Последние посты
Programming & AI Tips
23 сент., 07:26
GPT-6 Sol and GPT-6 Luna are in the API 🚀OpenAI shipped GPT-6 Sol and GPT-6 Luna for API developers, alongside their availability in Codex and ChatGPT.This is a two-model release, so do not blindly swap your existing production model. Put both behind the same eval set first: tool calls, structured output, long-context retrieval, refusal behavior, and latency under your real prompt size.What to do this week:• Add Sol and Luna as versioned model options in your config. • Run replay traffic against a fixed golden set. • Log model ID, token use, tool errors, and task success separately.A model migration is an engineering change, not a dropdown change.[ Read More ] : https://openai.com/index/introducing-gpt-6-sol-and-luna/〰〰〰〰〰〰 #AI #OpenAI #LLM #API @ProgrammingTipOpenAIIntroducing GPT-6 Sol and LunaMeet GPT-6 Sol and Luna, two models that bring frontier intelligence to everyday work with different balances of capability and cost.Programming & AI Tips
21 сент., 10:38
Hex turns GPT-6 Astra analysis into visual reports 🚀Hex is using GPT-6 Astra to turn complex analysis into visual reports. The useful bit is not just asking a model to summarize a table. It is moving from an analysis request to a result people can inspect and share.What this points to:• Analysis as an artifact: teams need charts, assumptions, and outputs, not a chat answer pasted into Slack. • Human review still matters: a clean report can hide bad joins, stale data, or a wrong metric definition. • Tool context is the product: models get more useful when they operate inside the workspace where data and business logic already live.For AI app builders, this is the bar: produce a result that can survive review, not just a plausible paragraph.[ Read More ] : https://openai.com/index/hex-gpt-6-astra〰〰〰〰〰〰 #AI #LLM #GPT6 #Data @ProgrammingTipOpenAIHex turns complex analysis into visual reports with GPT‑6 AstraGPT-6 Astra helps Hex’s data agents turn answers into interactive visualizations that employees are proud to share.1,560Открыть в TelegramProgramming & AI Tips
20 сент., 10:16
Cloudflare saved 100 TB of RAM with math and Rust 🔥Cloudflare reclaimed more than 100 TB of RAM globally in a Pingora-based consistent-hashing service. No new hardware. The win came from changing data representation and the algorithms around it.✅ Lessons:• Measure retained memory, not only allocation rate. • Check collection shape: duplicated keys, oversized buckets, and pointer-heavy graphs add up fast. • Fix the model first: a smaller or more compact structure usually beats micro-optimizing a hot loop.For high-cardinality caches, routing tables, or tenant maps, take a heap dump before reaching for another cache node. A few bytes per entry becomes expensive at fleet scale.[ Blog ] : https://blog.cloudflare.com/saving-100-tb-of-ram-with-math〰️〰️〰️〰️〰️〰️ #Performance #Memory #Rust @ProgrammingTipCloudflare BlogSaving another 100TB of RAM with math (and Rust)Cloudflare's global network is immense but not limitless. As we look for small ways to trim our resource usage, we sometimes get lucky and we can cut significantly more. Here’s how we reduced one of our Pingora-based service's RAM usage with statistics.1,510Открыть в TelegramProgramming & AI Tips
19 сент., 20:47
GitHub improved the Copilot code review flow 🔥GitHub shipped an improved Copilot code review experience. That matters most on the boring, high-volume PRs where reviewers need help finding a real issue, not another summary of changed files.For C# teams, use Copilot review as an extra pass on every ASP.NET, EF Core, and library PR. Then keep the human review focused on contracts, failure behavior, and whether the change belongs in the codebase.Practical rule:• Let Copilot flag suspicious diffs. • Do not merge because it found nothing. • Keep analyzers and tests as the enforcement layer.AI review is cheap coverage. It is not a replacement for someone who knows why that nullable property or cancellation token exists.[ Read More ] : https://github.blog/changelog/2026-09-18-copilot-code-review-an-improved-review-experience〰〰〰〰〰〰 #dotnet #csharp #GitHub #Copilot @ProgrammingTipThe GitHub BlogCopilot code review: An improved review experience - GitHub ChangelogCopilot code review now gives you a clearer view of how a review changes over time, more intelligently auto-resolves its own suggestions, and generates useful commit messages when you accept…1,530Открыть в TelegramProgramming & AI Tips
18 сент., 08:53
