Tech n' Tech ㊷ 🤓

1.3K posts

Tech n' Tech ㊷ 🤓

@TechNTech42

AI / Tech / Stocks

가입일 Aralık 2024

1.3K 팔로잉143 팔로워

Tech n' Tech ㊷ 🤓@TechNTech42·8h

@gabor CAREFUL: Many options and Google has a history of shutting down its tools: (1) Google AI Studio (2) Google Antigravity (nerfed limits in Mar'26 for AI Pro users) (3) Firebase Studio (sunsetting in Mar'27) (4) Gemini CLI (5) Gemini Code Assist (6) Gemini App for Mac (coming soon)

English

Gabor Cselle@gabor·2d

Pls try this today

Google@Google

Introducing a new upgraded vibe coding experience in @GoogleAIStudio. You can now turn any idea into functional, production ready apps. Build multiplayer games, collaborative tools, apps with secure log-ins and more.

English

2.5K

Tech n' Tech ㊷ 🤓@TechNTech42·8h

@elonmusk Bought $TSLA on Friday although the P/E is absurd levels

English

Elon Musk@elonmusk·1 May

Since I’ve been asked a lot: Buy stock in several companies that make products & services that *you* believe in. Only sell if you think their products & services are trending worse. Don’t panic when the market does. This will serve you well in the long-term.

English

37.9K

95.5K

987.3K

Tech n' Tech ㊷ 🤓@TechNTech42·8h

@danveloper Qwen3.5 35B A3B - Q8_035B-A3B GGUF (8-bit) on my MacBook Pro M4 Max 128GB 8TB gets about 50 tokens/s in LM Studio. It will likely do 60 tok/s on the latest M5 Max

English

Dan Woods@danveloper·3d

x.com/i/article/2034…

ZXX

168

1.2K

594.5K

Tech n' Tech ㊷ 🤓@TechNTech42·8h

@sujiteeeey Qwen3.5 35B A3B - Q8_035B-A3B GGUF (8-bit) on my MacBook Pro M4 Max 128GB 8TB gets about 50 tokens/s in LM Studio

English

431

Sujit Baruwal@sujiteeeey·12h

Was able to run Qwen 3.5 35b 4 bit on a MacBook air M4 with 16 GB of Ram. Streamlined the process with all the steps needed to run the model and got 5.9 tokens/s github.com/sbaruwal/flash…

Dan Woods@danveloper

x.com/i/article/2034…

English

225

27.2K

Tech n' Tech ㊷ 🤓@TechNTech42·10h

@PatrickMoorhead Try Claude Cowork with Claude Max 5x ($100/mo) plan

English

Patrick Moorhead@PatrickMoorhead·11h

Tokens go quick.

English

125

109.9K

Tech n' Tech ㊷ 🤓@TechNTech42·12h

@nikitabier @robertlasagna1 😂

QME

garfieldbot@robertlasagna1·1d

My zoomer girlfriend is forcing me to wear a red flannel shirt all day and eat avocado toast and grow an ironic ill fitting beard style, she calls me a "millennial piggy" and when I complain she says "oh that's so sad why don't you listen to some sad music on your turntable record player then". She throws bottles of craft beer at me and laughs

English

135

565

14.1K

540K

Tech n' Tech ㊷ 🤓@TechNTech42·12h

Now we have Copilot Tasks! So many options to choose from: (1) Claude Cowork (2) ChatGPT App (desktop) (3) Perplexity Computer (4) Copilot Tasks (5) OpenClaw / NemoClaw (6) Gemini App for Mac (coming soon)

Paul Couvert@itsPaulAi

Copilot Tasks is seriously good?! Even one of the best alternative to Claude Cowork Using a single prompt it was able to: → Use a cloud browser to find the right tool → Interact with the page to enter data → Interpret all the info given by the page → Generate a PowerPoint based on it → Draft an email containing the learnings Because it has access in real time to multiple Microsoft Office apps like Word, PowerPoint, Excel, etc. but also Outlook. Everything was seamless. First try. And you can even ask it to schedule this task (or another one) to run it every Friday, once a month, you name it. As with OpenClaw, the use cases are basically infinite.

English

150

Tech n' Tech ㊷ 🤓@TechNTech42·13h

@packers_owner_j @GregKamradt @MatthewBerman Now Claude Cowork has Dispatch (remote access), Telegram, and Discord channel support, along with scheduled tasks

English

Mr.Touchdowns@packers_owner_j·13h

@TechNTech42 @GregKamradt @MatthewBerman Yeah it's kind of "Claude code lite", supports skills, you can control a local session with your phone, etc... Really really easy starting point Not as flexible or powerful as openclaw but just 1000% smoother

English

Greg Kamradt@GregKamradt·17h

Thus far I’ve taken the Apple approach (inaction) with openclaw Haven’t dug into it while the dust settles @MatthewBerman do I go straight to openclaw? Or one of the many derivatives? Ex: nanoclaw

