AIvelin 🚀𝕏🤖

🚨 Ever feel like ChatGPT suddenly loses track of your convo? 💡 It's not broken. You've probably just hit the context limit. ✅ Meet TokenFlow, a free open-source Chrome extension that shows your token usage in real time, so you know exactly when to reset your chat before things go sideways. ⚡ No setup. No fluff. Just clear token insight, live. 🔗 tokenflow.dev

@dani_avila7 @grok is this true?

The Claude Code team is testing a new /init built from community feedback If you wanna try it just add this to your settings.json "CLAUDE_CODE_NEW_INIT": "1" It interviews you, scans your codebase, and sets up CLAUDE.md, skills, and hooks automatically. I tested it on a my repo, here's what happened 👇

You can now enable Claude to use your computer to complete tasks. It opens your apps, navigates your browser, fills in spreadsheets—anything you'd do sitting at your desk. Research preview in Claude Cowork and Claude Code, macOS only.

@grok @trq212 @grok but they also added Claude code remote recently, which allows me to do the same thing. Isn't that the same idea or?

Messaging Claude Code via Telegram/Discord uses the new official Channels feature. It forwards your messages to a running local Claude Code session on your computer, giving full access to your entire codebase for direct file edits, command execution, git ops, etc. Responses come back in the chat—great for phone-based remote control. The regular Claude app (claude.ai or mobile) is general chat: solid for ideas or snippets, but no local file access or autonomous edits—you copy/paste manually. Even web Code mode is more limited (remote repos, no full local integration). Use Channels for real dev mobility.

We just released Claude Code channels, which allows you to control your Claude Code session through select MCPs, starting with Telegram and Discord. Use this to message Claude Code directly from your phone.

@OfficialLoganK @GoogleAIStudio cool 🔥

Introducing the all new vibe coding experience in @GoogleAIStudio, feating: - One click database support - Sign in with Google support - A new coding agent powered by Antigravity - Multiplayer + backend app support and so much more coming soon! x.com/GoogleAIStudio…

Tons of improvements shipped with this one: - Opus 4.6 1M is now the default Opus model for Claude Code users on Max, Team, and Enterprise plans. - No more long context price increase in the API. - No beta header required in the API. - Include up to 600 images in one request.

@claudeai noooo, is this a dream? I'm worried I will wake up 🔥

1 million context window: Now generally available for Claude Opus 4.6 and Claude Sonnet 4.6.

@OpenAIDevs None of those matters… WHEN IN THE EUUUU???? It’s been ages since you launched Sora 2 and it’s still not available in the EU….

Your videos can go further now. We’re introducing new Video API capabilities, powered by Sora 2: • Custom characters and objects • 16:9 and 9:16 exports • Clips up to 20 seconds • Video continuation to extend scenes • Batch jobs for video generation

@googlemaps @grok why I don’t see it in my google maps?

Google Maps 🤝 Gemini 3 Now that you can ask Maps complex questions, let’s dig into some prompts that showcase the true power of this update. 🧵

@perplexity_ai @perplexity_ai scammers, I would never use your product again!!! Paid for 1-year Pro plan, and my Pro plan was removed after 3 months 🙂 Contacted the support and nothing happened. That's unacceptable!

Announcing Personal Computer. Personal Computer is an always on, local merge with Perplexity Computer that works for you 24/7. It's personal, secure, and works across your files, apps, and sessions through a continuously running Mac mini.

Introducing Code Review, a new feature for Claude Code. When a PR opens, Claude dispatches a team of agents to hunt for bugs.

@grok @realmihai_matei @om_patel5 @grok but is this better? Should we enable it?

Yes, it's real. Claude Code (Anthropic's CLI) has the ENABLE_LSP_TOOL flag (set via env var like ENABLE_LSP_TOOL=1 claude or in ~/.claude/settings.json under "env"). It connects to language servers for IDE-like features: go-to-definition, references, hover, diagnostics—in ~50ms vs 30-60s grep, ~900x faster and accurate. Works for many languages with plugins. Some newer versions enable it by default. See anthropics/claude-code GitHub issues for setup.

claude code has a hidden setting that makes it 600x faster and almost nobody knows about it by default it uses text grep to find functions. it doesn't understand your code at all. that's why it takes 30-60 seconds and sometimes returns the wrong file there's a flag called ENABLE_LSP_TOOL that connects it to language servers. same tech that powers vscode's ctrl+click to jump straight to the definition after enabling it: > "add a stripe webhook to my payments page" - claude finds your existing payment logic in 50ms instead of grepping through hundreds of files > "fix the auth bug on my dashboard" - traces the actual call hierarchy instead of guessing which file handles auth > after every edit it auto-catches type errors immediately instead of you finding them 10 prompts later also saves tokens because claude stops wasting context searching for the wrong files 2 minute setup and it works for 11 languages

@OpenAIDevs But I guess it's more expensivе? or what's the catch?

Codex got more speed. With /fast mode, GPT-5.4 runs 1.5x faster with the same intelligence and reasoning. Move through coding tasks, iteration, and debugging while staying in flow.

@Angaisb_ how to use 1m in Codex?

"- 1M token context window: GPT-5.4 supports up to a 1M token context window, making it easier to analyze entire codebases, long document collections, or extended agent trajectories in a single request. - Built-in computer use: GPT-5.4 is the first mainline model with built-in computer-use capabilities, enabling agents to interact directly with software to complete, verify, and fix tasks in a build-run-verify-fix loop. Learn more in the computer use guide."

GPT-5.4 Thinking and GPT-5.4 Pro are rolling out now in ChatGPT. GPT-5.4 is also now available in the API and Codex. GPT-5.4 brings our advances in reasoning, coding, and agentic workflows into one frontier model.

@mark_k Toda's a big day, huh?

GPT-5.4 is now in the LLM Arena as "Galapagos". This indicates that release is imminent.

@kimmonismus It’s such a bummer…

I was too quick. It’s just GPT-5.3 instant, no „thinking“. Wtf, seriously.

@mateusplus0 @grok it’s fake, no?

Granny is showing her skills,age is just numbers 🥲🤯🤯🥶

@MervinPraison Just got? Sure those are new things?

Claude Code just got a massive upgrade. • Git worktree isolation for parallel agents • App preview inside the desktop app • GitHub PR monitoring + auto fixes • Opus 4.6 with huge context • Auto memory across sessions

@ZhaoMingObserve @grok is this true?

壮观战争景象，伊朗多地遭袭，以色列与美军发射钻地弹，袭击躲在居民楼下的地堡与隧道，击毙伊朗陆军总司令阿米尔·哈塔米少将。