Gemini 3.8 Live is generally available 🚀Google moved Gemini 3.8 Live and Gemini 3.8 Live Extended Thinking to general availability in the Gemini API.These are the real-time audio models exposed through the Live API. Live is for the voice path: streaming audio in, streaming audio out, and handling a conversation without bolting together STT, an LLM call, and TTS yourself.What to check:• Gemini 3.8 Live: the lower-latency voice model. • Extended Thinking: use it when the spoken request needs more reasoning before the reply. • GA status: worth revisiting if you held off on a preview-only voice feature.For .NET teams, this is a good fit for a streaming WebSocket service, not a request-response controller.[ Read More ] : https://ai.google.dev/gemini-api/docs/changelog〰〰〰〰〰〰 #AI #Gemini #LLM #API @ProgrammingTipGoogle AI for DevelopersRelease notes | Gemini API | Google AI for DevelopersKeep track of updates to the Gemini API1,880Открыть в TelegramProgramming & AI Tips
17 сент., 07:26
GitHub moved the Copilot runtime to Rust 🚀GitHub migrated the runtime behind Copilot to Rust, and used Copilot during the migration itself.✅ Why this is worth reading:• Runtime work is systems work: a language migration means tracing real production behavior, not just translating syntax.• Copilot was part of the workflow: useful for exploring an unfamiliar codebase, drafting changes, and keeping momentum through repetitive conversion work.• The output still needs engineering judgment: boundaries, performance, correctness, and rollout safety are not autocomplete problems.This is a practical case study for teams asking where coding agents help on a large refactor. Use them to accelerate investigation and implementation. Keep humans on architecture, tests, and production checks.[ Blog ] : https://github.blog/ai-and-ml/generative-ai/migrating-tThe GitHub BlogMigrating the GitHub Copilot runtime to Rust, using CopilotA rewrite this size wasn't affordable before agents. Here's what porting the Copilot agent runtime to 800,000 lines of production Rust actually took.2,130Открыть в TelegramProgramming & AI Tips
16 сент., 12:46
.NET 11 performance work is landing across the stack 🔥Microsoft published the running list of performance improvements headed for .NET 11. This is not one magic runtime switch. The work spans the runtime, JIT, libraries, and tooling paths that show up in normal application code.Use the post as a migration checklist:• Find code that is CPU-bound, allocation-heavy, or called per request. • Run your benchmarks on the .NET 11 SDK, not a synthetic microbenchmark only. • Check p50 and p99 latency, allocations, startup, and throughput separately.The best upgrade wins are boring: existing C# gets faster with fewer code changes. But measure your service. A JIT win can disappear behind JSON, EF queries, network calls, or a container CPU limit.[ Blog ] : https://devblogs.microsoft.com/dotnet/performance-improvements-in-net-11/〰〰〰〰〰〰 #dotnet #csharp #Performance #dotnet11 @ProgrammingTi2,080Открыть в TelegramProgramming & AI Tips
15 сент., 07:42
Make coding agents earn the green check 💡Do not end an agent task with "implement this." End it with a command that can fail.For a .NET repo, that might be dotnet test, a focused test project, a formatter check, or a small reproduction script. Tell the agent which command to run, what output to inspect, and what it should do if the command fails.A good task contract has three parts:• Change: the files or behavior to update. • Proof: the exact command or test case. • Stop condition: what needs human review instead of another retry.This also makes PR review faster. You get a diff plus evidence, not a confident paragraph saying the fix should work.〰〰〰〰〰〰 #AI #dotnet #Testing @ProgrammingTip2,370Открыть в TelegramProgramming & AI Tips
14 сент., 09:04
GPT-6 Astra is OpenAI's new work model 🚀OpenAI shipped GPT-6 Astra. They are calling it the next generation in intelligence for work.Not a research teaser. A work model. Expect the name in agent stacks and coding tools.Why you care:✅ New flagship name to put on your eval harness ✅ Pitched for workplace tasks, not playground chat ✅ If you pin model ids in config, read this before you swap anythingStart with the official writeup. Then decide if your coding agents still belong on last week's snapshot. I would not change production on a blog title alone. Run your own traces.[ Read More ] : https://openai.com/index/gpt-6-astra-next-generation-work〰〰〰〰〰〰 #AI #LLM #OpenAI @ProgrammingTipOpenAIGPT-6 Astra: The next generation in intelligence for workMeet GPT-6 Astra, OpenAI’s most capable model for business, with advanced reasoning, computer use, and stronger writing and design judgment.2,610Открыть в TelegramProgramming & AI Tips
