Quoting Adam Gordon Bell
I think that a lot of resistance to AI coding tools comes from the same place: fear of losing something that has defined you for so long. People are reacting against overblown hype, and there is overblown hype. I get that, but I also think there’s something deeper going on here. When you’ve worked hard to build your skills, when coding is part of your identity and where you get your worth, the idea of a tool that might replace some of that is very threatening.
— Adam Gordon Bell, When AI Codes, What’s Left for me?
Tags: llms, careers, ai, generative-ai, ai-assisted-programming
An original technicolor print of Star Wars (before all of Lucas’s tinkering)...
An original technicolor print of Star Wars (before all of Lucas’s tinkering) was recently shown in Britain. “It was very clear — without a doubt — that Han shot first.”
TIL: Rate limiting by IP using Cloudflare's rate limiting rules
TIL: Rate limiting by IP using Cloudflare's rate limiting rules
My blog started timing out on some requests a few days ago, and it turned out there were misbehaving crawlers that were spidering my/search/ page even though it's restricted by robots.txt.
I run this site behind Cloudflare and it turns out Cloudflare's WAF (Web Application Firewall) has a rate limiting tool that I could use to restrict requests to /search/* by a specific IP to a maximum of 5 every 10 seconds.
Tags: rate-limiting, security, cloudflare, til
Frequently Asked Questions (And Answers) About AI Evals
Trial Court Decides Case Based On AI-Hallucinated Caselaw
Trial Court Decides Case Based On AI-Hallucinated Caselaw
Joe Patrice writing for Above the Law:[...] it was always only a matter of time before a poor litigant representing themselves fails to know enough to sniff out and flag Beavis v. Butthead and a busy or apathetic judge rubberstamps one side’s proposed order without probing the cites for verification. [...]
It finally happened with a trial judge issuing an order based off fake cases (flagged by Rob Freund). While the appellate court put a stop to the matter, the fact that it got this far should terrify everyone.
It's already listed in the AI Hallucination Cases database (now listing 168 cases, it was 116 when I first wrote about it on 25th May) which lists a $2,500 monetary penalty.
Tags: law, ai, generative-ai, llms, ai-ethics, hallucinations
Hued is a daily game in the vein of Wordle/Spelling Bee where...
I built something that changed my friend group's social fabric
I built something that changed my friend group's social fabric
I absolutely love this as an illustration of the thing where the tiniest design decisions in software can have an outsized effect on the world.Dan Petrolito noticed that his friend group weren't chatting to each other using voice chat on their Discord server because they usually weren't online at the same time. He wired up a ~20 lines of Python Discord bot to turn people joining the voice channel into a message that could be received as a notification and had a huge uptick in conversations between the group, lasting several years.
Via Hacker News
Tags: social-software, discord
French artist Mantra paints photo-realistic murals that look like massive butterfly specimen...
French artist Mantra paints photo-realistic murals that look like massive butterfly specimen display frames. Fantastic.
There’s No Undo Button For Our Fallen Democracy
CBS News: ‘Paramount, President Trump Reach $16 Million Settlement Over “60 Minutes” Lawsuit’
cbsnews.com/news/paramount-trump-60-minutes-lawsuit-settlement/
CBS News:
Paramount will settle President Trump’s lawsuit over a “60 Minutes” interview with Kamala Harris for $16 million, the company announced late Tuesday.
CBS News’ parent company worked with a mediator to resolve the lawsuit. Under the agreement, $16 million will be allocated to Mr. Trump’s future presidential library and the plaintiffs’ fees and costs. Neither Mr. Trump nor his co-plantiff, Texas Rep. Ronny Jackson, will be directly paid as part of the settlement.
The settlement did not include an apology.
It could have been a lot worse, but this is, ultimately, bribery.
Sandboxed tools in a loop
Something I've realized about LLM tool use is that it means that if you can reduce a problem to something that can be solved by an LLM in a sandbox using tools in a loop, you can brute force that problem.
The challenge then becomes identifying those problems and figuring out how to configure a sandbox for them, what tools to provide and how to define the success criteria for the model.
That still takes significant skill and experience, but it's at a higher level than chewing through that problem using trial and error by hand.
My x86 assembly experiment with Claude Code was the thing that made this click for me.
Tags: llm-tool-use, ai-assisted-programming, claude-code, sandboxing, generative-ai, ai, llms
I Will Do Anything to End Homelessness Except Build More Homes. “Look,...
Diogo Jota, Liverpool and Portugal footballer, dies aged 28 in car crash....
Table saws
Quitting programming as a career right now because of LLMs would be like quitting carpentry as a career thanks to the invention of the table saw.
Tags: careers, ai-assisted-programming, generative-ai, ai, llms
Global Ranking
Kilmar Ábrego García says he was tortured in El Salvadorian prison. Hundreds...
Wanna Sit Down? You Gotta Solve The Rubik’s Cube Chair.
American science to soon face its largest brain drain in history. “Over...
Architect David Romero has built several digital models of Frank Lloyd Wright’s...
Architect David Romero has built several digital models of Frank Lloyd Wright’s unrealized buildings, including a mile-high Chicago skyscraper with 528 floors.