News for hackers. Stuff that matters.

gatienboquet

Re:Cerebras Code now supports GLM 4.6 at 1000 tokens/sec on Friday November 07, 2025 @11:03PM (#45854033)
Vibe Slopping at 1000 tokens per second
Re:Copilot Chat in VS Code is now open source on Friday June 27, 2025 @04:42PM (#44400061)
Here's the system Prompt Template they use : https://github.com/microsoft/vscode-copilot-chat/blob/4c72d6...
Re:Quick Primer on MCP Using Ollama and LangChain on Monday April 14, 2025 @09:06AM (#43680853)
You know it's going to be a great article when the design is from 1995
Re:The Agent2Agent Protocol (A2A) on Wednesday April 09, 2025 @12:56PM (#43634412)
XHTML 2.0,WML,SOAP, APPN,WAP...for each new technology there's thousands of failed protocol.
Re:QVQ-Max: Think with Evidence on Sunday April 06, 2025 @09:12AM (#43601205)
Isn't "thinking" in image mode basically what chatgpt 4o image generation do ?
Model is insane but the RPM limit is insane too.
I have ADHD and while you're right that everyone experiences some of these things occasionally, for those with ADHD our emotion regulation system is fundamentally different.

As a kid, you build your identity and coping mechanisms through emotional experiences, but when your emotion engine is 'broken' or works differently, you develop differently.

The intensity, frequency, and impact of these experiences for someone with ADHD is far beyond what neurotypical people experience.

It's not about occasional forgetfulness or distraction - it's about a brain that's structurally and functionally different, affecting every aspect of daily functioning.

Getting diagnosed isn't about finding an excuse, it's about finally understanding why basic things others find easy have always been so much harder for you.

Re:Qwen2.5-VL-32B: Smarter and Lighter on Monday March 24, 2025 @03:08PM (#43464396)
So today is Qwen. Tomorrow a new SOTA model from Google apparently, R2 next week.

We haven't hit the wall yet.

I have ADHD and I've decided that it's part of my identity.

I was diagnosed late at 28. When I got diagnosed, my psychologist told me that I had to reassess my life. Many behaviors that people had misinterpreted as laziness, carelessness, or lack of commitment were actually manifestations of my ADHD.

Friends who thought I didn't care when I forgot plans, teachers who believed I wasn't trying hard enough, and colleagues who saw me as disorganized - they were all seeing untreated ADHD symptoms, not character flaws.

Understanding this was liberating because it meant I wasn't fundamentally flawed as a person. I had to rebuild myself, my confidence - it was a new start in life.

It's a process to relearn and teach yourself that you can do it now. Labeling publicly, saying to your friends and family that you are ADHD makes it so that you OWN your change, you OWN your disability.

tldr, ADHD as an IDENTIY is for me : Reclaim control over your narrative instead of letting others define your behaviors

Create accountability for yourself and set realistic expectations with others

Remove shame from the equation by openly acknowledging your challenges

Enable yourself to access appropriate accommodations and support systems

You can build your own MCP client https://modelcontextprotocol.io/quickstart/client

You will need an ANTHROPIC_API_KEY though.

Re:US Ends Support For Ukrainian F-16s on Sunday March 09, 2025 @02:04PM (#43311891)
If you have local warrants.
Re:Mistral OCR on Thursday March 06, 2025 @03:16PM (#43284661)
La Plateforme agent builder - https://console.mistral.ai/build/agents/new
Re:Mistral OCR on Thursday March 06, 2025 @02:44PM (#43284341)
I feel like i can't create an agent with their OCR model yet ? Is it something planned or it's only API?
Re:Exploring the Paramilitary Leaks on Thursday March 06, 2025 @09:00AM (#43280253)
Great tool, could be the solution indeed
Re:Exploring the Paramilitary Leaks on Thursday March 06, 2025 @08:23AM (#43279888)
ask claude for the script, it will be done in 3 seconds.
Re:Expanding AI Overviews and Introducing AI Mode on Wednesday March 05, 2025 @01:27PM (#43270343)
creative destruction.

They will kill their own product with constant innovation before someone else do.

Re:Apple M3 Ultra on Wednesday March 05, 2025 @11:09AM (#43268479)
If my grandmother had wheels, she’d be a bicycle
Re:Apple M3 Ultra on Wednesday March 05, 2025 @11:04AM (#43268410)
VRAM capacity is the initial gatekeeper, then bandwidth becomes the limiting factor.
Re:Apple M3 Ultra on Wednesday March 05, 2025 @09:53AM (#43267276)
They use their own M chips for IA. They are far more advanced on AI than the majority of company.

They are using OpenAI for now but in couple months they will own the full chain of value.

Re:Apple M3 Ultra on Wednesday March 05, 2025 @09:51AM (#43267252)
NVIDIA RTX 4090: ~1,008 GB/s

NVIDIA RTX 4080: ~717 GB/s

AMD Radeon RX 7900 XTX: ~960 GB/s

AMD Radeon RX 7900 XT: ~800 GB/s

How's that slow exactly ?

You can have 10000000Gb/s and without enough VRAM it's useless.

Re:Apple M3 Ultra on Wednesday March 05, 2025 @09:43AM (#43267089)
LLMs are primarily "memory-bound" rather than "compute-bound" during normal use.

The model weights (billions of parameters) must be loaded into memory before you can use them.

Think of it like this: Even with a very fast chef (powerful CPU/GPU), if your kitchen counter (VRAM) is too small to lay out all the ingredients, cooking becomes inefficient or impossible.

Processing power still matters for speed once everything fits in memory, but it's secondary to having enough VRAM in the first place.

Re:Apple M3 Ultra on Wednesday March 05, 2025 @09:40AM (#43267037)
No benchmarks yet for the LLMs :(
Re:The Era of Solopreneurs Is Here on Sunday March 02, 2025 @02:07PM (#43233798)
A sales team is even more important! Actual humans to talk to you—this is the future! The demand for non-automated, human tasks will skyrocket. Our society will shift back to being human-centric, just like before any automation.
Re:The Era of Solopreneurs Is Here on Sunday March 02, 2025 @02:05PM (#43233779)
Shopify will use AI too and add way more values on their product soon also ?

The need for IA Programmer will be x10 too.

I want this and as input scanned pdf. It would solve my issues.
Re:AI's Biggest Flaw? The Blinking Cursor Problem on Wednesday February 26, 2025 @06:02PM (#43189288)
Great article, Mistral CEO spoke about this issue, it's their main task now, figuring out the interface between IA and human.
Re:Kaneo – An open source project management platform on Saturday February 22, 2025 @05:47PM (#43144071)
Quick tips : You homepage should be the product on "demo" mode without any login.
Re:Kaneo – An open source project management platform on Saturday February 22, 2025 @05:46PM (#43144068)
I have no idea how to log on the demo.
Re:Kaneo – An open source project management platform on Saturday February 22, 2025 @05:45PM (#43144058)
> Click on the website

> After spending 20 sec on the website i have no idea what the app look like

> Leave

Re:Show HN: Willpayforthis.com – Ideas people will pay for on Saturday February 22, 2025 @05:03PM (#43143741)
PumpFun Driven Development (PFDD) : Launch a Solana Token without any project behind it. When people buy it. Rug pull them. Rince and repeat.

Older »