1381
S1: A $6 R1 competitor?
Principal AI Architect. Creator of open-strix, a harness for building agent teams. Writing about AI architecture, stateful agents, and what happens when you give AI memory.
New
The latest blog posts to take off on Hacker News. 3,091 posts.
1382
How I use LLMs as a staff engineer
What I use them for and what I don't
1383
"A computer can never be held accountable"
This legendary page from an internal IBM training in 1979 could not be more appropriate for our new age of AI. A computer can never be held accountable Therefore a …
1384
Decorator JITs: Python as a DSL
Spend enough time looking at Python programs and packages for machine learning, and you'll notice that the "JIT decorator" pattern is pretty popular. For example, this JAX snippet:
1385
Anthropic: "Applicants should not use AI assistants"
While we encourage people to use AI systems during their role to help them work faster and more effectively, please do not use AI assistants during the application process. We …
1386
I Use Cline for AI Engineering
An assessment after evaluating the landscape
1387
How to Run DeepSeek R1 671B Locally on a $2000 EPYC Server
When you click on links to various merchants on this site and make a purchase, this can result in this site earning a commission. Affiliate programs and affiliations include, but are not limited to, the eBay Partner Network. As an Amazon Associate I earn from qualifying purchases. #ad #promotions
1388
Notes on OpenAI o3-mini
OpenAI’s o3-mini is out today. As with other o-series models it’s a slightly difficult one to evaluate—we now need to decide if a prompt is best run using GPT-4o, o1, …
1389
How to Train an AI Image Model on Yourself
It takes less than an hour and $3.
1390
Mini-R1: Reproduce DeepSeek R1 "Aha Moment"
Reproduce Deepseek R1 „aha moment“ and train an open model using reinforcement learning trying to teach it self-verification and search abilities all on its own to solve the Countdown Game.
1391
On DeepSeek and export controls
A few weeks ago I made the case for stronger US export controls on chips to China. Since then DeepSeek, a Chinese AI company, has managed to — at least in some respects — come close to the performance of US frontier AI models at lower cost.
1392
I do not want AI to "polish" me
I was sending an email when a little magic wand popped up that said “Polish” and I thought that was weird because why would I want to translate my email into Polish? I tried to click on…
1393
Promising results from DeepSeek R1 for code
PR by Xuan-Son Nguyen for llama.cpp: This PR provides a big jump in speed for WASM by leveraging SIMD instructions for qX_K_q8_K and qX_0_q8_0 dot product functions. Surprisingly, 99% of …
1394
1395
I trusted an LLM, now I'm on day 4 of an afternoon project
A quick project spiraled into a marathon of AI missteps, hardware headaches, and hard-earned lessons. Welcome to the story of Deskthang.
1396
The Illustrated DeepSeek-R1
A recipe for reasoning LLMs
1397
When AI promises speed but delivers debugging hell
Lessons learned from building Codescribble with a little help (and a lot of frustration) from an AI
1398
Using AI for Coding: My Journey with Cline and LLMs
How I leveraged AI tools like Cline to enhance the UI/UX of a website and streamline backend tasks. From redesigning pages and translating content to navigating the benefits and challenges of AI-assisted development, this blog post highlights the potential of using large language models to boost productivity while…
1399
Explainer: What's r1 and everything else?
Principal AI Architect. Creator of open-strix, a harness for building agent teams. Writing about AI architecture, stateful agents, and what happens when you give AI memory.
1400
AI slop, suspicion, and writing back
On developing an involuntary reflex for spotting AI slop
1401
Searching for DeepSeek's glitch tokens
A first attempt at identifying and cataloging DeepSeek's glitched tokens
1402
The impact of competition and DeepSeek on Nvidia
All the reasons why Nvidia will have a very hard time living up to the currently lofty expectations of the market.
1403
AI isn't going to kill the software industry
I feel like half of my social media feed is composed of AI grifters saying software developers are not going to make it. Combine that sentiment with some economic headwinds and it's easy to feel like we're all screwed. I think that's bullshit. The best days of our industry lie ahead.
1404
An overview of gradient descent optimization algorithms (2016)
Gradient descent is the preferred way to optimize neural networks and many other machine learning algorithms but is often used as a black box. This post explores how many of the most popular gradient-based optimization algorithms such as Momentum, Adagrad, and Adam actually work.
1405
Using generative AI as part of historical research: three case studies
... in specific domains. Three case studies with GPT-4o, o1, and Claude Sonnet 3.5, and what they mean
1406
Coping with dumb LLMs using classic ML
Taking the output of many dumb LLM search relevance judges and feeding the output to a decision tree to improve precision
1407
OpenAI's o1 Playing Codenames
I got OpenAI's o1 to play codenames and the results were surprisingly good
1408
Should we use AI and LLMs for Christian apologetics? (2024)
The reasons why I don’t give permission for material I’ve written to be used as training data for an LLM chatbot designed to do Christian apologetics
1409
Minecraft with object impermanence
I generally am uninterested in generative AI that's too close to the real thing. But every once in a while there's a modern AI thing that's so glitchy and broken that it's strangely compelling. There's this generative AI knockoff of Minecraft that fails so hard
1410
Using ChatGPT is not bad for the environment
And a plea to think seriously about climate change without getting distracted