HNHacker News
TopNewBestAskShowJobs

perrygeo

3,194 karma · joined April 28, 2014

submissionscomments
perrygeo··on Emacs and Vim in the Age of AI
Try CodeCompanion if you're using neovim. I have a keybind set up and takes the highlighted region, prepends some context which says roughly "if you see a TODO comment, do it, if you see a WTF comment, try to explain it", and presents you an inline diff to accept/reject edits. It's great for tactical LLM use on small sections of code.

For strategic use on any larger codebase though, it's more productive to use something like plan mode in Claude code.

perrygeo··on We should revisit literate programming in the agent era
Considering LLMs are models of language, investing in the clarity of the written word pays off in spades.

I don't know whether "literate programming" per se is required. Good names, docstrings, type signatures, strategic comments re: "why", a good README, and thoughtfully-designed abstractions are enough to establish a solid pattern.

Going full "literate programming" may not be necessary. I'd maybe reframe it as a focus on communication. Notebooks, examples, scripts and such can go a long way to reinforcing the patterns.

Ultimately that's what it's about: establishing patterns for both your human readers and your LLMs to follow.

perrygeo··on ZeroDayClock: Statistics on CVEs Exploitation
Wow, the world is getting much faster at exploiting CVEs

> 67.2% of exploited CVEs in 2026 are zero-days, up from 16.1% in 2018

But the exploit rate (the pct of all published CVEs that are actually exploited in the wild) has dropped from a high of 2.11% in 2021 to 0.64% in 2026. Meaning we're either getting worse at exploitation (not likely) or reporting more obscure, pragmatically not-really-an-issue issues that can't be replicated IRL.

So we're in a weird situation:

The vast majority 99.4% of CVEs will never see the light of day as an actual attack. Lots of noise, and getting noisier.

But those that do will happen with increasing speed! So there are increased consequences for missing the signal.

Don't worry about it. But don't blink.

perrygeo··on The happiest I've ever been
The entire zeitgeist of software technology revolves around the assumption that making things efficient, easy, and quick is inherently good. Most people who are "sitting in front of rectangles, moving tiny rectangles" have sometime grandiose notions of their works' importance; we're making X work better for the good of Y to enable Z. Abstract shit like that.

No man, you're just making X easier. If the world needs more X, fine. If not, woops.

The detachment from reality makes it all too easy to deceive yourself into thinking "hey this actually helps people".

perrygeo··on I hate AI side projects
I agree. I think this is the LLM superpower: making quick prototypes that allow us to speak concretely about technical tradeoffs.

My comment was pointed at people who use AI specifically with the goal of making anything easier and faster. Doesn't matter what it is. "Faster and easier is better". as though doing more of the same shit are primary goals in themselves.

If you're using AI to explore better technical decisions, you're doing it right! AI can be a catalyst for engineering and science. But not if we treat it like a mere productivity tool. The quality of the thing enabled by the AI very much matters.

perrygeo··on The Software Development Lifecycle Is Dead
Requirements handed down - never seen it in 25 years. The requirements are always fluid, by definition. At best, you get a wish list which needs to be ammended with reality. If you have completely static requirements, you don't need an engineer! You just do it. Engineering IS refining the requirements according to empirical data.

Once you have requirements that are correct (for all well-defined definitions of "correct"), the code implementation is so trival that an LLM can do it :-)

perrygeo··on I hate AI side projects
Doing things "faster" and "easier" is an interesting way to put it. It places all of the value on one's personal experience of using the AI, and completely ignores the quality of the thing produced. Which explains why most stuff produced by LLMs is throwaway garbage! It only reinforces the parent comment - there is virtually no emphasis on making things "better".
perrygeo··on Infrastructure decisions I endorse or regret after 4 years at a startup (2024)
I agree with the sentiment, that most non-decisions are really implicit decisions in disguise. They have implications whether you thought about them up front or not. And if you need to revisit those non-decisions, it will cost you.

