MarkL

[ashe @ashebytes]

I used gpt-6 astra to try to understand what the navier stokes problem is.. aesthetically

metaphor: imagine you are stirring your tea. could a whirlpool exist that speeds up rather than smooths out over time? ☕️

it put together this visual essay: https://t.co/O3jGGAS8aa

[MarkL @sun_shine9999]

@GamesHafi15131 @clashreport Haha and what go back to Stone Age?

[Jared Friedman @snowmaker]

Graphify Labs is the first YC company to hit 100K github stars during the batch.

[ClaudeDevs @ClaudeDevs]

A few patterns we frequently use with Fable 5:

Use Fable 5 as an "advisor."

An executor (Sonnet 5) calls Fable 5 for guidance.

Most tokens are billed at the lower executor rate.

[Richard Vermillion, JM, MBA🌟 @VermillionRich]

@CuriosityonX Here’s the direct download link to the Gutenberg PDF of the 3rd edition:

https://t.co/g8lbnXwe60

[MarkL @sun_shine9999]

I always had this uneducated feeling that humans are inefficient: food, drinks, bathroom breaks, sleep.

Then you work with AI and see the data centres and power needed.

A human running on coffee suddenly looks like a miracle of efficiency.

[MarkL @sun_shine9999]

@TfL Ok got it - thanks.

[MarkL @sun_shine9999]

@TfL why is Oxford Circus station closed for entry?? This is crazy there is like a million people here!!

[MarkL @sun_shine9999]

@VibeCoderOfek @EpochAIResearch Slop

[Khairallah AL-Awady @eng_khairallah1]

🚨 Anthropic's own team just showed how to actually use Claude Code properly.

30 minutes. free. the person who created Claude Code.

watch the workshop. bookmark it.

worth more than every $500 course you almost bought.

you've been using Claude without knowing 40 of its commands.

Then read the guide below.

[MarkL @sun_shine9999]

@ClementDelangue I need to OCR a google sheets doc with one column being images - how can I do that? Post OCR the agent needs to fill out rows of the doc

[Nav Toor @heynavtoor]

🚨 Twilio charges $0.0079 per SMS. Someone just turned any old Android phone into a free SMS gateway. Unlimited messages. $0.

It's called SMS Gateway for Android.

Install it on any Android phone. It becomes a full SMS sending and receiving server with an API.

No Twilio. No MessageBird. No per-message pricing. No contracts. Just an old phone and a SIM card.

Here's what's inside this thing:

→ Send and receive SMS through a REST API from any app or service
→ Works with any Android phone running 5.0 or newer
→ End-to-end encryption. Messages are encrypted before they leave the device.
→ Multi-SIM support. Use multiple SIM cards on one phone.
→ Multi-device support. Connect multiple phones to the same account.
→ Real-time webhooks for incoming messages
→ Multipart messages with auto-splitting for long texts
→ Track delivery status of every message in real time
→ No registration required. No email. No account in local mode.

Here's the wildest part:

That old Android phone in your drawer that you haven't touched in 2 years? Install this app. Insert a SIM card. You now have your own private SMS infrastructure.

Two-factor authentication. Order confirmations. Appointment reminders. Notification alerts. All the things startups pay Twilio thousands a month for.

Free. Running on a phone you already own.

Startups spend $500 to $5,000/month on SMS APIs. This costs the price of a SIM card.

875 GitHub stars. 359 commits. Apache 2.0 License.

100% Open Source.

[Unsloth AI @UnslothAI]

You can now fine-tune Qwen3.5 with our free notebook! 🔥

You just need 5GB VRAM to train Qwen3.5-2B LoRA locally!

Unsloth trains Qwen3.5 1.5x faster with 50% less VRAM.

GitHub: https://t.co/2kXqhhvLsb
Guide: https://t.co/JCPGIRo99s

Qwen3.5-4B Colab: https://t.co/2Aj1mZ3f5j

[Google AI @GoogleAI]

Smarter. Faster. Gemini 3.1 Flash-Lite is here⚡

The model offers uncompromising speed & intelligence at scale by focusing on:

— Cost-efficiency: Priced at just $0.25/1M input and $1.50/1M output tokens, it gets work done faster at a fraction of the cost of larger models, including a 45% increase in output speed compared to Gemini 2.5 Flash

— Compute control: 3.1 Flash-Lite comes with flexible thinking levels so you can actively select how much the model “thinks” for a given task, based on the complexity of your project

— Scalable intelligence for building: The model can handle high volume tasks at scale while keeping costs down *and* can tackle complex workloads where in-depth reasoning is needed, like generating user interfaces or detailed instruction following

3.1 Flash-Lite is rolling out in preview today via the Gemini API in @GoogleAIStudio and Vertex AI.

[Google DeepMind @GoogleDeepMind]

Gemini 3.1 Flash-Lite has landed.

It’s our most cost-efficient Gemini 3 series model yet, built for intelligence at scale. Here’s what’s new 🧵

[Qwen @Alibaba_Qwen]

🚀 Introducing the Qwen 3.5 Medium Model Series
Qwen3.5-Flash · Qwen3.5-35B-A3B · Qwen3.5-122B-A10B · Qwen3.5-27B

✨ More intelligence, less compute.
• Qwen3.5-35B-A3B now surpasses Qwen3-235B-A22B-2507 and Qwen3-VL-235B-A22B — a reminder that better architecture, data quality, and RL can move intelligence forward, not just bigger parameter counts.

• Qwen3.5-122B-A10B and 27B continue narrowing the gap between medium-sized and frontier models — especially in more complex agent scenarios.

• Qwen3.5-Flash is the hosted production version aligned with 35B-A3B, featuring:
– 1M context length by default
– Official built-in tools

🔗 Hugging Face: https://t.co/wFMdX5pDjU

🔗 ModelScope: https://t.co/9NGXcIdCWI

🔗 Qwen3.5-Flash API: https://t.co/82ESSpaqAF

Try in Qwen Chat 👇
Flash: https://t.co/UkTL3JZxIK

27B: https://t.co/haKxG4lETy

35B-A3B: https://t.co/Oc1lYSTbwh

122B-A10B: https://t.co/hBMODXmh1o

Would love to hear what you build with it.

[Miłosz Szewsky 🇵🇱 @milosz_szewsky]

llmfit - полезная утилита, которая показывает, какую LLM можно запустить на вашем устройстве и с каким успехом, определяет оптимальную квантизацию для памяти, прикидывает количество токенов в секунду
вот какие результаты на моём компе 7-летней давности

[Pau Labarta Bajo @paulabartabajo_]

Advice for AI engineers 💡

A small Visual Language Model fine-tuned on your custom dataset is as accurate as GPT-5...

... and costs 50 times less.

For example, LFM2.5-VL-1.6B by @liquidai running locally at full speed with llama.cpp ↓

[Aman @Amank1412]

Someone built a web-based System Design Simulator,

where you drag & drop architecture components and actually simulate traffic, failures, latency, and scaling in real time,

System design just got way more interactive.