- philipp-gayretContext is garbage in, garbage out.
- And https://downdetectorsdowndetector.com says that https://downdetector.com/ is up! >:( What a world we live in
- I find writing a good CLAUDE.md is done by running /init, and having the LLM write it. If you need more controls on how it should work, I would highly recommend you implement it in an unavoidable way via hooks and not in a handwritten note to your LLM.
- I had a similar experience at a different university in NL, practically the entire curriculum was Oracle & Cisco.
- Had me in the first half. But from the "The Microsecond Window" chapter and on...;
> No warning. No error. Just different methods that make no sense.
> This is why write barriers exist. They're not optional extras for C extension authors. They're how you tell the garbage collector: "I'm holding a reference. Don't free this
It's all ChatGPT LinkedIn and Instagram spam type slop. An unfortunate end to an otherwise interesting writeup.
- It's true, when I was working with LLMs on a novel idea it said sorry I can't help you with that!
- I'm aware of the issues around rules as in a default prompt. I had hoped the author of the blog meant a different mechanism when they mentioned "steering rules". I do mean something different, where an agent will self-correct when it is seen going against rules in the initial prompt. I have a different setup myself for Claude Code, and would call parts of that "steering"; adjusting the trajectory of the agent as it goes.
- This is the first time I see "steering rules" mentioned. I do something similar with Claude, curious how it looks for them and how they integrate it with Q/Kiro.
- What is "very very quickly"?
From Wikipedia:
> The reported half-life of glyphosate in soil varies from two to 197 days with a typical field half-life of 47 days being suggested.[56] Soil and climate conditions affect glyphosate's persistence in soil. The median half-life of glyphosate in water varies from a few days to 91 days.[56] At a site in Texas, half-life was as little as three days. A site in Iowa had a half-life of 141.9 days.[94] The glyphosate metabolite AMPA has been found in Swedish forest soils up to two years after a glyphosate application.
It has a lower half-life in water, and a lower half-life when it's warmer. I store my oats both dry and cold.
As for cancer, I don't know - but it certainly is giving everyone parkinsons.
- Our Alexa's stopped responding and my girl couldn't log in to myfitness pal anymore.. Let me check HN for a major outage and here we are :^)
At least when us-east is down, everything is down.
- All I know is I'm on the Claude Code 5x max plan and it works on my machine.
- Tried it in Claude Code via /config, makes it feel like I'm running on Cerebras. It's seriously fast, bottleneck is on human review at this point.
- > But Claude Code now has Plugins
> Do you hear that noise in the distance? It’s me sigh-ing. (...) Yes, maintaining good documents for specific tasks is a good idea. I keep a big list of useful docs in a docs folder as markdown.
I'm not that familiar with Claude Code Plugins, but it looks like it allows integrations with Hooks, which is a lot more powerful than just giving more context. Context is one thing, but Hooks let you codify guardrails. For example where I work we have a setup for Claude Code that guides it through common processes, like how to work with Terraform, Git or manage dependencies and the whitelisting or recommendation towards dependencies. You can't guarantee this just by slapping on more context. With Hooks you can both auto-approve or auto-deny _and_ give back guidance when doing so, for me this is a killer feature of Claude Code that lets it act more intelligently without having to rely on it following context or polluting the context window.
Cursor recently added a feature much like Claude Code's hooks, I hope to see it in Codex too.
- (The irony in posting this was missed by the reasoning HN user)
- I really like this and we're doing a similar approach but instead using Claude Code hooks. What's really nice about this style of whitelisting is that you can provide context on what to do instead; Let's say if `terraform apply` is banned, you can tell it why and instruct it to only do `terraform plan`. Has been working amazing for me.
- Since reading I can --continue I do the same. If I find it's missing something after compressing context I'll just make it re-read a plan or CLAUDE.md
- Can't agree with the formula for performance, on the "/ size" part. You can have a huge codebase, but if the complexity goes up with size then you are screwed. Wouldn't a huge but simple codebase be practical and fine for AI to deal with?
The hierarchy of leverage concept is great! Love it. (Can't say I like the 1 bad line of CLAUDE.md is 100K lines of bad code; I've had some bad lines in my CLAUDE.md from time to time - I almost always let Claude write it's own CLAUDE.md.).
- > I live in the UK now, and my impression is that the same is true here but to a much lesser extent
I worked for a client once who had units in NL and BE, and a UK supplier. We had a short meeting once, it went like so:
> Architect(BE): I have an idea, let's do X!
> Developers(BE): OK boss!
> Developers(NL): Terrible idea. No way we're doing X. Let's do Y!
> Supplier(UK): Well X is interesting. None of our customers do X. But, it is possible!
BE thought X was a good idea, developers questioned it but an architect outranks them. NL thought they decided to do Y, and work on it will start the moment the meeting ends. UK thought they were very very clear not to ever do X.
- I very often hear from developers at clients I work with that code they (not me) generate with AI is not of enough "quality".
So I ask them what quality means. So far, I only get the most basic feedback: it should be in X style, pass Y linter, have N% coverage, have documentation...
At the same time, most, if not all manually written repositories do not pass the newfound quality metrics that must apply to AI code to be quality. I'm glad people are thinking about it at least, but let's not pretend like we cared before when it took manual labour. I'm even more glad we are in an age where quality standards can be fully automated.