But I don't like calling this tech debt. The tech debt concept is about taking on debt explicitly, as in choosing the sub-optimal path on purpose to meet a deadline then promising a "payment plan" to remove the debt in the future. Tech debt implies that you've actually done your homework but picked door number 2 instead. A very explicit choice, and one where decision makers must have skin in the game.

A hurried, implicit choice has none of those characteristics - it's ignorance leading (inevitably?) to novel problems. That doesn't fit the debt metaphor at all. We need to distinguish tech debt from plain old sloppy decision making. Maybe management can even start taking responsibility for decisions instead of shrugging and saying "Tech debt, what can you do, amirite?"

perrygeo··on Bridging Elixir and Python with Oban
> Succinctness, functionality and popularity of the language are now much more important factors.

Not my experience at all. The most important factor is simplicity and clarity. If an LLM can find the pattern, it can replicate that pattern.

Language matters to the extent it encourages/forces clear patterns. Language with more examples, shorter tokens, popularity, etc - doesn't matter at all if the codebase is a mess.

Functional languages like Elixir make it very easy to build highly structured applications. Each fn takes in a thing and returns another. Side effects? What side effects? LLMs can follow this function composition pattern all day long. There's less complexity, objectively.

But take languages that are less disciplined. Throw in arbitrary side effects and hidden control flow and mutable state ... the LLM will fail to find an obviously correct pattern and guess wildly. In practice, this makes logical bugs much more likely. Millions of examples don't help if your codebase is a swamp. And languages without said discipline often end up in a swamp.

perrygeo··on AI made coding more enjoyable
> explore new approaches and connect ideas faster

This is the hidden super power of LLM - prototyping without attachment to the outcome.

Ten years ago, if you wanted to explore a major architectural decision, you would be bogged down for weeks in meetings convincing others, then a few more weeks making it happen. Then if it didn't work out, it feels like failure and everyone gets frustrated.

Now it's assumed you can make it work fast - so do it four different ways and test it empirically. LLMs bring us closer to doing actual science, so we can do away with all the voodoo agile rituals and high emotional attachment that used to dominate the decision process.

perrygeo··on There is unequivocal evidence that Earth is warming (2024)
> Even the crotchetiest and most out-of-touch people I know basically accept that the Earth is warming now

Same. Empirical evidence is just too hard to ignore.

It's quite amazing watching the "climate change isn't real" folks transition to "climate change is no big deal", then to "climate change is too hard/expensive to deal with".

perrygeo··on Drinking 2-3 cups of coffee a day tied to lower dementia risk
An Alarming Decline in the Nutritional Quality of Foods: The Biggest Challenge for Future Generations’ Health

https://pmc.ncbi.nlm.nih.gov/articles/PMC10969708/

perrygeo··on Drinking 2-3 cups of coffee a day tied to lower dementia risk
The proposed mechanism is polyphenols.

Historically, you'd get your polyphenols from your garden or wild gathering. But we know that industrial crops (even organic grown) have extremely low polyphenol content compared to their wild counterparts. So coffee remains as one of the few strong sources you can buy in a grocery store.

Hypothesis: Polyphenols from other sources would be just as protective as coffee.

perrygeo··on What have you been working on and AI is replacing you?
> The features I am currently working on cannot be vibe-coded, because no AI can understand the context.

It's always possible to improve understanding and put the context into writing, usually just that no one has. Clean up the variable names and docs and the language models (and other developers!) will understand the context better. This amounts to doubling down on clear technical communications.

Another way to say it: LLMs are pattern matching machines. So in a twisted way, I see LLMs driving code quality improvements - if only to make the LLMs more effective. Improve the pattern, improve the pattern matching.

perrygeo··on Improving 15 LLMs at Coding in One Afternoon. Only the Harness Changed
Witness the giant leap forward in the capabilities of coding agents over the last year. There has been no such leap in LLM model performance. I think the causality is crystal clear. It's nothing about "AGI" and all about existing LLMs learning to use existing tools.

