Fast on trends, easy on doing

The hardest-core AI tool field guide

Latest

By publish date, newest first

GitHub Copilot: Six Models Deprecated December 14, What to Fix

Six GitHub Copilot models are deprecated on December 14, 2026, and the official November 13, 2026 changelog gives six migration sentences but no configuration file name, model ID string or migration script. This SOP turns those sentences into a checkable list: replace hardcoded model names in workflows and integrations, enable model policies in Copilot settings, and understand what global default, the model selector, Copilot Chat, inline edits and code completions each do. All six model names and suggested alternatives are quoted as published, Kimi K3 stays To be announced, and the Claude Haiku 4.5 annual-plan exception for individual subscribers is spelled out.

TrnRT, Kindi, Baseten: One License Forbids Managed Service

Three inference engine repositories, TrnRT, Kindi and Baseten, on one comparison table, with license terms and hardware bets as the axis rather than a buying recommendation or benchmark ranking. Apache-2.0, Elastic License 2.0 and AGPL-3.0 coexist; one LICENSE says verbatim that the software may not be provided to third parties as a hosted or managed service, and GitHub reports NOASSERTION. Hardware claims from NKI megakernels on Trainium2 to GB300, B300, Quadro K420 and RTX 3080 are labelled as README self-reports. Stars are cumulative totals, with no growth score or single-day delta.

Frontline Hotspot

Fast-tracking AI industry hot events with concise ~1000-word analysis.

View all →

DeepSeek App APIs: Five Tools, Fees on Top of Tokens

Only what the DeepSeek November 13, 2026 changelog, guides and pricing page actually say about the full suite of application APIs: web search, deep-thinking search, file input, URL reading and model safety are now exposed on the cloud API, while Search, Fetch, OCR, ASR and TTS remain standalone APIs. Tool calls and context assembly happen server-side. Fees are quoted verbatim as tool usage fees in addition to standard token charges; no price conversion, no cross-vendor comparison, no invented discount end date, and the chat-demo repository and MIT license are described as published.

Hy Realtime Lands in Yuanbao, but the Cloud API Is Still Coming

Checks the official wording and channel timing of Tencent Hunyuan Hy Realtime, released on November 13, 2026: voice calls in Yuanbao and Tencent Customer Service are already live, while the Tencent Cloud API remains at the official will-soon stage with no public interface documentation, endpoints, or pricing. It stops at the web-search decision, the six song-request dimensions from the TME Co-Design, and the two entry layers of the Yuanbao voice preset and the partial web demo. Full-duplex interaction and the other two items remain on the roadmap. Internal A/B Test and chart figures are not turned into third-party results.

Gemini Decisions API: Up to 1,000 Judgments, Zero Output Cost

A November 11, 2026 official blog from Google introduces Gemini Decision 1 and the Decisions API: instead of emitting answer text token by token, the model scores candidate options in a single forward pass, evaluating up to 1,000 yes/no, choice, and rubric-scoring questions at once, with no output-token billing. The model ID is gemini-decision-1, and the input side accepts one multimodal input across text, images, audio, video, and PDFs (up to 256K). This piece checks only what the official page says verbatim and what it does not: no benchmarks, no rankings, no integration tutorial, and any unpublished pricing or availability is marked as not disclosed. As of November 12, 2026, qualifiers such as coming soon and rolling out are kept as written.

96% on a Production Line, yet DeepMind Calls It a Pilot. Why?

On November 10, 2026, Google DeepMind published two official posts the same day: on the robotics side, Gemini Robotics 2.5 helped the Apptronik Apollo 2 humanoid pick and pack automotive parts on Mercedes-Benz production lines with a 96% success rate that the vendor itself frames as a real-world proof-of-concept and pilot showing promising progress toward widespread real-world industrial applications; on the verification side, AlphaProof Code spent four weeks generating over six million lines of Lean - a lower bound, per the official wording - proving that the core cryptographic code of the Signal protocol delivers the key security properties its experts specified, with just one percent of the codebase needing human review. This piece unpacks four boundaries that get misquoted most often: 96% is a pilot, not mass production; 99.5% jailbreak resistance belongs to Gemini 4 Argon and 82% to the previous baseline Gemini Robotics ER 2, while 2.5's own safety numbers are 33% and 43%; four weeks measures the verification process, not the project; and the open-sourced ASIMOV-Jailbreak is a benchmark, not a model, with public availability, API and pricing unstated. As of November 11, 2026, missing denominators, counts and version numbers are recorded as unstated rather than inferred.

Hardcore Reviews

Real-scenario comparison tests of mainstream AI tools, with exclusive data and tables.

