It. Every developer has experienced this. You clone a repository, open it, and suddenly you're staring at thousands of files. You spend hours answering questions like: Where is this function called? Which files depend on this module? What happens if I modify this class? Is this code even used anymore? Traditional tools like grep , IDE search, or AI chat assistants can help you find code. They don't help you understand the architecture . That's why I built CodeTrace-AI . What is CodeTrace-AI? CodeTrace-AI is an AI-powered code intelligence tool that transforms your repository into a searchable structural knowledge graph. Instead of treating your project as plain text, it understands your codebase structurally by analyzing: 📂 Folder hierarchy 📄 Files 🏛 Classes ⚙ Functions 📦 Imports 🔗 Function calls 🌐 Cross-file dependencies Think of it as having an AI Software Architect that understands your entire repository. 🚀 What's New in v1.0.1 This release focuses on speed, privacy, and understanding large repositories. 🕸 Interactive Code Graph One of the biggest additions is the interactive repository graph. Instead of reading hundreds of files manually, you can visualize relationships between: Folders Files Classes Functions Imports Function calls Understanding a new project becomes dramatically easier. ⚡ SHA-256 Delta Sync Engine One feature I'm particularly proud of is the new Incremental Indexing Engine. Most code intelligence tools rebuild their entire index every time. CodeTrace-AI doesn't. It computes a SHA-256 fingerprint for every tracked file and detects: ✅ Modified files ➕ Newly added files ❌ Deleted files Only those files are: Re-parsed Re-embedded Re-added to the knowledge graph Everything else is skipped. This makes repeated indexing dramatically faster, especially for large repositories where only a few files change between runs. Under the hood The sync engine includes: SHA-256 fingerprinting Parallel f

DeepSeek has previewed its V4 model family, led by a 1.6 trillion-parameter flagship, and made a one-million-token context window the default across all its services. The weights are downloadable and self-hostable, putting frontier-scale long context in reach of smaller labs and individuals without per-token payment to a closed provider. Key facts What: DeepSeek previewed two free-to-download V4 models that can read a million tokens at once, no longer as a premium add-on but as the standard setting. When: 2026-06-29 Primary source: read the source A large language model has no persistent memory. Each time it answers, it re-reads everything in front of it — your question, the conversation so far, any documents you pasted — and that pile of text is the context. The context window is the hard ceiling on how much it can hold at once. For years that ceiling was a few thousand words, then tens of thousands. Pushing it to a million has been possible but expensive, usually sold as a special, pricey tier. DeepSeek's move is to make a million the everyday default. The family comes in two sizes. V4-Pro is the big one — 1.6 trillion parameters in total, but only about 49 billion of them switch on for any given word. That design is called a mixture of experts : instead of running the entire brain for every token, the model routes each piece of text to a small relevant subset of specialists, so it stays affordable to run despite its enormous size. V4-Flash is the smaller, cheaper, faster sibling, meant for everyday chat and quick edits, and DeepSeek says it keeps up with Pro on simpler agent tasks. Making a million-token window affordable comes down to how the model handles its KV cache — the running set of notes it stores about every previous word, which grows steadily the longer the conversation gets. At a million tokens those notes become a mountain of memory, and the model normally has to consult every note for every new word it writes. DeepSeek's approach, which they call sp