FeedCity

Just randomly rabbit-holing down into how traits work in Rust.

A non-technical CFO built a production operations dashboard with Claude Code that had failed with low-code tools and agencies. This shift in who can build software is going to change everything.

Skills actually came out of a prototype I built demonstrating that Claude Code is a general-purpose agent :-)

It was a natural conclusion once we realized that bash + filesystem were all we needed

— Barry Zhang, Anthropic

Tags: skills, claude-code, ai-agents, generative-ai, ai, llms

Anthropic this morning introduced Claude Skills, a new pattern for making new abilities available to their models: Claude can now use Skills to improve how it performs specific tasks. Skills are folders that include instructions, scripts, and resources that Claude can load ...

Today's links The AI that we'll have after AI: Cheap GPUs, unemployed engineers, and open source models. Hey look at this: Delights to delectate. Object permanence: FBI confuses KISS and Dr Who; How the NSA breaks crypto: Bricked Ferrari; Taxing billionaires. Upcoming appeara...

VCF Midwest was even better than I expected Jeff Geerling October 16, 2025

An essential part of being able say ‘I told you so’ is in fact having told you so. Here goes. In April 2023, I wrote an article titled AI: Guaranteed to disrupt our economies. In this piece I also announced I was going to make a fool of myself by making some AI predictions. I have singularly failed to do so. In retrospect this was all spot on, except for perhaps missing the sheer magnitude of the madness that was about to ensue.

NVIDIA DGX Spark + Apple Mac Studio = 4x Faster LLM Inference with EXO 1.0 EXO Labs wired a 256GB M3 Ultra Mac Studio up to an NVIDIA DGX Spark and got a 2.8x performance boost serving Llama-3.1 8B (FP16) with an 8,192 token prompt. Their detailed explanation taught me a lot...

Pro se litigants [people representing themselves in court without a lawyer] account for the majority of the cases in the United States where a party submitted a court filing containing AI hallucinations. In a country where legal representation is unaffordable for most people, it is no wonder that pro se litigants are depending on free or low-cost AI tools. But it is a scandal that so many have been betrayed by them, to the detriment of the cases they are litigating all on their own.

— Riana Pfefferkorn, analyzing the AI Hallucination Cases database for CIS at Stanford Law

Tags: ai-ethics, generative-ai, law, hallucinations, ai, llms

Last year the most useful exercise for getting a feel for how good LLMs were at writing code was vibe coding (before that name had even been coined) - seeing if you could create a useful small application through prompting alone.

Today I think there's a new, more ambitious and significantly more intimidating exercise: spend a day working on real production code through prompting alone, making no manual edits yourself.

This doesn't mean you can't control exactly what goes into each file - you can even tell the model "update line 15 to use this instead" if you have to - but it's a great way to get more of a feel for how well the latest coding agents can wield their edit tools.

Tags: coding-agents, ai-assisted-programming, generative-ai, ai, llms

While Sonnet 4.5 remains the default [in Claude Code], Haiku 4.5 now powers the Explore subagent which can rapidly gather context on your codebase to build apps even faster.

You can select Haiku 4.5 to be your default model in /model. When selected, you’ll automatically use Sonnet 4.5 in Plan mode and Haiku 4.5 for execution for smarter plans and faster results.

— Catherine Wu, Claude Code PM, Anthropic

Tags: coding-agents, anthropic, claude-code, generative-ai, ai, llms, sub-agents

Previous system cards have reported results on an expanded version of our earlier agentic misalignment evaluation suite: three families of exotic scenarios meant to elicit the model to commit blackmail, attempt a murder, and frame someone for financial crimes. We choose not to report full results here because, similarly to Claude Sonnet 4.5, Claude Haiku 4.5 showed many clear examples of verbalized evaluation awareness on all three of the scenarios tested in this suite. Since the suite only consisted of many similar variants of three core scenarios, we expect that the model maintained high unverbalized awareness across the board, and we do not trust it to be representative of behavior in the real extreme situations the suite is meant to emulate.

— Claude Haiku 4.5 System Card

Tags: ai-ethics, anthropic, claude, generative-ai, ai, llms

Introducing Claude Haiku 4.5 Anthropic released Claude Haiku 4.5 today, the cheapest member of the Claude 4.5 family that started with Sonnet 4.5 a couple of weeks ago. It's priced at $1/million input tokens and $5/million output tokens, slightly more expensive than Haiku 3....

As it turns out they don't actually want you to do this (and have some interesting ways to stop you)

Today's links Microsoft, Tear Down That Wall! What the Eurostack is missing. Hey look at this: Delights to delectate. Object permanence: Giga pudding; What Technology Wants; Blue Screens of Death; Bernie outperforming Obama; DRM in JPEGs; Dirty words are politically potent; F...

The October 2025 PEO Directory – Update 2. The Department of War (DoW) is one of the world’s largest organizations.  If you’re a startup trying to figure out who to call on and how to navigate the system, it can be – to put it politely – challenging.Those inside the DoW have little perspective of […]

Microsoft today released software updates to plug a whopping 172 security holes in its Windows operating systems, including at least three vulnerabilities that are already being actively exploited. October's Patch Tuesday also marks the final month that Microsoft will ship security updates for Windows 10 systems. If you're running a Windows 10 PC and you're unable or unwilling to migrate to Windows 11, read on for other options.

A modern approach to preventing CSRF in Go Alex Edwards writes about the new http.CrossOriginProtection middleware that was added to the Go standard library in version 1.25 in August and asks: Have we finally reached the point where CSRF attacks can be prevented without rel...

NVIDIA sent me a preview unit of their new DGX Spark desktop "AI supercomputer". I've never had hardware to review before! You can consider this my first ever sponsored post if you like, but they did not pay me any cash and aside from an embargo date they did not request (no...