Gondola has doubled its revenue while expanding its use of OpenAI's Codex, which raised its lead engineer's output by 50%. The company, which helps creatives get credit and get hired, also uses ChatGPT to simplify daily work.
Amplitude's proactive product agent Wave, built primarily on OpenAI models, identifies what to build, helps teams ship changes with coding agents, and measures the impact. The setup lets Amplitude ship product improvements in 1–2 days.
Microsoft Research Focus Edition #98 highlights AI advances bringing universal translation closer to reality and a new proof resolving the 31-year-old KLS conjecture in high-dimensional geometry. The edition also covers CompactionBench and APEC, which cut coding-agent context compaction costs by up to 25.4% and execution time by 9.6%, plus the Latent Core Tokenizer, which improved tokenization across 104 languages.
Amplitude's proactive product agent Wave, built primarily on OpenAI models, identifies what to build, helps teams ship changes with coding agents, and measures the impact. The setup lets Amplitude ship product improvements in 1–2 days.
A self-service LLM gateway built on Amazon Bedrock Application Inference Profiles and LiteLLM running on AWS Fargate exposes Bedrock foundation models behind an OpenAI-compatible API, giving developers a single base URL and per-user key. The setup adds per-user spend controls, per-model quota isolation, and CloudWatch RPM/TPM observability, with Langfuse for prompt-level telemetry. Self-service key issuance requires LiteLLM Enterprise, since the free tier is limited to five users.
Moonshot AI's Kimi K3.1 Pro Highspeed is now available on Amazon Bedrock, a post-trained version of Kimi K3 with the same 3T-class open-weight architecture and 1-million-token context window, trained with more post-training compute for long-horizon agentic work and fewer factual errors. Moonshot AI reports 2–3 times the output speed of Kimi K3.1 Pro, and existing Kimi K3 users can switch by changing the model ID. The post shows Chat Completions, Responses and Converse API calls, the Flex tier at half the Standard price, explicit prompt caching with prompt_cache_breakpoint, and connecting the model to the OpenCode coding agent.
Holiday Extras is using OpenAI's Codex to turn customer expertise into better apps, higher booking conversion and new growth opportunities. The travel add-ons company is rethinking what it can build with the coding model.
A Google engineer who leads the company's agent skills program built a pipeline in which Gemini 4 Argon reads Go source and RISC-V disassembly and translates surviving runtime.panicBounds traps into Z3 constraints, then go test replays any satisfying input as a real reproducer. The workflow caught all three planted bugs and three latent bugs in skill-lint, while unseeded go test -fuzz missed two of the planted crashes because Go checks slices against capacity rather than length. Clipping capacity to length with data[:len(data):len(data)] made the fuzzer crash both overrun bugs in all three runs, with a median of 0.28 s and 0.17 s.
Google DeepMind made Gemini 4 Carbon available to developers, enterprises, scientists and consumers, positioning it above Gemini 4 Argon for tasks that need deeper reasoning and more tokens. Carbon ranks #1 on CursorBench 4.0, Perplexity's WANDR and Zapier's AutomationBench at more than 2X lower cost per task than the next best external model, and is priced at $2 per million input tokens and $10 per million output tokens, the same introductory price as Argon. Google also previewed /swarm in Google Antigravity, which turns a single prompt into a coordinated team of agents, and reported that Carbon blocked 99% of attack trajectories in simulated cyberattack testing.
Why it matters: Google's release notes detail how Gemini 4 Carbon trades higher token usage for deeper reasoning, ranking first on CursorBench 4.0, WANDR and AutomationBench at under half the per-task cost of the next external model.
Meta released Muse Ember, its smallest and most efficient model, aimed at the repetitive work agents do all day such as tool calls, coding subtasks, routing, extraction and long document parsing. Meta says it matches Claude Haiku 5.5's best score at about a third of the cost and beats every GPT-6 Luna setting, at $0.10 per million input tokens and $0.50 per million output tokens. It ships with a 1M-token context window, up to 512K output tokens, native text, image, audio and video input, and is available today on Muse Code and the Meta Model API as muse-ember-1.0.
Why it matters: Meta's smallest model targets the high-volume agent steps, and its cost-per-task comparison against Claude Haiku 5.5 and GPT-6 Luna shows where the efficiency claim comes from.
