Posts tagged with "ai"
- The whole point of OpenAI's Responses API is to help them hide reasoning traces
- Don't feed me AI slop
- The famous "bottomless pit" AI greentext is fake
- Is chain-of-thought AI reasoning a mirage?
- What's the strongest AI model you can train on a laptop in five minutes?
- OpenAI's new open-source model is basically Phi-5
- AI interpretability has the same problems as philosophy of mind
- Why I don't allow AI-generated content on my blog
- The refusal problem in large language models
- Can small AI models think as well as large ones?
- Do not yell at the language model
- The case for regulating AI companions
- How to actually use Model Context Protocol
- Vibe coding and the silent AI war inside tech companies
- Practical notes on getting LLMs to generate new ideas
- The three great virtues of an AI-assisted programmer
- Building an RTS where you issue orders to AI agents
- METR's AI productivity study is really good
- Why we should anthropomorphize LLMs
- Mecha-Hitler, Grok, and why it's so hard to give LLMs the right personality
- How I use LLMs to learn new subjects
- Building tiny AI tools for developer productivity
- Continuous AI in software engineering
- AI coding agents are already commoditized
- What's going to happen to junior engineers?
- Is this your brain on ChatGPT?
- The first big AI disaster is yet to happen
- The illusion of "The Illusion of Thinking"
- AI interpretability is further along than I thought
- John Henry and the large language model
- Why DeepSeek is cheap at scale but expensive to run locally
- How does ChatGPT work? What is AI, really?
- Strengths and limitations of diffusion language models
- Practical AI techniques for daily engineering work
- Diffusion models explained simply
- For many, patience is the killer LLM feature
- Why can't language models come up with new ideas?
- I don't care about your magic prompts
- Sycophancy is the first LLM "dark pattern"
- The OpenAI house style is exhausting
- When you should lie to the language model
- Is using AI wrong? A review of six popular anti-AI arguments
- Principles for coding securely with LLMs
- Why are model arena leaderboards dominated by slop?
- The future of AI is Ruby on Rails
- Refactoring to understand and "vibe coding"
- What's next after the AI bubble bursts?
- Model Context Protocol explained as simply as possible
- Advice for prompting reasoning models
- Using LLMs effectively isn't about prompting
- Thinking like a LLM
- To avoid being replaced by LLMs, do what they can't
- How I use LLMs as a staff engineer
- Why does AI slop feel so bad to read?
- Are DeepSeek's new models really that fast and cheap?
- Why AI labs offer so many different models
- What did DeepSeek figure out about reasoning with DeepSeek-R1?
- Talking to ChatGPT costs 5ml of water, not 500ml
- MCTS and LLMs: what's the big deal?
- From hours to seconds: AI tools to detect animal calls
- How LLMs work
- Building LLM-driven agents
- Porting and hacking Llama2.c for fun and profit