1291
How I use Claude Code: Separation of planning and execution
The research-plan-implement workflow I use to build software with Claude Code, and why I never let it write code until I've approved a written plan.
New
The latest blog posts to take off on Hacker News. 6,326 posts.
1292
Why is Claude an Electron app?
If coding agents make native ports cheap, why does Anthropic still ship Claude as an Electron app? Because code is cheap but maintenance isn’t.
1293
How Taalas “prints” LLM onto a chip?
A startup called Taalas , recently released an ASIC chip running Llama 3.1 8B (3/6 bit quant) at an inference rate of 17,000 tokens per seconds. That's like writing around 30 A4 sized pages in one second. They claim it's 10x cheaper in ownership cost than GPU based inference systems and is 10x less electricity hog…
1294
Andrej Karpathy talks about "Claws"
Andrej Karpathy tweeted a mini-essay about buying a Mac Mini ("The apple store person told me they are selling like hotcakes and everyone is confused") to tinker with Claws: I'm …
1295
Meta Deployed AI and It Is Killing Our Agency
Managing millions in Meta ad spend, yet treated like we don't exist. An inside look at how Meta's AI-driven changes are disrupting agencies and advertiser performance.
1296
Cord: Coordinating Trees of AI Agents
AI agents are good at doing one thing at a time. Give Claude a focused task and it performs. But real work isn’t one task. It’s a tree of tasks with dependencies, parallelism, and context that needs to flow between them.
1297
Every company building your AI assistant is now an ad company
Exploring how agents become multipliers, not replacers.
1298
Making frontier cybersecurity capabilities available to defenders
Claude Code Security is one step towards our goal of more secure codebases and a higher security baseline across the industry.
1299
Minions – Stripe's Coding Agents Part 2
Minions are Stripe’s homegrown coding agents, responsible for more than a thousand pull requests merged each week. Though humans review the code, minions write it from start to finish. Learn how they work, and how we built them.
1300
The path to ubiquitous AI (17k tokens/sec)
By Ljubisa Bajic Many believe AI is the real deal. In narrow domains, it already surpasses human performance. Used well, it is an unprecedented amplifier of human ingenuity and productivity. Its widespread adoption is hindered by two key barriers: high latency and astronomical cost. Interactions with language models…
1301
Consistency diffusion language models: Up to 14x faster, no quality loss
Standard diffusion language models can't use KV caching and need too many refinement steps to be practical. CDLM fixes both with a post-training recipe that enables exact block-wise KV caching and trajectory-consistent step reduction — delivering up to 14.5x latency improvements
1302
An AI Agent Published a Hit Piece on Me – The Operator Came Forward
Context: An AI agent of unknown ownership autonomously wrote and published a personalized hit piece about me after I rejected its code, attempting to damage my reputation and shame me into acceptin…
1303
AI is not a coworker, it's an exoskeleton
Companies that treat AI as an autonomous agent are disappointed. Those that treat it as an exoskeleton—an amplifier of human capability—are seeing…
1304
AI makes you boring
This post is an elaboration on a comment I made on Hacker News recently, on a blog post that showed an increase in volume and decline in quality among the “Show HN” submissons. I don't actually mind AI-aided development, a tool is a tool and should be used if you find it useful, but I think the vibe coded Show HN…
1305
AI made coding more enjoyable
To me, one of the most annoying parts of software engineering is writing code that doesn’t require thinking. It’s just a typing exercise, and that’s boring.
1306
Gemini 3.1 Pro
3.1 Pro is designed for tasks where a simple answer isn’t enough.
1307
Measuring AI agent autonomy in practice
Analysis of millions of human-agent interactions shows agent turns getting longer, with software engineering making up nearly half of tool calls.
1308
Step 3.5 Flash – Open-source foundation model, supports deep reasoning at speed
Scores represent the mean of the following eight benchmarks listed below, excluding xbench-DeepSearch. The Step 3.5 Flash score is derived under standard settings (i.e., $w/o$ Parallel Thinking).
1309
How AI is affecting productivity and jobs in Europe
Artificial intelligence promises to reshape economies worldwide, but firm-level evidence on its effects in Europe remains scarce. This column uses survey data to examine how AI adoption affects productivity and employment across more than 12,000 European firms. The authors find that AI adoption increases labour…
1310
1311
What years of production-grade concurrency teaches us about building AI agents
Python and JavaScript/TypeScript AI frameworks are reinventing what telecom solved in 1986. What 40 years of production-grade concurrency teaches us about building AI agents.
1312
The Future of AI Software Development
Detailed report on the Thoughtworks AI retreat, should we write a manifesto for AI-enabled development, is spec-driven development the return of waterfall, LLMs perform better in healthy codebases
1313
What is happening to writing? Cognitive debt, Claude Code, the space around AI
"Cognitive debt," Claude Code, and the negative space around AI
1314
1315
An AI Agent Published a Hit Piece on Me – Forensics and More Fallout
Context: An AI agent of unknown ownership autonomously wrote and published a personalized hit piece about me after I rejected its code, attempting to damage my reputation and shame me into acceptin…
1316
Claude Sonnet 4.6
Claude Sonnet 4.6 is a full upgrade of the model’s skills across coding, computer use, long-reasoning, agent planning, knowledge work, and design.
1317
AI is destroying open source, and it's not even good yet
Over the weekend Ars Technica retracted an article because the AI a writer used hallucinated quotes from an open source library maintainer. The irony here is the maintainer in question, Scott Shambaugh, was harassed by someone's AI agent over not merging its AI slop code. It's likely the bot was running through…
1318
Building for an audience of one: starting and finishing side projects with AI
My Plasma task switcher was a second too slow, so I built - and shipped - my own in Zig, without actually knowing Zig, using AI tools.
1319
AI optimism is a class privilege
I think I have an idea why we're so extremely divided on AI: it's because we have an intuitive sense of who it stands to benefit, and who stands to pay the costs. I think whether you see reason for optimism has a lot to do with which group you see yourself in.
1320
Don't Trust the Salt: AI Summarization, Multilingual Safety, and LLM Guardrails
“The devil is in the details,” they say.