GitHub published a developer's guide to agentic engineering, walking through how Copilot supports the Plan, Build, Verify, and Observe stages of software work. The guide cites GitHub's 1.2 billion commits in one week this October, over 400% more than a year earlier, and a Faros AI study finding pull requests spent 441% longer in review as teams moved from low to high AI adoption. It details features including Copilot in Slack or Teams, Plan Mode, GitHub Agentic Workflows, cloud sandboxes, session continuity, shared memory, Copilot Dreaming, and Copilot Fusion.
) references. Agents acted on the bug ID in 6% of encounters, and 83% of those actions were unprompted by the developer; 41% of unprompted detours chased already closed tickets while 57% hit still-open bugs and expanded scope. Controlling for developer, codebase complexity, task type, model tier and other factors, unprompted bug detours added 70% more steps, 77% more tokens and 105% more wait time per session.
Why it matters: Google's large-scale trace analysis shows stale TODO bug references pull coding agents into unprompted detours, and its cleanup agents removed thousands of obsolete references with over 95% reviewer acceptance.
Microsoft Research introduced PDD Kit, a research prototype that turns a developer's plain-language intent into a Verus formal specification, proves the coding agent's Rust code meets it for every input, and falls back to tests where a proof cannot reach. In a demo inside GitHub Next's Chopin, the team used PDD Kit to verify the login logic of Pet Store, a roughly 5,000-line Rust full-stack app, with the developer reviewing the intent artifact rather than the generated code line by line. PDD Kit only verifies Rust today, and its guarantees rest on six developer-approved trusted pieces, including the bcrypt password check and the two database lookups.
Figma's code layers feature is now in open beta for 100% of users, letting teams build and compare code-backed prototypes directly on the Figma canvas. The walkthrough shows a designer cloning a GitHub repository into a code layer, prompting the Figma agent to generate three delivery-address variations side by side, and refining one in the full-screen code editor. Extract designs turns screens or recorded flows into editable design layers that can be sent back to the prototype with Update code layer, and the agent can merge two teammates' code layers into one combined experience.
Microsoft Research Focus Edition #97 highlights ForkPilot, a self-improving agentic framework that matches the best existing methods while cutting AI processing demands by up to 59% across six benchmarks. The edition also covers CABRA, a framework showing coding agents still struggle to understand unfamiliar codebases, and TeleTune, which learns reusable skills from user activity logs. It also examines Copilot Chat activity, where document editing exceeded 20% of classified activities.
Meta has moved Catching JiTTests, its LLM-based just-in-time test generation approach, from research prototype into production infrastructure, and published the results in the FSE 2026 paper "Just-in-Time Catching Test Generation at Meta." The system runs overnight on spare capacity, targets risky diffs, generates tests through dodgy-diff and intent-aware workflows, and filters false positives with an LLM-as-Judge ensemble plus a rule-based RubFake assessor before reaching engineers. As of writing, 589 engineers (64% of outreach) engaged with the results, which showed a 60% true-positive rate, and in the first half of 2026 the system caught 74 serious privacy bugs at the diff stage and lowered privacy SEVs by 20%.
Mistral AI released the open weights of Mistral Large 4 (Le Chonk), a 1-trillion-parameter natively multimodal model that entered public preview earlier this month and was trained from scratch in Europe. The company says three additional weeks of reinforcement learning lifted it to the top of open-weight coding, with 41% on Terminal-Bench 4.0 and 48% on the Artificial Analysis Coding Agent Index while using 47% fewer tokens per task than GLM-5.3. It adds Low, Medium and High reasoning modes, scores 51% on the Artificial Analysis Cyber Index, and is priced at $0.70 input, $0.07 cached input and $2.10 output per million tokens under a modified MIT license.
Why it matters: Mistral opens the weights of its 1-trillion-parameter flagship, pairing coding and defensive-security benchmark gains with three reasoning modes and per-token pricing.