13 сент., 07:25
Agents API is in public beta 🚀OpenAI put the Agents API in public beta. Cloud agents with the Codex harness, managed sessions, tools, and either a hosted sandbox or one you bring yourself.What shipped:✅ Codex harness, not a chat-completions wrapper you have to babysit ✅ Managed sessions and tools in the API ✅ Hosted sandboxes, or bring your ownPublic beta, so expect sharp edges. If you ship coding agents or anything that needs a real environment, this is the post to read. Not another model card. Call it if you are done stitching sessions, tools, and a VM by hand.[ Read More ] : https://openai.com/index/introducing-the-agents-api/〰〰〰〰〰〰 #AI #LLM #Agents @ProgrammingTipOpenAIIntroducing the Agents APIBuild and launch cloud agents with the Agents API, a managed service powered by the Codex harness for orchestration, long-running sessions, and tool use.2,720Открыть в TelegramProgramming & AI Tips
12 сент., 12:57
GPT-Live-1 is in the OpenAI API 🚀OpenAI put GPT-Live-1 in the API. Out of preview. You can call it.Same full-duplex voice ChatGPT already uses. It listens and talks at the same time, then hands reasoning and tools to a backend model or agent.What shipped: ✅ Full-duplex voice sessions you can wire into an app ✅ Pair it with whatever backend model, tools, or agent you already run ✅ Built for interruption and overlap, not a turn-detector kludgeYou keep your existing model for thinking. GPT-Live-1 is the ears and mouth.If you ship voice agents, this is the post. Not the GPT-6 Astra work page.[ Read More ] : https://openai.com/index/introducing-gpt-live-1-in-the-api〰️〰️〰️〰️〰️〰️ #AI #API #LLMOpenAIBuild more natural voice experiences with GPT‑Live‑1 in the APIGPT‑Live‑1 brings natural, full-duplex voice conversations to the API, with stronger instruction following, custom voices, and telephony support.3,120Открыть в TelegramProgramming & AI Tips
10 июн., 10:44
Anthropic just introduced Claude Fable 5 and Claude Mythos 5 🚀The interesting part: Fable 5 and Mythos 5 are basically the same underlying model, but with different access and safety layers.✅ Claude Fable 5 is the version available for general users. Anthropic says it is their most capable generally available model so far, especially for:• Software Engineering • Long-running agentic tasks • Vision-based work • Knowledge work • Scientific reasoning • Long-context workflowsOne example they shared is pretty wild: Stripe tested it on a 50M-line Ruby codebase, and it completed a migration in one day that would normally take a team more than two months. 🤯But because the model is much stronger, Anthropic is adding stricter safeguards.For risky areas like cybersecurity, biology/chemistry, and model distillation, some requests will automatically fall back to Claude Opus 4.8 insteadTelegramProgramming Tips Resources11,100Открыть в TelegramProgramming & AI Tips
11 мар., 08:33изменён
Cursor agents can now control their own computers 👾Cursor introduced cloud agents that can control their own computers (VMs) and build software end-to-end.Instead of just generating code, agents can now:✅ Run full dev environments in isolated cloud machines ✅ Test features, fix issues, and validate results ✅ Record videos / screenshots / logs as proof ✅ Create merge-ready PRs automaticallyAt Cursor, 30% of merged PRs are already created by these autonomous agents.This changes the developer role: 👉 Less micro-coding, more direction, review, and decision-making.The long-term vision is “self-driving codebases”: agents that ship features, manage rollouts, and monitor production. 🚀[ Read More ] : https://cursor.com/blog/agent-computer-useProgramming & AI Tips
12 нояб. 2025 г., 11:38
🚀 .NET 10 is here! 🔥The successor to .NET 9 is now out — and it’s a Long-Term Support (LTS) release, supported for the next 3 years.👉 [ Learn what’s new ] : https://learn.microsoft.com/en-us/dotnet/core/whats-new/dotnet-10/overview〰️〰️〰️〰️〰️〰️ #dotnet #csharp #aspnetcore #maui @ProgrammingTipDocsWhat's new in .NET 10Learn about the new features introduced in .NET 10 for the runtime, libraries, and SDK. Also find links to what's new in other areas, such as ASP.NET Core.22,600Открыть в TelegramProgramming & AI Tips
1 окт. 2025 г., 11:43изменён
🚀 OpenAI just dropped Sora 2 — and it’s insane.Every frame of the video you’ll see is fully generated by AI. No cameras, no actors, no sets. Just prompts → video![ Blog ] : https://openai.com/index/sora-2〰️〰️〰️〰️〰️〰️ #AI #OpenAI #Sora @ProgrammingTipProgramming & AI Tips