Even a sub-par LLM, put into a context where it has access to unix tools and network and files etc, is vastly more capable than the best LLM chatbot.

perrygeo··on Claude Code is being dumbed down?
I must use AI differently than y'all. Do we not use plan mode?

There is almost no value in watching the stream of intermediate tokens. There's no need to micromanage the agent's steps. Just monitor the artifact and insist the LLM summarizes findings in plain English.

If it can't explain the proposed change coherently, it can't code it coherently either. `git restore .`

I find it much more effective to throw away bad sessions, try a new prompt than to massage the existing context swamp.

perrygeo··on The silent death of good code
For me it comes down to Language. They're LLMs after all. They pattern match on tokens, and if your tokens have muddled semantics, you've lost before you even started.

I have a codebase where variables are named poorly - nah that's too generous, variable names are insane; inconsistent even within a single file and often outright wrong and misleading. No surprise - the LLMs choke and fail to produce viable changsets. Bad pattern = bad code generated from that pattern.

Going through and clarifying the naming (not ever refactoring) was enough to establish the pattern correctly. A little pedantry and the LLM was off to the races.

If LLMs are the future of coding, the number one highest priority for the software industry should be to fix muddled naming, bad patterns, and obfuscated code. My bet is that building clean code foundations is the fastest way to fully agentic coding.

perrygeo··on How to effectively write quality code with AI
This. Historically there's been a lot of resistance to the idea of refactoring or refining features. The classic "It works, just ship it" mentality that leaves mountains of tech debt in its wake.

And there _was_ a good reason to resist refactoring. It takes time and effort! After "finishing" something, the timeline, the mental and physical energy, the institutional support, is all dried up. Just ship it and move on.

But LLMs change the equation. There's no reason to leave sloppy sub-optimal code around. If you see something, say something. Wholesale refactoring your PR is likely faster than running your test suite. Literally no excuses for bad code anymore.

You'd think it didn't need to be said but, given we have a tool to make coding vastly more efficient, some people use that tool to improve quality rather than just pump out more quantity.

perrygeo··on Coding assistants are solving the wrong problem
I feel the same way. LLMs errors sound most plausible to those who know least.

On complex topics where I know what I'm talking about, model output contains so much garbage with incorrect assumptions.

But complex topics where I'm out of my element, the output always sounds strangely plausible.

This phenomenon writ large is terrifying.

perrygeo··on Coding is when we're least productive
Having been in this situation more than once, recreating a concept from scratch when you've already coded it once takes ~20% of the time. This also tracks with my long term empirical observation that roughly 80% of a software project is maintenance, testing, debugging, monitoring, fixing bugs, planning, refactoring, etc.

Sitting down to an editor and typing out ascii charachters is the smallest and least consequential part of software development. And that was _before_ LLMs enter the equation - now it's not even strictly necessary. The software industry needs to get over its obsession with coding as an activity, and with code as an asset. Code is at best a necessary liability. Software systems are what we should be focused on.

perrygeo··on Some notes on starting to use Django
> (configure to run in CI)

Every time I've believed this, I came back to broken CI.

Depending on your language ecosystem, your CI workflows and build deps stand a greater chance to break than your code.

perrygeo··on AI’s impact on engineering jobs may be different than expected
I jumped into a new-to-me Typescript application and asked Claude to build a thing, in vague terms matching my own uncertainty and unfamiliarity. The result was similarly vague garbage. Three shots and I threw them all away.

Then I watched a someone familiar with the codebase ask Claude to build the thing, in precise terms matching their expertise and understanding of the code. It worked flawlessly the first time.

Neither of us "coded", but their skill with the underlying theory of the program allowed them to ask the right questions, infinitely more productive in this case.

