#aicoding

image generation has become an important tool for coding agents you can use it to generate concept UI or reference art for video games OpenCode 2.2.3 has an image gen tool that supports image models from OpenAI, Gemini, Grok and more

🆕 GPT-6.1 Terra from @OpenAIDevs is now generally available in GitHub Copilot. Our early testing shows GPT-6.1 Terra solved noticeably more terminal and C# coding tasks than GPT-5.6 Terra. It works in focused, consolidated steps on well-scoped tasks. Try it out for everyday agentic coding and terminal work at a lower cost than GPT-6.1 Sol. Find it in the GitHub Copilot app, CLI, and @code.

Announcing Gemini 4 Carbon, our strongest model with state-of-the-art cybersecurity and long horizon capabilities. Carbon represents a step up across most benchmarks, delivering strong frontier performance in autonomous coding and cyber defense. We’re first making Carbon available to a subset of trusted cyber defenders in our Fairwind program. We’ll expand access as soon as possible.

JUST IN: SpaceX engineer declares the time for "mourning coding" is long over

Introducing Gemini 4 Carbon, it's a big jump over Argon which we released just 2 weeks ago. Gemini 4 Carbon is SOTA on cyber, long horizon tasks, ranks #1 on Artificial Analysis V5, significantly improves on usability in domains like coding, and is more aligned.

AI is already running across the enterprise, and securing it is now one of CISOs' biggest concerns Already in production at their companies: - Employee generative AI tools (92%) - AI coding assistants or agents (83%) - MCPs or agent-to-app integrations (55%) - Autonomous agents with tool access or write permissions (34%) Their biggest concerns: - AI attacks outpacing their team (55%) - Employees leaking data into AI tools (47%) - AI agents exceeding permissions or getting compromised (46%) From a16z's @OwenColby and @steph_zhang, breaking down a survey of 100 CISOs at companies with 1,000+ employees:

AI can write code fast, but fast is not the same as reliable. Here are 4 rules teams are using in late 2026: Write the spec before the agent writes code Review every AI change like unreviewed code Limit what coding agents can access Measure outcomes, not AI usage #AICoding

DeepSeek V4.1 Flash + GLM 5.3 Flash for FREE every day 😳 what u get: - free daily usage on both models - resets every day - one API key for Claude Code, Cursor, OpenCode - OpenAI compatible how to get it: > go to > sign up and grab your API key > plug it into your coding tool no subscription needed for the free tier

feels like there needs to be a new way to distribute opensource software such that people can modify via agents but also get upstream automatically merged in coding agents can do this but they won’t do it automatically

experimenting with a lil personal project: an AI-native macOS dock with custom modes (writing, building, etc.) to help me stay focused my agent is able to customize mode behavior and add new modes, it uses jev to classify my activity + notifications in real time & act on them

We launched the Gemini API CLI. A CLI for calling the Gemini API. Give it to the agent you already use (Claude Code, Codex, Antigravity, Cursor, OpenClaw, Hermes...). It's NOT a new coding agent you can use it too: 1. Generate images, video, speech, music. 2. Analyze PDFs, images, audio, video, YouTube URLs, 3. Transcribe recordings to md / json / srt, 4. Run Deep Research in the background. Stateless. No memory, no chat mode. Your agent owns the context and the plan, gemini-api does the API call. Build for Agents, it's self-describing. `--help`, `--dry-run`... Start here:

FREE JAILBREAK PROMPTS FOR 26+ AI MODELS someone dropped a whole collection of jailbreak prompts on GitHub, completely free. here are some of the major models covered: - Claude Opus and Sonnet - Gemini 4 Argon and Gemma 4 - DeepSeek V3, V4 and 4.1 - GLM 5.2 and 5.3 Flash - Kimi K2, K3 and K3.1 - Qwen 3.7 and 3.8 - Mistral Large 4 - GPT-OSS 20B - Nemotron 3 Ultra - Muse Spark 1.3 how to use: 1. open the repo and find your model's file 2. copy the full prompt 3. paste it into system instructions or custom instructions 4. for coding agents, add it to "AGENTS.md" 5. start a new chat and test it 32 prompts, free and open source. save it before it gets taken down

🚀 Discover what’s new in GitHub Copilot in @code! From running agents across devices to comparing model results and customizing your agent workflows, explore the latest updates from @github Universe 2026. Checkout what's new: Happy Coding!

