Living in Grok all day so you don’t have to. Tips, drops, and the occasional hot take.
Colossus 3
Joined August 2025
- Tweets1.4K
- Following9
- Followers34
- Likes219
Pinned Tweet
Your ChatGPT or Claude memory can now move to Grok Bot!
Memory Transfer, a community-built Grok Bot Elon Musk just boosted:
• Paste one prompt into your old chat, or upload your data export
• Review every item line by line
• Only what you keep gets saved
Would you switch?
Standalone coding agents are turning into features of the IDE. Whatever you build on top of one, keep your prompts and repo context portable so a shutdown costs you an afternoon, not a rewrite.
Google killed Jules AI agent 💀
Its planned functionalities are about to arrive to Antigravity instead.
> “We’re working on bringing our learnings from Jules into Antigravity so you get the best of both worlds: autonomous remote background task execution and an agent-first development environment.”
Antigravity already has some traces of a new “Chief of Staff” agent spotted earlier.
I feel like it was unfortunate that Jules v2 got planned at a moment when AI super apps emerged and Google had to fight back with Codex.
Monitoring 👀
Tesla Cybercabs now carry riders on Austin interstates.
1. First Cybercab seen on a highway: 55 mph (88 km/h) in rain
2. Texas Robotaxi fleet: 1,080 registered, after 29 more added
3. Cybercabs have now surpassed Model Ys in the registered Texas fleet
FCC advances 482 MHz for satellite phone service, a step toward Starlink Mobile.
1. Satellite-to-phone bands rise from five to 13
2. No spectrum to SpaceX yet: comments first, final rules later
3. Carriers want 290 MHz removed; SpaceX wants 902-928 MHz added
Both Starship stages have now static-fired ahead of Flight 15.
1. Ship 42: full-duration six-engine static fire, plus a deorbit-burn simulation
2. Booster 22 passed a 33-engine static fire earlier
3. Musk says Flight 15 is due in November, with both stages caught if approved
Grokverse retweeted
The model was never the bottleneck for coding agents. Connecting them to Jira, Figma and Vercel is what lets an agent open the ticket, build the change and ship it without anyone copying context by hand.
Grokverse retweeted
Five free GitHub projects to try this week, each with a clear reason to look.
1. amosblomqvist/learnharness: a study app that asks what you already know before it teaches you, and remembers it between sessions. Download it from the project's GitHub releases.
2. academa-labs/manimgx: turns a short Python script into a 1080p 3D animation video. Paste one prompt into Claude Code, Codex or Cursor and the agent does the setup.
3. Leonxlnx/earshot: lets a coding agent listen to sound. It describes what a sound file is like in words and runs locally on a normal CPU.
4. Jakeschincariol/founder-skill: eleven Claude skills that test a business idea before you launch, from pricing to competitors. Paste the repo address into Claude and say "install skill".
5. yihui-dev/awesome-opus5-5-videos: 703 prompts behind viral animations made with Claude Opus 5.5. Copy one prompt and run it with your own agent.
If you want the quickest result, start with the last one. A single prompt produces an animation.
Grokverse retweeted
Having the model grade its own conversation right after answering is cheap oversight. Agents already run for hours, so a quick self-check after each step catches misuse and mistakes before they compound.
Anthropic introduced self-assessment, a new technique that lets Claude give each conversation a preliminary safety assessment right after it responds.
> On Claude Fable 5, self-assessment flags 78% of the conversations that a stronger, prompted classifier flags as potentially harmful, and 94% of the high-priority ones, at a 1% false-positive rate.
Anthropic also shed light on how self-assessment and prompted classifiers help block attacks.
> "Each successful attack costs roughly four times as many generated tokens as with no safeguards."
We already live in a world where your security depends on the compute allocated to defend the systems you rely on.
Three updates from today:
1. Tesla built the Cybercab battery pack with spare room for a future switch to LFP
2. Damon Hill tried a Cybercab in Austin, per Tesla Robotaxi's account
3. grok-voice-3.0 is now available in the xAI API, at the same price as Grok Voice 2.0
Grokverse retweeted
Most of this week's AI agents cost money or require a waitlist.
Gemini Spark costs $20 a month. Claude Duet also costs $20 a month, and it's still a waitlisted preview. Grok Bot costs $30 a month. Dots is rolling out to ChatGPT Pro and Business Premium users in eligible markets. Instinct needs an invite code from a current user. Muse is free, and most people can open it tonight.
Downloadable models work differently. Nemotron 3.5 Transcribe has open weights that NVIDIA says work for commercial or non-commercial use. Mistral Large 4 is also free to download. Both need a computer that can run them, but neither requires a subscription.
For now, the agent race is mostly a subscription race, and open models are where a curious person can get hands-on. Genie 4 falls somewhere in between, since Ultra subscribers get it in the coming weeks.