Skill and understanding matter now more than ever! LLMs are pushing us rapidly away from specialized technicians to theory builders.

perrygeo··on Vitamin D and Omega-3 have a larger effect on depression than antidepressants
Thank you. Fixing a vitamin deficiency is an obvious benefit to physical health. But does it "cure depression"? To the extent that your depression was caused by vitamin deficiency, sure. But then didn't you just cure a vitamin deficiency? I'm sure a lot of things starting improving once your body starts getting proper nutrients after years of neglect! That doesn't indicate causality.
perrygeo··on Making niche solutions is the point
Wat? Android, Linux, BSD (incl iOS and Mac) absolutely dominate the market in terms of mind share and deployment. I can't think of another philosophy that is so directly, causally responsible for billions of dollars of realized value.

It sounds like you're parroting the corporate line of the early 80s. "Making money directly selling software artifacts is the only way to win." Which, as we know in retrospect, was a completely failed strategy, steamrolled by companies which... wait for it... adopted more flexible technology based on the Unix philosophy.

perrygeo··on Microservices for the Benefits, Not the Hustle (2023)
I guess I will never understand the microservices vs monolith debate. What about just "services"? There are 1001 reasons you might want to peel off functionality into a separate service. Just do that, without making it into some philisophical debate.
perrygeo··on Gas Town's agent patterns, design bottlenecks, and vibecoding at scale
I get that Gas Town is part tongue-in-cheek, a strawman to move the conversation on Agentic AI forward. And for that I give it credit.

But I think there's a real missed opportunity here. I don't think it goes far enough. Who wants some giant complex system of agents conceived by a human. The agents, their role and relationships, could be dynamically configured according to the task.

What good is removing human judegment from the loop, only to constrain the problem by locking in the architecture a priori. It just doens't make sense. Your entire project hinges on the waterfall-like nature of the agent design! That part feels far too important, but gas town doesn't have much curiousity at all about changing that. These Mayors, and Polecats, and Witnesses, and Deacons ... but one of infinite ways you arrange things. Why should there be just one? Why should there be an up-front design at all? A dynamic, emergent network of agents feels like the real opportunity here.

perrygeo··on We’re more patient with AI than with each other
Speaking only of written communication here: I've noticed a distinct trend of people stopping documentation, comments, release notes, etc. intended for human consumption and devoting their writing efforts to building skills, prompts, CLAUDE.md intended for machines.

While my initial reaction was dystopian horror that we're losing our humanity, I feel slightly different after sitting with it for a while.

Ask yourself, how effective was all that effort really? Did any humans actually read and internalize what was written? Or did it just rot in the company wiki? Were we actually communicating effectively with our peers, or just spending lots of time on trying to? Let's not retcon our way to believing the pre-AI days were golden. So much tribal knowledge has been lost, NOT because no one documented it but because no one bothered to read it. Now at least the AI reads it.

perrygeo··on Ask HN: How can we solve the loneliness epidemic?
For me, the loneliest period of my life was when I was socially active but hanging out with people that I didn't really like or respect. Don't neglect spiritual and mental health as a strong component of loneliness. It's not always about dragging your body from one event to another to maximize the number of people in your life. You have to make sure your mind, body and spirit are present and aligned.
perrygeo··on What a Programmer Does (1967) [pdf]
It's remarkable how these papers show a deep understanding of programming 50 years ago. Even with anemic hardware, the limit is always in the programmers brain - as uncomfortable as that is to admit. Half a century of new tech and AI and the cloud etc, we still hit "terminal trauma" fairly quickly in the development cycle, almost like clockwork. All the tools and technical tricks don't seem to matter vs. our ability to hold the application in our heads.
perrygeo··on How much of my observability data is waste?
I don't know what it is about observability that brings out the over-engineering in us. I haven't actually measured it but I suspect many startups doing things the "modern" way (ie logs, distributed traces, metrics, ci/prod/stage/dev environemts etc going to a dozen different services) generate more metadata than actual data. I mean, we need to observe your systems but ultimately that data is a second class citizen to what we're observing in the first place, the application.

At the most absurd, I've seen observability systems replicated across 3 data centers for an application that hadn't been built yet. But don't worry, by the time it was released, they'd have an observability system so good it couldn't fail (narrator: "It did, in fact, fail.")

← PreviousPage 7 of 34Next →