Google DeepMind announced Gemini 4 Carbon, its strongest model yet, with state-of-the-art cybersecurity and long-horizon capabilities, ranking #1 on the v5.0 Artificial Analysis Intelligence Index at 59. It scores 88.2% on SEC-bench Pro for finding vulnerabilities, 54.8% on ExploitGym for exploitation and 71.0% on CWE-bench for patching, and reaches #4 (1768) on WebDev Arena. Carbon launches at the same introductory price as Argon, $2 per million input tokens and $10 per million output tokens, and is first available to a subset of cyber defenders through the Fairwind Program before wider release.
Why it matters: Gemini 4 Carbon's benchmark results in vulnerability discovery and patching show how frontier models are being positioned for cybersecurity defense work.
Replit launched Cloud Agents for existing repositories, letting anyone on a team describe a change in plain language and have the agent open a tested pull request in GitHub or GitLab, available to all Pro and Enterprise customers. The agent runs each change in isolated cloud sandboxes, clicks through the running app, and attaches screenshots and video to the PR, while shared environments give every contributor a preconfigured setup that updates from the main branch. Replit also introduced early-access self-improving workspace memory, which turns review comments into team skills that engineers approve, and a Slack integration that lets users mention @Replit in a thread to start a change.
Why it matters: Replit 把 Cloud Agents 接入企业既有代码库，让非工程人员以带测试视频的 PR 形式提交改动，展示了 AI 编码工具向团队协作流程延伸的一种路径。
Three Java Champions with over a decade of Java experience each shared how they use GitHub Copilot in production and open source work. Vlad Mihalcea built a Hypersistence Optimizer web app in two days instead of weeks, and created custom skills trained on 65 of his articles to match his writing voice. Patrick Baumgartner migrated roughly 900 teaching slides across 15 presentations from Reveal.js to Marp with Copilot, verifying results through screenshot comparisons.
GitHub Copilot app sessions can now be opened directly in VS Code, carrying over the conversation, code changes, and worktree so developers can review diffs, edit by hand, and test locally without restarting. The tutorial walks through opening a session, reviewing the agent's changes line by line, continuing the same conversation in the Copilot sidebar, and pushing updates to the session's pull request.
MiniMax officially rolled out MiniMax M3.1 Flash, a next-generation Flash model that it says cuts usage cost by 70% versus its predecessor and makes online inference nearly three times faster. The company reports 73.7% on DeepSWE v1.1, 76.2 on BankerToolBench, 61.7 on OSWorld V2, 29.6 on Agents' Last Exam and 82% on CyberGym, with output speeds of 200+ TPS and a median of 170+ TPS. Pricing is $0.15 per 1M input tokens, $0.60 per 1M output tokens and $0.015 per 1M cached input tokens, and the model is available through the MiniMax API, M Plan and MiniMax Code, with weights to be released later.
Why it matters: MiniMax's Flash model claims top-tier agentic and coding scores at $0.15 per 1M input tokens, offering a concrete data point on the cost side of agent workloads.
The Claude Code team describes its layered code review flow, in which most reading is done by machines and human attention is reserved for risk-based approval. From June to September, merged pull requests to the Claude Code codebase more than doubled while the share that had to be reverted fell by more than 40 percent. The process stacks verification before the PR, required CI, Claude review, security review, risk-tiered human approval and a merge queue with flags and fast rollback, and the team turned past incidents into a daily eval set for the reviewer.
Why it matters: Anthropic's Claude Code team details how it moved most code reading to automated layers while merged PRs doubled and reverts fell over 40 percent, offering a transferable review model for agent-heavy teams.
Meta released the weights for Muse Spark Open, an open-weight natively multimodal model with 816B total parameters (42B active) and a 1M-token context window, positioned for coding and agentic work. It is the first model in its class to run on a desktop using two Apple M5 Ultra Mac Studios with the MLX framework, and it is available through API partners including Baseten, Fireworks AI, Groq, Modal, Nebius, OpenRouter and Together AI, with weights on Hugging Face, Amazon SageMaker AI, Google Cloud Model Garden and Microsoft Foundry Models. Meta says the model ships with auto-tunable Helion GPU kernels in SGLang, delivering 1.03-3.95x kernel-level speedups on NVIDIA and AMD GPUs and a 3% end-to-end speedup on AMD MI350.
Why it matters: Meta releases open weights for an 816B-parameter multimodal model that runs on two Mac Studios, giving developers a local option for long-horizon coding and agentic tasks.