View all →

TrnRT, Kindi, Baseten: One License Forbids Managed Service

Three inference engine repositories, TrnRT, Kindi and Baseten, on one comparison table, with license terms and hardware bets as the axis rather than a buying recommendation or benchmark ranking. Apache-2.0, Elastic License 2.0 and AGPL-3.0 coexist; one LICENSE says verbatim that the software may not be provided to third parties as a hosted or managed service, and GitHub reports NOASSERTION. Hardware claims from NKI megakernels on Trainium2 to GB300, B300, Quadro K420 and RTX 3080 are labelled as README self-reports. Stars are cumulative totals, with no growth score or single-day delta.

qwen-code Preview, OpenBot, free-claude-code: Three Compared

Sets the qwen-code v1.0.0-preview beside OpenBot v1.0.2 and the rolling v6.x of free-claude-code in one table, comparing version states and access boundaries rather than picking a winner. Five rows cover models and providers, where AG-UI and MCP attach, permissions and approvals, stability during Preview, and license points. The free-claude-code column states AGPL-3.0-only, the NOASSERTION value from GitHub, the README disclaimer that it is not affiliated with Anthropic, and that provider terms govern integrations. Star counts are cumulative totals.

Qwen4, ERNIE, ChatGPT: Three Calendars, Three Different Tenses

Line up three official calendars posted in November and the single label coming soon stops working: Alibaba Cloud spells out the Qwen4-Max-Preview window but gives no general-availability date, Baidu frames ERNIE 5.5 Flash Preview open-sourcing as a pledge not yet delivered, and OpenAI publishes a dated sunset schedule for legacy voice modes, December 11, 2026, with a fixed replacement path. One undated, one unfulfilled, one already scheduled. This comparison covers only what each official page says, what it leaves unsaid, and when a stated commitment lands: no benchmarks, no ranking, no recommendation, and no filling in blanks on behalf of any vendor. As of November 12, 2026, sources are limited to official product pages from each vendor, specification docs, and help-center notices.

Three Vendors, One Day, Zero Published Prices: What Opened?

On November 10, 2026 OpenAI, Google and Anthropic all pushed AI into the work screen, yet their official pages read very differently: OpenAI puts Businesses in ChatGPT in beta, reaching the 1.2 billion weekly ChatGPT users with Business Agents first open to eligible U.S. ecommerce and online service businesses; Google splits two lines with a soon pathway from Gmail and Drive into Adobe Acrobat and a preview in the U.S. for Gemini for healthcare with partners HCA, Highmark and Northwell; Anthropic stacks beta (Whiteboards, Sheets), GA (Claude Data) and rolling out (interactive connectors) in one day. The side-by-side tables register published fields only - scope, plan availability (all paid plans, Team on by default, Enterprise off by default with Data flipping on November 19), statuses and qualifiers - and the most consistent column is pricing: none of the three official pages publishes one; unstated is not rendered as free, and nothing is ranked or recommended. Both claude.com pages contain no Claude Meetings string, so meeting features stay out; soon is never written as shipped. Angled against the earlier ChatGPT-in-Chrome work-mode hotspot.

Open Source

Curated open-source AI projects with verified GitHub data and hands-on breakdowns.

View all →

Univer Office SDK: Agents Edit Cells Without an AI SDK

Only what the dream-num/univer README, LICENSE and GitHub API fields support. Apache-2.0 covers the Web SDK core architecture and engine implementations; commercial plugins, the Server SDK and commercial AI SDK extensions are distributed under separate licences. Facade APIs such as FWorkbook, FWorksheet, FRange, getRange and setValues let an application or Agents Edit Cells directly with formula recalculation, while workbook.save() persists a JSON snapshot rather than XLSX import or export. No AI SDK is required anywhere in that path. Stars are cumulative GitHub API totals, not single-day growth.

llama.cpp and ggml Ship v1.0.0: Deprecated APIs Removed

Reads only what the GitHub API fields, the two v1.0.0 release notes, Discussion 1579, LICENSE and README of the ggml-org llama.cpp and ggml repositories can verify. Both v1.0.0 tags landed on November 13, 2026. It separates semantic versioning, the rule that a release tag requires the internal ggml copy to match the released one, the split between b-numbered nightlies and vX.Y.Z releases, and the 35 removed functions, RPC v9 and MIT notice-retention and AS IS terms. The August 2026 versioning discussion is not presented as a November announcement, and no figure from the unretrieved HF blog is quoted.

LingBot-Touch: Code Apache-2.0, Weights Elsewhere

Robbyant/lingbot-touch reached 238 stars within days of creation, with Apache-2.0 in both the license field and the badge alt text, yet the model weights are not in the source repository: the README states verbatim that model files are hosted separately and access requires an account with permission to the model repository. This piece reads only API fields, README wording, and the LICENSE text: created November 9, 2026, last push November 11, main language Python, default branch main, not a fork and not archived. It also covers how three heterogeneous tactile sensors feed one representation and how the two model variants differ, without importing scores, download counts, or star totals the repository never states. As of November 12, 2026, code licensing and gated weights remain two separate questions.