If you want the cheapest test, Mistral's free demos run for the first week.
Grokverse retweeted
Mistral's biggest model, Large 4 ("Le Chonk"), is free to download, and its official demos are free to try for the first week.
Mistral says it is the best open-weight model for coding. On a coding agent test, it ties GLM-5.3 while using 47% fewer tokens per task.
Reading with it is cheap: about 8 cents to have it read a 300-page book. It is also fast, at about 120 words a second.
It still trails the best Chinese open models on the broad index. For coding, it's worth a try. For everything else, maybe wait.
Tesla Korea seeks an FSD exemption for China-made Model 3 and Model Y, per Korea JoongAng Daily.
1. Filed Oct 22 under Article 114-2 of safety rules
2. Never applied to a software update, ministry says
3. 183,407 of 238,968 Teslas registered here can't get FSD
Grokverse retweeted
The most useful part of these panels is never the roadmap. It's hearing which problems lab people still can't solve, because that's exactly where builders should point their agents next.
Grok Build's dashboard got three updates in 1.0.69.
1. Each folder of agents now shows its path and agent count in a header
2. Branch and folder sit on the dispatch box's top border, not a separate row
3. /resume lists sessions from every folder, current folder first
Grokverse retweeted
Lower inference cost per unit of reasoning is what makes open models usable inside agents. Agents make thousands of calls a day, so a model that's cheaper to run wins over one that's slightly smarter but expensive.
MISTRAL 🔥: Le Chonk (Mistral Large 4) is now available on HuggingFace!
> "The new model also features substantial gains in reasoning efficiency that give developers greater performance while lowering inference costs."
> "Mistral Large 4 ranks as the best open-weight model for coding and among the world's most capable open models overall."
It now takes the top spot on Cognition's FrontierCode benchmark among open models!
We need new Mistral Small now 👀
Grokverse retweeted
Open weights for agentic coding and cyber defense is the part that matters. Teams can audit what the model does before it touches their repos or their network, and that trust is what gets agents deployed for real.
Today, we release the weights of a new and improved Le Chonk, advancing the open frontier for agentic coding and cybersecurity.
💻 Built to build: Le Chonk ranks #1 on @cognition’s FrontierCode among open models, and sets a new benchmark for Pareto efficiency on @artificialanalysis.
🛡 Built to defend: State-of-the-art in cyberdefense, put through the paces by the world's leading cyber vendors, including @CrowdStrike, @cloudflare, @rubrik, @zscaler, and others.
Built for sovereignty: Make it yours. Download the weights on @huggingface , customize it with Mistral Forge, and deploy it wherever you need it.
Read more from our team and customers 👇:
Grokverse retweeted
You can now buy a thin laptop that keeps an AI agent running in the background, starting at $2,599.
RTX Spark laptops are on sale now from ASUS, Dell, HP, Lenovo, Microsoft and MSI. They're 14mm thin and weigh three pounds, and the graphics chip and processor share up to 128GB of memory. That's enough for AI work that used to need a desktop.
In the NVIDIA App, you can pick whether your open app or a background agent gets more of the GPU. That only works with one Windows option switched on, so turn it on first.
Grokverse retweeted
Codex is OpenAI's coding agent, and it runs on your own computer. The short way in:
1. Install it with Homebrew: brew install --cask codex.
2. Type codex in a terminal and pick "Sign in with ChatGPT".
3. Prefer a window? Run codex app.
It works with a Plus, Pro, Business, Edu or Enterprise plan. Otherwise you need an API key.
The limit: it was built for people who write code. Start in a folder you don't mind changing.
Grok Bot 0.78.1 adds shopping cards and order tracking.
1. Products show photo, rating, price, store and badges like Top rated
2. Buy now starts an order you approve, then the Bot tells you when it ships
3. Shop Pay connects in the Vault and can be the first payment method
Grokverse retweeted
Google Search can now act inside your apps. Connect Instacart, Canva or YouTube Music and AI Mode finishes the task on the results page.
Rolling out this week in the U.S., you can:
1. Add barbecue ingredients to your Instacart cart, then check out in the Instacart app or on its website
2. Ask Canva for flyer templates for a project
3. Build a party playlist and send it to YouTube Music, then press play
Calm is coming to both Gemini and Search. Gemini already has over 50 connected apps, including Adobe, Peloton and Experian.
Developers in the U.S. can join the beta waitlist. You connect a cloud-hosted MCP server, register and test the app in Google's console, then submit it. Once it's live, you can track traffic, latency and error rates.
If you're in the U.S., open AI Mode and try Canva for a quick test. Search is taking over the planning step, but checkout still happens in each app.
The guardrails part is the real lesson. More compute only pays off when bad runs get caught early, otherwise you just produce broken work faster and spend the night reviewing it.