Meta released the weights for Muse Spark Open, and Modal now serves the model through its Auto Endpoints with per-token billing. The model targets agentic coding and long-horizon tasks, with native multimodal understanding, a 1M-token context window, multi-step planning, sequential tool use and failure recovery. Meta reports 76.4 on Terminal-Bench 2.1 with the Terminus 2 agent and 60 on DeepSWE 1.1 using its preferred harness at xhigh reasoning effort.
Why it matters: Meta's open-weight Muse Spark Open is now served on Modal, giving teams a per-token way to try an agentic coding model with a 1M-token context window.
Vapi 工程师 Lat Ware 复盘自建 Pedantic Review Bot 的实践，该机器人现已审查每个 PR，平均合并时间从 130 小时降至 65 小时。
Meta introduced the Muse Wonder series, comprising Muse Wonder and Muse Wonder Full, which it says delivers state-of-the-art performance on personal and professional agentic tasks, memory and coding. Muse Wonder is available today through the Meta Model API and Muse Code, while Muse Wonder Full is available today for Muse Code subscribers. The models pair Active Memory, which carries context across conversations and retrieves task-relevant details, with Active Focus, which sustains work on long-running goals and checks in before important actions; Meta says both were trained at its gigawatt-scale Prometheus data center.
Why it matters: Meta's Muse Wonder series claims state-of-the-art results on agentic, memory and coding benchmarks, with Active Memory and Active Focus as the two capabilities it is built around.
Mistral has launched a public preview of Mistral Large 4, a 1 trillion-parameter natively multimodal model with 52 billion active parameters, available now through the Mistral Studio API. Mistral says the model is competitive with the strongest open-source models and outperforms other open-weight models from the US and Europe, scoring 82% on an Artificial Analysis Cyber Index vulnerability reproduction and patching test and 49.8% on its combined Coding Agent Index. The weights are set to be released by the end of the month, after red-teaming with cybersecurity partners and authorities; Mistral says the model was trained from scratch on 3,800 NVIDIA Grace Blackwell GPUs in its own European datacenters.
Why it matters: Mistral's largest model yet claims open-weight leadership in cybersecurity and agentic coding, with weights promised by month's end.
GitHub released ReviewBench, an open benchmark for AI code review agents built on 219 public pull requests across 19 languages, with language and repository-size distributions modeled on 103.9 million GitHub pull requests. The golden set draws findings from human reviewers, author follow-up commits, static analysis and multiple frontier LLMs, graded by Claude Sonnet 5 under a published rubric, and senior engineers independently re-labeled every finding with 96.6% agreement. GitHub says its offline evaluation of Copilot code review anticipated the direction of a production A/B test, where addressed rate rose 8.0%, recall rose 13.6% and cost per review fell 8.0%.
GitHub Blog outlines three skills developers should strengthen as AI changes their work: directing AI agents rather than just using them, critically reviewing AI output instead of trusting the first answer, and using time saved by AI to tackle broader problems. It cites GitHub Copilot's built-in Rubber Duck agent, which uses a second model to critique plans, code, and tests before a developer proceeds.
Factory has made Automations generally available, letting teams describe a recurring workflow and have Droid run it on a schedule or event trigger. Each automation combines a trigger (schedule, Slack, GitHub, or webhook), instructions, a user-chosen model and reasoning level, and a machine that can be local, connected, or a Factory-managed Droid Computer. Factory says 52% of enterprise users ran automated code review in the past 30 days, 48% used security review, 35% used AutoWiki, and automation session volume grew 51% over the prior 30 days.
Why it matters: Factory makes its Automations generally available, showing which recurring engineering workflows enterprises actually hand to Droid and how model and machine choice work per task.
Anthropic released Claude Sonnet 5.5, the second model in the Claude 5.5 family after Opus 5.5, which the company says is smarter, more efficient and 30% faster than Sonnet 5 at the same per-token price. Because it typically needs fewer tokens per task, Anthropic says most work costs up to 30% less, and the model ships with a native 1M-token context window, 128k max output and thinking on by default. The release guide lists breaking changes for Sonnet 5 users, including replacing disabled thinking with the between_tools setting, swapping forced tool_choice for auto plus strict tools, and moving computer use to the computer_toolset_20260801 toolset.