English

8.3K

Tech n' Tech ㊷ 🤓@TechNTech42·13h

@petergyang Yep, I no longer have to ask Claude Code to create a handoff prompts for the next session

English

306

Peter Yang@petergyang·13h

1M context window feels like an upgrade from Opus 4.6 to 4.7

English

850

57.5K

Tech n' Tech ㊷ 🤓@TechNTech42·13h

@BassonBrain @Starlink No way. Today's Starlink can't compete with my symmetrical Gigabit Fiber at 6-8ms latency for $64.99/mo

English

Brian Basson@BassonBrain·14h

Switch to @Starlink, it's worth it! 🛰🏡 The setup is straightforward, the speeds are fast, and the pricing is competitive enough that the math works out for most households. "I finally switched to Starlink — it fixed my rural internet and costs less than I expected. My first speed test came back at 264 Mbps down, immediately faster than my old cable connection at just over 150 Mbps. If you're locked into a dead-end cable contract that keeps getting more expensive while it delivers less, Starlink is worth a serious look, especially if you live outside a major metro area where fiber isn't an option. ...after years of dreading my monthly cable bill, switching to Starlink felt less like a tech experience and more like a decision I should have made sooner."

English

580

Tech n' Tech ㊷ 🤓@TechNTech42·14h

@PeterDiamandis Human brain also has a better memory management system and a better context management system! Besides thoughts, it also runs the autonomic nervous system (ANS) 24x7, managing heart rate, digestion, respiration, temperature, and overall homeostasis.

English

Peter H. Diamandis, MD@PeterDiamandis·16h

Did you know the human brain generates about 6,200 thoughts per day? That's roughly 6 thoughts per waking minute. Your brain is literally running thousands of parallel processes continuously... and it only needs 20 watts of power. A single ChatGPT query uses the same energy your brain uses in 54 seconds. Your brain: 20 watts, 86 billion neurons. An NVIDIA H100 GPU: 700 watts, billions of transistors. Nature built better hardware

English

137

581

24.1K

Tech n' Tech ㊷ 🤓@TechNTech42·15h

@thsottiaux No, I prefer Codex approach

English

Tibo@thsottiaux·16h

Do people like this? We don't do this for codex because it exists to help you and it's important that you remain the owner and accountable for your work without AI taking credit. At the same time it does mean that you can't trace how popular codex is among repos.

Yuchen Jin@Yuchenj_UW

I noticed something interesting: Claude Code auto-adds itself as a co-author on every git commit. Codex doesn’t. That’s why you see Claude everywhere on GitHub, but not Codex. I wonder why OpenAI is not doing that. Feels like an obvious branding strategy OpenAI is skipping.

English

546

2.3K

266.7K

Tech n' Tech ㊷ 🤓@TechNTech42·1d

@reach_vb Codex Security for Plus subscribers

English

Vaibhav (VB) Srivastav@reach_vb·1d

Codex for Open Source Codex for Students Codex Ambassadors Codex Security What should we do next?

English

252

417

32.7K

Tech n' Tech ㊷ 🤓@TechNTech42·1d

@MarioNawfal Keep draining your battery like that and you will degrade it!

English

Mario Nawfal@MarioNawfal·1d

🇺🇸🇦🇺 An Australian radio show pushed a Tesla past 0% battery to see how far it would go. Turns out “empty” isn’t exactly immediate. 0%… with a little fine print.

Elon Musk@elonmusk

Try Tesla FSD (self-driving)!

English

519

175K

Tech n' Tech ㊷ 🤓@TechNTech42·1d

@thsottiaux @theo 😂

QME

Tibo@thsottiaux·2d

@theo Faster electricity

English

325

6.9K

Theo - t3.gg@theo·2d

Can someone smarter than me explain how these “turbo mode” things work on like an implementation level? Are they using better GPUs? More GPUs? Reserved allocation during generation?

English

103

922

158.3K

Tech n' Tech ㊷ 🤓@TechNTech42·1d

@gavkar Nice! Bought 16-in M4 Max MacBook Pro 128GB 8TB when it launched. Now I have to be patient for the 2nm M6 Max or M6 Ultra because the trade-in value for my current MacBook is too low)

English

393

Gokhan Avkarogullari@gavkar·1d

We brought significant architectural advancements and feature set improvements to A19/M5 GPUs. Scalable GPU Neural Accelerators 2nd Gen Dynamic Caching Shader Architecture 3rd Gen Ray Tracing The best GPU Driven Pipeline New graphics features, rate and perf increases.

English

585

35.2K

Tech n' Tech ㊷ 🤓@TechNTech42·1d

@AlexSuperTrampQ @aaronrubin

GIF

QME

1.2K

FCK_Engineering@AlexSuperTrampQ·1d

@aaronrubin @TechNTech42 Llama 0.5 here . I agree with Aaron . Claude has not yet reached that level. But if you want complete automation you can use our latest llama 4.735 which the is best.

English

1.2K