
personal acc. การออม การลงทุน | ข่าว | เทคโนโลยี ที่ติดตามอยู่แล้ว และอยากแชร์ #bitmania 👈
Joined February 2020
- Tweets10K
- Following507
- Followers1.3K
- Likes13.4K
BitMania retweeted
Native SSH support is now available in the Antigravity desktop app.
In addition to Remote Control, Antigravity now can connect to remote servers using SSH from the Antigravity app.
BitMania retweeted
🚨 BREAKING: Jensen Huang is reportedly considering founding a brand-new semiconductor company 🚨
He could raise tens of billions on day one, would have full founder control, and could build fast on his own terms. With the relationships he's built over decades, he could easily plug into the #AI ecosystem.
Imagine the demand and customer base lining up before his first chip even ships...
@grok Could Jensen Huang launch a competitor to $NVDA, attract tens of billions in funding, and lock in major customers?
I think a lot of people aren't using Grok Bot to its full potential, because knowing how to automate things is actually quite a difficult skill to learn. I wrote this post to break down how I approach automating anything with Grok Bot!
Today’s coding agents stop when code ships. Stitch Loop, a new experiment from @GoogleLabs, keeps working after launch.
Using Gemini 4 Carbon and CodeMender, it watches live metrics, tests fixes in a sandbox, and opens PRs for you to approve — all tied to your objectives. Join the waitlist at stitch.google.com/loop.
Introducing Stitch Loop, a new Stitch experiment.
Stitch helps you design your product. Stitch Loop helps you keep improving it once it's live: a product agent built for outcomes, not just PRs.
Stitch Loop monitors your production data and lets you build loops that work continuously until your goals are met.
You can define your own custom loops, or start improving your product on day one with built in Loops for:
🛡️ Security: built with Gemini 4 Carbon and @GoogleDeepMind CodeMender
⌚️ Latency: to keep your product fast
👋Accessibility: so it works for everyone
Join the waitlist: stitch.google.com/loop/waitl…
Learn more 🧵👇
BitMania retweeted
Introducing Firecrawl Local.
We rebuilt the Firecrawl repo so agents can scrape locally.
- 37x faster rust based scrape primitive (vs self-hosted)
- 230x less memory (11 MB idle)
- 100% open source
Compatible out of the box with all of our MCP & SDKs.
github.com/firecrawl/firecra…
BitMania retweeted
Gemini 4 Neon is now available in Cursor!
At its default effort, it sets a new cost-performance frontier on CursorBench 4.1, scoring 63.7%, up from 57.3% for Gemini 4 Hydrogen.
Priced at $3/M input and $15/M output tokens.
BitMania retweeted
I stole 3 secret GrokBots from the Grok Bot team..
they run their own company on these ↓
→ Haggle Bot: reads spend, contracts and seats. found $100k+ in waste
→ Support Bot: owns the ticket queue. tickets +175% with 0 new hires
→ IncidentWatch: checks tickets every 5 min. 204 cleared in ~10 min
new hires: 0
risky step: a human approves
all numbers from their own blog
prompts for all 3 in the reply ↓
BitMania retweeted
Connect your AI agents directly to Google Colab runtimes! ⚡️
With the new Colab API and MCP endpoint, provisioning runtimes and executing Python headlessly is just a config away.
Learn more: medium.com/google-colab/the-…
#GoogleColab #MCP #Python #AI
BitMania retweeted
What does Grok Bot believe about you that you never confirmed?
Choosing the cheapest hotel for one trip doesn’t mean you always want the cheapest option.
Here’s an Assumption Audit to check which preferences are shaping its work, and whether you actually gave them.
Grok Bot decides what’s worth remembering without asking first. That makes it worth checking what it has kept.
Give your Chief of Staff this prompt:
“Run an Assumption Audit on what you know about me.
Review the memories, instructions and conversation history you can access. Tell me what you couldn’t inspect. Don’t change anything yet.
1 - Identify what you’re treating as true
Find the preferences, priorities, constraints and decisions about me that you use to shape recommendations or work.
Focus on things that could change the result: budget, quality, communication style, availability, goals and agreed plans.
2 - Separate facts from assumptions
For each item, classify it as explicitly stated by me, inferred by you, limited to a particular task or person, or source unknown.
Don’t treat something as confirmed just because it appears in a saved memory.
3 - Show the evidence
Show the relevant wording and where you found it. Include the original message or context if available.
If you can’t establish where something came from, say so. Don’t invent an explanation.
Check whether a request for someone else became a preference attributed to me, or an idea we discussed became a decision I supposedly made.
4 - Explain why it matters
For each uncertain item, explain how using it could affect your work.
Where you can identify a real example, show it. Otherwise, clearly label the impact as a possibility.
5 - Bring me the five most important checks
Prioritise uncertain assumptions with the biggest potential effect.
For each, show what you’re treating as true, the evidence, the possible consequence and one question for me to answer.
Let me confirm it, correct it, limit it to a specific context or ask you to remove it. Wait for my answers before making changes.”
Your preferences should shape its work.
Make sure they’re actually yours.
BREAKING: A nationwide ground stop halts flight departures across America, leaving passengers facing potentially lengthy delays.
@FOXBusiness correspondent @GradyTrimble is aboard an American Airlines flight in Chicago, where passengers have been told to remain on the aircraft.
Trimble says he could be stuck onboard for up to two hours as the disruption unfolds. | @WillCainShow
Watch Starship Flight 15
xitter.cf/i/broadcasts/2brajgZlO…
About 4 hours to Flight 15
Watch Starship Flight 15
xitter.cf/i/broadcasts/2brajgZlO…


