Why it matters: Anthropic's Sonnet 5.5 keeps Sonnet 5 pricing while cutting per-task token use, and the migration notes show what changes for teams already building on Sonnet 5.
MiniMax released M3, an open-weight model it says is the first to combine frontier coding and agentic performance, a 1M-token context window, and native image and video input. M3 uses MiniMax's new MSA sparse attention architecture, which the company reports cuts per-token compute at 1M context to 1/20 of the previous generation and speeds prefill by more than 9x and decoding by more than 15x. It scores 59.0% on SWE-Bench Pro, 66.0% on Terminal-Bench 2.1 and 74.2% on MCP Atlas, and is available through MiniMax Code, the Token Plan and the API, with weights and a technical report promised within 10 days.
Why it matters: MiniMax M3 combines a 1M-token context, frontier coding and agentic scores, and native image and video input in one open-weight model, with MSA cutting per-token compute at long context.
OpenAI released a Developers plugin that gives ChatGPT and Codex access to the OpenAI API Platform and API setup guidance, with adaptations for Claude Code and Cursor bundling portable developer skills and the public OpenAI Docs MCP server. It covers API key setup, Agents SDK app building, API migration to the Responses API, and troubleshooting common API failures.
Factory built an open-source benchmark testing 13 models on 50 real pull requests from Sentry, Grafana, Keycloak, Discourse and Cal.com, with each model reviewing every PR at least three times at high reasoning effort and an LLM judge scoring findings against a human-curated golden set. GPT-5.2 led at 60.5% F1 for $1.25 per PR, ahead of Claude Opus 4.6 at 59.8% F1 and $3.11 per PR, while MiniMax M2.7 reached 45.6% F1 at $0.15 per PR and Kimi K2.5 hit 51.9% F1 at $0.41. Factory says cost explains only about 21% of quality variance, and it open-sourced the golden set, evaluation scripts and a Droid Action GitHub Action supporting all 13 models.
OpenAI published an overview of new Codex app updates aimed at working across tools, apps, automations and other developer workflows. The material is a short summary only, so specific features, versions and availability details are not described.
Why it matters: OpenAI outlines Codex app updates that extend the coding agent across tools, apps and automations, showing how its scope is widening beyond code generation.
OpenAI released a Codex prompting guide for developers calling the Codex-tuned gpt-5.3-codex model directly through the API, recommending medium reasoning effort for interactive coding and high or xhigh for the hardest tasks. The guide covers migrating an existing harness to the open-source codex-cli, including the standard Codex-Max prompt, the apply_patch, shell_command and update_plan tools, and first-class compaction via /compact in the Responses API for multi-hour sessions. It also describes the new phase field, supported only on gpt-5.3-codex, which marks assistant items as commentary or final_answer and must be preserved in history to avoid performance degradation.
Why it matters: OpenAI's official guide details how to tune prompts, tools and compaction for gpt-5.3-codex, giving teams a concrete migration path for their own coding agents.
Ramp built Ramp Inspect, an internal background coding agent running on Modal Sandboxes, and it now starts roughly half of all merged pull requests across Ramp's frontend and backend repos. Each session boots a full-stack environment with Postgres, Redis, Temporal and RabbitMQ in seconds, because a Modal cron job clones repos and saves filesystem snapshots every 30 minutes. Modal Functions, Dicts and Queues handle snapshot builds, session locks and prompt routing, letting Inspect support multiplayer sessions and hundreds of concurrent sessions without one affecting another.
Modal 推出 GLM-5 的免费 OpenAI API 兼容端点，可用至 4 月底，限单个并发请求，同时发布在单节点 8 张 B200 上用 SGLang 部署的可复现代码。
Why it matters: Modal 为 Z.ai 的 GLM-5 提供免费 OpenAI 兼容端点，并给出在 OpenCode、OpenClaw、Claude Code 和 Vercel AI SDK 中接入的具体配置。
OpenAI introduced the Codex app, a dedicated app for its Codex coding agent, in an official developers blog post. The post is an intro walkthrough covering the app and its core workflows, with the full video hosted on YouTube.
Why it matters: OpenAI's official walkthrough shows how the Codex app structures core coding workflows, useful for developers weighing it against existing coding agents.