Featured
The paper asked me to explain vibe coding, and I did so, because I think something big is coming there, and I'm deep in, and I worry that normal people are not able to see it and I want them to be prepared. But people can't just read something and hate you quietly; they can't see that you have provided them with a utility or a warning; they need their screech. You are distributed to millions of people, and become the local proxy for the emotions of maybe dozens of people, who disagree and demand your attention, and because you are the one in the paper you need to welcome them with a pastor's smile and deep empathy, and if you speak a word in your own defense they'll screech even louder.
— Paul Ford, on writing about vibe coding for the New York Times
Tags: vibe-coding, new-york-times, paul-ford
The latest scourge of Twitter is AI bots that reply to your tweets with generic, banal commentary slop, often accompanied by a question to "drive engagement" and waste as much of your time as possible.
I just found out that the category name for this genre of software is reply guy tools. Amazing.
Tags: ai-ethics, twitter, slop, generative-ai, definitions, ai, llms
Nothing humbles you like telling your OpenClaw “confirm before acting” and watching it speedrun deleting your inbox. I couldn’t stop it from my phone. I had to RUN to my Mac mini like I was defusing a bomb.
I said “Check this inbox too and suggest what you would archive or delete, don’t action until I tell you to.” This has been working well for my toy inbox, but my real inbox was too huge and triggered compaction. During the compaction, it lost my original instruction 🤦♀️
Tags: ai-ethics, generative-ai, ai-agents, openclaw, ai, llms
We’ve made GPT-5.3-Codex-Spark about 30% faster. It is now serving at over 1200 tokens per second.
— Thibault Sottiaux, OpenAI
Tags: openai, llms, ai, generative-ai
Taalas serves Llama 3.1 8B at 17,000 tokens/second
This new Canadian hardware startup just announced their first product - a custom hardware implementation of the Llama 3.1 8B model (from July 2024) that can run at a staggering 17,000 tokens/second.I was going to include a video of their demo but it's so fast it would look more like a screenshot. You can try it out at chatjimmy.ai.
They describe their Silicon Llama as “aggressively quantized, combining 3-bit and 6-bit parameters.” Their next generation will use 4-bit - presumably they have quite a long lead time for baking out new models!
Via Hacker News
Tags: ai, generative-ai, llama, llms
Reached the stage of parallel agent psychosis where I've lost a whole feature - I know I had it yesterday, but I can't seem to find the branch or worktree or cloud instance or checkout with it in.
... found it! Turns out I'd been hacking on a random prototype in /tmp and then my computer crashed and rebooted and I lost the code... but it's all still there in ~/.claude/projects/ session logs and Claude Code can extract it out and spin up the missing feature again.
Tags: parallel-agents, coding-agents, claude-code, generative-ai, ai, llms
Long running agentic products like Claude Code are made feasible by prompt caching which allows us to reuse computation from previous roundtrips and significantly decrease latency and cost. [...]
At Claude Code, we build our entire harness around prompt caching. A high prompt cache hit rate decreases costs and helps us create more generous rate limits for our subscription plans, so we run alerts on our prompt cache hit rate and declare SEVs if they're too low.
Tags: prompt-engineering, anthropic, claude-code, ai-agents, generative-ai, ai, llms
LadybirdBrowser/ladybird: Abandon Swift adoption
Back in August 2024 the Ladybird browser project announced an intention to adopt Swift as their memory-safe language of choice.As of this commit it looks like they've changed their mind:
Everywhere: Abandon Swift adoption
After making no progress on this for a very long time, let's acknowledge it's not going anywhere and remove it from the codebase.
Via Hacker News
25+ years into my career as a programmer I think I may finally be coming around to preferring type hints or even strong typing. I resisted those in the past because they slowed down the rate at which I could iterate on code, especially in the REPL environments that were key to my productivity. But if a coding agent is doing all that typing for me, the benefits of explicitly defining all of those types are suddenly much more attractive.
Tags: ai-assisted-programming, programming, programming-languages
LLMs are eating specialty skills. There will be less use of specialist front-end and back-end developers as the LLM-driving skills become more important than the details of platform usage. Will this lead to a greater recognition of the role of Expert Generalists? Or will the ability of LLMs to write lots of code mean they code around the silos rather than eliminating them?
— Martin Fowler, tidbits from the Thoughtworks Future of Software Development Retreat, via HN)
Tags: martin-fowler, careers, generative-ai, ai, llms, ai-assisted-programming
This is the story of the United Space Ship Enterprise. Assigned a five year patrol of our galaxy, the giant starship visits Earth colonies, regulates commerce, and explores strange new worlds and civilizations. These are its voyages... and its adventures.
— ROUGH DRAFT 8/2/66, before the Star Trek opening narration reached its final form
Tags: screen-writing, science-fiction
