ako

> I agree, but I think I'm less optimistic than you that Claude will be able to catch its own mistakes in the future. On the other hand, I can definitely see how a ~more intelligent model might be able to catch mistakes on a larger and larger scale.

Claude already does this. Yesterday i asked it why some functionality was slow, it did some research, and then came back with all the right performance numbers, how often certain code was called, and opportunities to cache results to speed up execution. It refactored the code, ran performance tests, and reported the performance improvements.

And who does he sell his software to? Companies that have only 1 employee, don’t need a lot of user licenses for their employees…

What works best for me using Claude Code is to let the CC engineer its own context. You need to provide it with tools that it can use to engineer its context. CC comes with a lot of tools already (grep, sed, curl, etc), but for specific domain you may want to add more, e.g., access to a database, a cms, a parser for a bespoke language, etc.

With these i'll mostly just give it questions: what are some approaches to implement x, what are the pros and cons, what libraries are available to handle x? What data would you need to create x screen, or y report? And then let it google it, or run queries on your data.

I'll have it create markdown documents or skills to persist the insights it comes back with that will be useful in the future.

LLMs are pretty good at plan/do/check/act: create a plan (maybe to run a query to see what tables you have in your database), run the query, understand the output, and then determine the next step.

Your main goal should be to enable the PDCA loop of the LLM through tools you provide.

According to Claude (easy guess from the wikipedia link?):

The book is almost certainly by *Franco Moretti*, who coined the term "distant reading." Given the timeframe ("maybe a decade ago") and the description, it's most likely one of these two:

1. *"Distant Reading"* (2013) — A collection of Moretti's essays that directly takes the concept as its title. This would fit well with "about a decade ago."

2. *"Graphs, Maps, Trees: Abstract Models for Literary History"* (2005) — His earlier and very influential work that laid out the quantitative, computational approach to literary analysis, even if it didn't use "distant reading" as prominently in the title.

Moretti, who founded the Stanford Literary Lab, was the major proponent of the idea that we should analyze literature not just through careful reading of individual canonical texts, but through large-scale computational analysis of hundreds or thousands of works—looking at trends in genre evolution, plot structures, title lengths, and other patterns that only emerge at scale.

Given that the commenter specifically remembers learning the term "distant reading" from the book, my best guess is *"Distant Reading" (2013)*, though "Graphs, Maps, Trees" is also a strong possibility if their memory of "a decade" is approximate.

As a windsurfer, wingfoiler, and kitesurfer i can only say that both Windy.app a nd Windy.com are awesome. Like the ability to compare different models easily.

Thanks, everything was vibe coded, so visualizations thanks to vibe coding. I'm prompting like key user/product manager/architect, so expressing user needs, and ensuring the overall architecture seems reasonable.

For uke, would you expect same functionality but with 4 strings?

Freedom is a scale, not binary. I'm willing to move a bit on that scale to avoid going completely to one of the opposites. I completely disagree with your suggestion that if you don't have complete freedom, you're at the complete opposite end, I.e. zero freedom.

Not the generic concept of TUI sequencers (i know, have used sequencers on c64), but any weird slightly different idea.

In my case i wanted flexible way to display lyrics, chords, strumming, metronome, fingerpicking, scales, chord shapes, etc, with an easy way for LLMs to define the backing-track, so a backing track DSL.

I think we'll see a lot of these very specialized software popping up, instead of generic solutions that contain everything and the kitchen-sink, where you don't use 90% of the functionality.

How do you know the end result is worse than disinformation? If the Russian disinformation allow Russia to destroy the freedom and democracy in Europe, and allow Russia to take over, that seems to me to much worse than limiting the publication of lies and slander.

Nice, the AI enabled Cambrian explosion of software is happening. Any idea can be built and validated in a few hours or days.

I've built something similar, but focused on guitar backing tracks. It's a TUI built using go, with midi output. Backing-tracks: https://github.com/ako/backing-tracks

That statement would benefit from a link to your source.

But the world is better of with the scribes unemployed: ideas get to spread, more people can educate themselves through printed books.

Maybe the world is better off with fewer coders, as more software ideas can materialize into working software faster?

Fixed it with the help of claude, it quickly helped me diagnose the issue and fix it. The drivers for the discrete nvidia graphics card had suspend disabled. Enabling it enabled automatic suspend when closing the lid.