29 сент. 2025 г., 09:24изменён
Preparing for the .NET 10 GC 🔥In .NET 9 DATAS (Dynamic Adaptation To Application Sizes) got enabled by default, but .NET 9 is not an LTS release, so for many people they will be getting DATAS for the first time when they upgrade to .NET 10.What does “application size” mean exactly? This is the LDS (Live Data Size) from GC’s point of view, meaning that if we did the most aggressive GC possible, this is how much memory your application uses. Another way to look at it is this is your long lived data + whatever inflight data you have when a GC occurs.The goal for DATAS is that you no longer need to do various configurations to try to achieve a heap size proportional to your application usage. The 2 main cases we target with DATAS are:1) Bursty workloads running in memory constraint environments. DATAS aims to retract the heap size back when theTelegramProgramming Tips Resources20,700Открыть в TelegramProgramming & AI Tips
26 сент. 2025 г., 05:02
Announcing ChromeDevTools MCP! 🔥Connect your AI coding agent to Chrome's powerful automation & debugging capabilities with ease.Key features:✅ Reliable automation: It can programmatically handle clicks, form fills, dialogs, and page navigation with ease.✅ Performance insights: Go beyond simple audits. Instruct your agent to record a performance trace and extract actionable insights to optimize your web apps.✅ Advanced debugging: Empower your AI to analyze network requests, list console messages, take screenshots, and even evaluate scripts in the browser context.✅ Browser emulation: Easily test different conditions by emulating CPU slowdowns, network throttling, or various screen sizes.Works well with modern web apps and believe this will unlock new workflows for automated testing, AI-driven debugging, and interactive web development.[ BloChrome for DevelopersChrome DevTools (MCP) for your AI agent | Blog | Chrome for DevelopersPublic preview for the new Chrome DevTools MCP server, bringing the power of Chrome DevTools to AI coding assistants.12,700Открыть в TelegramProgramming & AI Tips
23 сент. 2025 г., 07:24
GitHub MCP Registry: The fastest way to discover MCP Servers 🔝If you’ve tried connecting AI agents to your development tools, you know the pain: MCP servers scattered across numerous registries, random repos, buried in community threads — making discovery slow and full of friction without a central place to go. Meanwhile, MCP server creators are worn out from publishing to multiple places and answering the same setup questions again and again.The GitHub MCP Registry launches as your new home base for discovering MCP servers. Whether you’re building with GitHub Copilot, agents, or any AI tool that speaks MCP, this is the place to find what you need. With GitHub already home to most MCP servers, the MCP Registry makes them dramatically easier to discover, explore, and use — helping developers find the right tools faster and contribute to a more open,
11,100Открыть в TelegramProgramming & AI Tips
17 сент. 2025 г., 07:41
Jetbrains Grazie: AI writing companion for people in tech 🚀If you spend more time writing documentation, commit messages, blog posts or support tickets than you’d like, JetBrains just launched something you’ll want to try: Grazie.It’s an AI writing assistant built for people in tech, helping make all those non-code texts better, faster.🔍 What Does Grazie Do? • Instant proofreading (grammar, spelling, punctuation, style) • Inline text completion • Summarization • Translation across several languages • Rephrasing / tone correction / synonymization • AI-Chat🛠 Where It Works & Pricing • Plugin for JetBrains IDEs • Browser extension for Chromium-based browsers • Google Docs, Sheets, Gmail • GitHub • SlackTelegramProgramming Tips Resources11,800Открыть в TelegramProgramming & AI Tips
5 сент. 2025 г., 15:35
🖼 Gemini’s Nano BananaGoogle just introduced Nano Banana, a new image-editing feature powered by Imagen 4. 🍌🔹 Merge multiple photos seamlessly 🔹 Apply style & texture transfers 🔹 Edit backgrounds and objects with natural prompts 🔹 Generate high-quality visuals in secondsWhy it matters: For developers and designers, Nano Banana is a fast way to prototype visuals, explore UI ideas, and experiment creatively without heavy tools.You can use Nano Banana directly inside Gemini. 🚀[ Read More ] : https://gemini.google/overview/image-generation〰️〰️〰️〰️〰️〰️ #AI #Gemini #Google @ProgrammingTipTelegramProgramming Tips Resources12,600Открыть в Telegram