16 Megapixels, No Upscaler: What Does the Repo Actually Ship?

MiniMax H3-Image is an open-weight image generation model whose official repository MiniMax-AI/MiniMax-H3-Image (hyphenated GitHub organization) holds, as verified on November 11, 2026, no runnable inference code - only a model card, a license and resource files, with language unset and a single commit. The README model card states 33.1B parameters in a dense single-stream transformer, distilled to 6 sampling steps (6 NFEs) with no classifier-free guidance, about 16 megapixels at every aspect ratio directly and without an upscaler, BF16 DiT weights at 68.65 GB, and a Qwen3-VL text encoder kept outside the repository; the official launch post separately claims a 4K (4096 x 4096) image in under 10 seconds, Standard 1.5-2x and Highspeed 3-4x speeds, pricing at 50-70% of mainstream offerings and a launch-week 50% off for 4K-and-above requests - all launch-post wording, with no seconds figure anywhere in the README. The API guide caps output area at 20,000,000 pixels, allows 1 to 16 reference images and 1 to 10 images per request, and both endpoints are synchronous. The license stays a one-sentence boundary: community license with GitHub NOASSERTION, terms per the in-repo LICENSE, angled against the October 24 M3.1-Flash deployment SOP.

Field SOP

Scenario-based tutorials with real screenshots, prompts, workflow templates and pitfalls.

View all →

GitHub Copilot: Six Models Deprecated December 14, What to Fix

Six GitHub Copilot models are deprecated on December 14, 2026, and the official November 13, 2026 changelog gives six migration sentences but no configuration file name, model ID string or migration script. This SOP turns those sentences into a checkable list: replace hardcoded model names in workflows and integrations, enable model policies in Copilot settings, and understand what global default, the model selector, Copilot Chat, inline edits and code completions each do. All six model names and suggested alternatives are quoted as published, Kimi K3 stays To be announced, and the Claude Haiku 4.5 annual-plan exception for individual subscribers is spelled out.

Bedrock AgentCore V2 Snapshots: Four Patterns, One Pre-warm

Turns the four official AWS section names into a checkable sequence for Bedrock AgentCore runtime V2 session startup: measure Latency and OverheadLatency in CloudWatch first, move imports and static data into init, use Working with hooks for build-time large files, then send a background warm-up request with Pre-warm on user engagement and keep the session ID. It records the 120-second /ping gate, that the V2 default applies only to new and updated runtimes, that existing ones need explicit platformVersion=V2, and that the sample code is for non-production use. The Region and cold-start discrepancies between the two official pages are kept side by side.

OpenRouter: MCP Costs 17x More, Tool Results Are the Culprit

A measurement published by OpenRouter on November 11, 2026 wired one cli/cli repository question three ways: on Claude Sonnet 5.5, the default MCP server used 42 times the CLI input tokens and cost 17 times as much, $127 against $7.50 per 1,000 tasks. The official TL;DR points at tool results rather than tool definitions as what fills the context, with 20,400, 42,182, and an 8,336 to 714 trim all checkable row by row. This is a single-task measurement and a self-check list, not an integration guide or a price comparison. Tool Search varies by model: it lowers the full-task total on Sonnet while making Haiku and Gemini more expensive, and it does not shrink tool results. Run mcp_cost.py on your own tasks before deciding, as the official post advises.

$2 to $4 After November 30: Will Your Bill Double?

Gemini 4 Carbon's introductory price is $2 per million input tokens and $10 per million output tokens, same as Argon, and the vendor footnote states verbatim that after the introductory period expires on November 30, 2026 the price becomes $4 and $20 per million, applying to the Carbon model intended for public access only - the widely echoed December 1 date is a paraphrase; the official text gives only the expiry. This piece is a cost-accounting and decision checklist, not a setup tutorial: what the vendor actually said covers building today on the paid tier in Google AI Studio and Android Studio, consulting the Gemini API Developer Guide, and the introductory window through November 30; an explicit unstated list records what the pages do not specify (non-paid tiers, consumer timing, rate limits, context and tiered pricing, the verbatim model ID), with unstated never rendered as disallowed. The core claim follows the vendor cost qualifier - Argon remains the ideal choice for the majority of software engineering and knowledge work, while Carbon uses more tokens - so a low unit price per token is not a low cost per task, since different models consume different token counts for the same job; benchmark ranks and cost-per-task comparisons are Google-reported and not independently audited. Angled against the October 30 Carbon hotspot, staying on price-and-cost wording only.