Most people don’t care about gaming, so they shouldn’t care about proton. What changed recently for those who don’t care about gaming?

> This year honestly feels quite stagnant. LLMs are literally technology that can only reproduce the past.

Is this such a big limitation? Most jobs are basically people trained on past knowledge applying it today. No need to generate new knowledge.

And a lot of new knowledge is just combining 2 things from the past in a new way.

Installed it myself, it’s not a system76 but a Lenovo thinkpad.

I have a thinkpad p1 with popos, but it doesn’t sleep properly. Closing the lid causes it to be super active. I have to lay it down up side down so the ventilation gaps are not blocked, otherwise it overheats. Burned one SSD this way.

Better safe than sorry. If the risk is significant, and the impact is big, it is sensible to have plan to address risks. You probably have many expenses you hope you never need, like all sorts of insurances. And even if it turns out climate changes was less impactful than forcasted, change sparks innovation and creates economic opportunity. E.g, these days electrucs cars are better than fossil fuel cars (my wife wont let me lease another fossil fuel car, she likes the way the electric one drives much better), and solar electricity is cheaper than fossil electricity.

It's a shame politicians can't be kept accountable tens of years from now. It would be great that if in 25 years it turns out global warming does indeed cause huge problems for humans, we could sue the politicians that took irresponsible risks with the environment. Now they can just focus on short term gains, and ignore all the long term side effects.

That is why the argument is not against guns per se, but against human access to guns. Gun laws aim to limit access to guns. Problems only start when humans have guns. Some for AI, maybe we should limit human access to AI.

2 days of vibe coding: https://github.com/ako/backing-tracks

Full vibe coded project: https://github.com/ako/backing-tracks

There’s a ton of difference provided on top of the LLMs, especially the tools that allow LLMs to engineer their own context, validate generated code, test generate code, research code bases, planners, memory, skills, etc. The difference is night and day: like a brain in a closed jar versus a brain in a mobile human with eyes, ears, mouth and hands.

I had a conversation with Claude code 2 weeks ago where it mentioned early support for LSP had been added into Claude code. Have been working on a LSP for a custom language since then.

Sure, for something big code needs more review and validation. But this is just a small command line tool that allows you to ask an LLM to generate a DSL to play a backing track: https://raw.githubusercontent.com/ako/backing-tracks/refs/he...

Not a big commitment from a user, and nothing lost if it doesn´t work as hoped.

I'm just positively surprised how quickly you can create a prototype for these sorts of ideas with Claude Code. This is literally just a few hours of vibe-coding.

It's not like this is very unique, YouTube has tons of training and backing track videos, which is what i typically use. And artist don't sell it in a way that can be consumed for guitar practice easily.

Yes, I noticed that Claude Code silently refused to generate lyrics for some songs i requested. Benefit of this approach is that anybody can quickly generate a YAML file for a backing track, no need to share it anywhere.

Yesterday i used Claude Code to define and implement a YAML based DSL for playing backing tracks. I can ask an LLM to generate this DSL for any well known song, and it will include chord progression, lyrics, bass, drums, strumming pattern, etc. It's a go command line tool that plays the DSL via midi, and displays the chords, strumming patterns, and lyrics. Also does export to Strudel.

Skills don’t solve the problem if you think an llm should know everything. But if you see LLMs mostly as a text plan-do-check-act machine that can process input text, generate output text, and can create plans how to create more knowledge and validate the output, without knowing everything upfront, skills are perfectly fine solution.

The value of standardizing skills is that the skills you define work with any agentic tool. Doesn't matter how simple they are, if they dont work easily, they have no use.

You need a practical and efficient way to give the llm your context. Just like every organization has its own standards, best practices, architectures that should be documented, as new developers do not know this upfront, LLMs also need your context.

An llm is not an all knowing brain, but it’s a plan-do-check-act text processing machine.

Replacing workers has been going on for many years, just ask mineworkers, factory employees, and many other workers. It seems that here on hackernews we're happy if this happens when it bring down prices and doesn't impact our jobs. But once it starts effecting software engineers it's the end of the world?

I do see and agree with the dangers of AI, but it would have been a bit less selfish if we'd been this concerned when other jobs got replaced by automation.