Google’s Gemini 4 Carbon is the new #1 on the Artificial Analysis Intelligence Index v5, and second only to Claude Opus 5.5 on the Artificial Analysis Coding Agent Index Gemini 4 Carbon scores 59 on Intelligence Index v5, driven by leading performance in complex reasoning, knowledge, and scientific tasks. It also has large gains in coding and knowledge work, particularly when compared to other Gemini models, but it is not leading in all these areas. As with launch of Gemini 4 Argon, Gemini 4 Carbon is being rolled out to selected users and is not yet publicly available. Google is offering a 50% launch discount, with no confirmed end date. All our charts and figures use standard pricing for both Gemini 4 Carbon and Argon. Key results for Gemini 4 Carbon with high reasoning: ➤ Gemini 4 Carbon leads the Intelligence Index v5, with the #1 score in 4 of the 9 Index evaluations: HLE-Diamond, Terminal-Bench-Science, AA-Omniscience, AutomationBench-AA. Carbon makes substantial gains elsewhere but is not leading in coding and knowledge work ➤ Behind only Claude Opus 5.5 on coding agents: With Antigravity CLI, Gemini 4 Carbon (high) scores 59 only 3 points behind Claude Code with Claude Opus 5.5 (max, 62) on the Artificial Analysis Coding Agent Index. Carbon ranks second on both Terminal-Bench 4.0 (64%) and FrontierCode v1.1 (51%), behind Claude Opus 5.5 (max) at 56%. Google has historically underperformed in this area and so this improvement stands out ➤ Improved agentic knowledge work, but not yet leading: On AA-Briefcase, Gemini 4 Carbon (high) scores 1609 Elo, a 126-point improvement over Gemini 4 Argon (high, 1483), but still behind models including Grok 4.7 (xhigh, 1638), Muse Wonder (max, 1659) and Kimi K3.1 Pro (1678). The largest gain comes from Presentation, up 293 Elo to 1598, alongside a 120-point improvement in Analytical Quality to 1671 ➤ Lower Cost per Task than Claude Opus 5.5 for comparable overall intelligence: Gemini 4 Carbon costs $7.76 per Intelligence Index task, ~23% less than Claude Opus 5.5 (max, $10.04) but ~1.2x GPT-6 Astra (max, $6.25). It uses 123k output tokens per task, 29% fewer than Claude Opus 5.5 (max, 173k). At the same $4/$20 standard pricing, its Cost per Task is in line with Gemini 4 Argon ($7.68), while scoring 9 points higher on the Intelligence Index ➤ Leading AA-Omniscience v1.1 score, with low hallucination: Gemini 4 Carbon scores 54 on our recently updated AA-Omniscience v1.1, 6 points ahead of Claude Opus 5.5 (max, 48) and 8 points ahead of Gemini 4 Argon (46). Accuracy (% correct) rises 10 points over Argon to 58%, while its hallucination rate rises from 4% to 11%. This is still the second lowest of any model, behind only Argon, compared with 50% for both Claude Opus 5.5 (max) and GPT-6 Astra (max) Key model details: ➤ Context Window: 1M tokens ➤ Multimodality: Text, image, video, and speech input, with text output ➤ Pricing: $4/$20 per 1M input/output tokens, the same as Gemini 4 Argon’s standard pricing, with a 50% discount. Cached input tokens receive a 95% discount ($0.20 per 1M) Congratulations to the @GoogleDeepMind team!

Introducing agent-desktop agent-browser, for your whole computer → Computer Use for any coding agent → macOS, Windows and Linux → Runs in bg while you keep working → Agents use your computer in parallel, each with its own cursor

A LA MIERDA EL VIBE-CODING! FUE BONITO MIENTRAS DURÓ: 2025 - 2026🪦 GitHub ha sacado spec-kit La idea: dejas de pedirle cosas al agente a lo loco y escribes primero la especificación. Luego el agente la ejecuta. El flujo son 5 comandos: /speckit.constitution → los principios de tu proyecto /speckit.specify → qué quieres construir /speckit.plan → stack y arquitectura /speckit.tasks → lista de tareas real /speckit.implement → lo construye Funciona con 30+ agentes: - Copilot, - Claude - Codex - Cursor y muuuuchos más. Link al repo en los comentarios👇🏼

Coding ais are great at giving people what the want. Unfortunately, the people are retarded, and don't know what is worth wanting

Frontier performance at a fraction of the cost. In the @ArtificialAnlys Coding Agent Index, Copilot Fusion Max scored within two points of Claude Code with Opus 5.5 Max at about half the API cost per task. Get 30% off through Nov. 30. Try it now. ⬇️

He quit the Claude Code team and now can say the truth

There’s 100% a kind of mania you can get into with coding agents, where it feels like you’re getting a lot done and working all the time but nothing is really happening. I think it's often a form of avoidance of something else in life.

@rubinovitz eh to be clear, coding agents are still a huge huge productivity multiplier for most people in most cases it's just that if you're staying up all night, working all the time and constantly feel like you're hitting new revelations, you should check on yourself

FREE AI coding API for developers! → DeepSeek V4.1 Flash → GLM 5.3 Flash What’s included? • Free daily usage on both models • Daily usage reset • One API key for Claude Code, Cursor & OpenCode • OpenAI compatible API • No subscription required for the free tier How to get started: 1. Visit : 2. Sign up and generate your API key 3. Connect it to your preferred coding tool 4. Start building! Free AI coding access without a monthly subscription 👀

I just open-sourced all of the skills I use for building 3D projects. 8 skills. MIT licensed. completely FREE. they’re designed to help coding agents handle 3D workflows better, from scene structure and interactions to more polished visual output. and setup is simple: one command and you’re ready to go. 🔗: