stillpointlab

I get the joke, but none of the offered prompts are close to how I speak with coding agents. I felt like I was being forced to feed garbage into the machine and then I'm supposed to act surprised when garbage came out.

I'm surprised I haven't seen this called out more directly and more often. This is a frequent error state.

And not just backwards compatibility, but migration scripts and all of the testing and machinery around it. I'll literally add feature A, merge it, then add feature B and it is like "oh no, we'll have to fix up and migrate all of the users using feature A".

The other problem is anchoring on an old implementation. I was working with Fable on a change to a core system and it pointed out a difficult failure edge case. It is something that can go wrong in extremely unlikely scenarios but the consequence would be short-term data loss (basically a non-durable intermediate cache being overwritten in a race before a flush to durable storage). It is very hard in these circumstances to get Fable to switch from "how to patch this given the existing implementation" to "how to prevent this with a more robust implementation".

These are both cases where the model seems to over-index on what is already there instead of considering what a first-principles approach would look like. A good engineer does both and then costs them side by side, because a first-principles approach can often be less work than patching what is already there.

Note: Incident Command is almost certain an allusion (or implementation) of the Incident Command System [1]

It is a common system in all kinds of emergency response scenarios, including local emergency services (fire/police/ambulance) and it scales all the way to massive disasters.

It is especially useful to clarify command structures when multiple response entities need to coordinate. That is true even within organizations like public companies, where the reporting structures may be distinct.

1. https://en.wikipedia.org/wiki/Incident_Command_System

> superintelligence is, like rocket fuel, an extremely powerful force that has a default tendency to break containment and go boom

what evidence do we have this is the case?

To experiment. Given the availability of new tools there is opportunity to try new things.

I didn't try Sublime on the same machine so I can't compare. Kate is less polished but genuinely a good choice if someone wants FOSS.

I would have no qualms recommending either.

Very few features on purpose. Every editor I tested had all the features I added and more.

It is worth noting that KTextEditor is a fully-featured library. Like, line numbers+gutter (for eventual git status icons), undo/redo, save, warn on exit for unsaved changes, syntax highlighting, color theming. It does 95% of what we'd all call "editing". But it doesn't do things like tab interface, project explorer, terminal pane, output windows, etc.

What the library didn't have were LSP features, of which I only implemented a few (error squiggles under things that fail the type check, go to definition). Notable absent are completions and hover features for things like help. I also only added (and tested) LSP servers for typescript, Rust and Go.

My plan has been: do as little as possible until I need something, then ask Fable to add it.

edit: I guess one thing I added I didn't see everywhere else was a built-in Markdown preview. But many editors have that (VSCode definitely does) so it isn't special.

No shade on keeping using what is working. I was moving from Windows to Linux Fedora so I was in the market for a new editor. VSCode just wasn't working for me any more.

I considered a bunch of options, including vim or neovim or lazyvim, emacs, newer projects like zed. LLM gave a few more I can't recall including helix and Kate. There are so many good options these days, we're all spoiled for choice.

But the main thing is, and YMMV, I am not writing a lot of code anymore. I'm mostly reading/searching/navigating. So all of the powerful editing features are lost on me. No editors really match my current workflow, they all have too much.

So this was an opportunity to try something out, to experiment. See if I could do the real-deal vibe coding thing and judge the result. I just said "I want it to do ..." and then a few minutes later it did. I repeated this until it did enough to use as my primary editor.

I don't recommend it for anyone else, nor do I expect people to agree. Just describing my thought process.

I was planning to. It is 100% vibe coded, the first project I did that way. I'm one of those who've been reading all the code in my major projects. But when I got frustrated with editors and off-handed mentioned to Fable something like "I like Kate, but it has way too many option I will never use" it told me that the core part could be wrapped pretty easily (like 50 lines of C++).

So I just said "do it" and have been merging everything without reading a single line. It wrote all the specs, wrote all the code, wrote all the tests. I just got it to write out a tutorial to take me on a tour of the code it wrote, but I haven't reviewed it yet.

I will push it as OSS once I've made sure it hasn't included anything that I don't want public. But it wouldn't be super useable for anyone else since many of the features (e.g fuzzel and broot) are glue that exists in the Sway configs and some helper scripts.

It's held together by bubble gum and scotch tape. But is does exactly what I want and so far without a single bug, crash or problem. It's my frankenstien editor and I love it. (disclosure: I've been using it for less than a week)

I literally just got Fable to write me a text editor. Well, I'll be honest, I got it to wrap the KDE KTextEditor library which is like 90% of a text editor.

I had been using Kate which was what an LLM suggested was the closest to something like Sublime Text on Fedora. But even Kate, which was great, had too much going on.

So I asked Fable to take the text editor part (KTextEditor) and wrap it using Rust with an LSP server. It took about 2 days but I have a tiny, super fast little editor. I use Sway to manage things like tabs, fuzzel stands in for fuzzy file search, broot stands in for an explorer view. I've already added Markdown preview support. I might get around to some basic git integration.

Then I got it to turn that little editor into a note-taking interface that I have bound to a Mod-m key binding to keep notes in ~/Notes.

We live in wild times. I hope everyone is taking advantage while they can.

> I now see relationships as their own domain rather than an attribute attached to a contact

I mostly skimmed this announcement, but this seems pretty obvious to me? Relationships form a graph, so it seems reasonable to use graph modeling techniques to handle them. At the least RDF triple style [1].

One thing I'd also strongly consider, in this age of LLMs, is how much you can store in text. A personal CRM seems like the kind of thing I want to check in to github, rather than deal with Postgres or even SQLite. And if you have a good structured text format (e.g. Markdown with YAML frontmatter, XML, json) then you can just point an agent at a repo and extract information that the app developer didn't even expect or add APIs for. Same for transformations. A full db engine is then more a performance optimization that can be applied for app-specific functionality.

1. https://en.wikipedia.org/wiki/Semantic_triple

My only concern is that sooner or later the best models will be priced out of my ability to pay.

I have been happy with Fable 5, it has done great work for me so far. Very excited to try out Fable 5.1 and see what differences and improvements there are.

I didn't see it anywhere on their announcements, but when I restarted Claude (on a Claude Max account) I see the model is now Fable 5.1

I've heard it said that true understanding is demonstrated when someone can explain difficult concepts well. Tao manages to convey complex ideas without making me feel like he is condescending to me. His depth of understanding is unmistakable.

My changes to his list would be s/Geometry/Topology/ and I might have found a place for logic and type theory. I am especially glad he brought to mind Dynamics since that is a field I know I need to pay more attention to.

Great video, we're lucky to have this kind of content so easily and widely available.

I've been using Firefox as my main browser since I switched from Windows to Linux.

No real complaints so far, haven't really noticed any difference from Chrome to be honest which is about as good a recommendation as I could give. It does chew up memory but so did Chrome I guess, I haven't done a head-to-head comparison.

Also, they can literally train the LLM inside the VM they create so it becomes an expert in whatever tools are there. And since they control the entire sandbox, less permission issues are likely.

I think they will become extremely vertical integrated sooner or later because that will be the most efficient and effective way to do this. I'm guessing anyone building this kind of thing now has only one hope: acquisition.

Thank you, those were very helpful backgrounds on the situation in Fedora. I suspect it will take some time for their community process to digest and it suggests there is no explicit ruling at this time.

But I would still love a page that was basically a table of distro, decision status, decision, etc. so that anyone interested could make an informed choice without having to scour forums, wikis, mailing lists, chats, etc. for each and every distro

I try not to think in black/white, good/evil kinds of terms. I think of forces and dynamic systems.

There appears to be some force that promotes one particular way of thinking, perhaps the inevitable consequence of accumulated experiences. In the case of cynicism, the balance tends to shift towards one side of a scale over time.

Without a countervailing force on the other side it can tip a normally balanced system out of stable equilibrium.

My point is explicitly: the world provides the force in one direction, and the individual must provide the force in the other.

"Human understanding" is not yet an objectively quantifiable metric that can be applied to code change sets. As it would only ever be self-reported (a claim made by a user submitting to a repo), I see little to no value in it.

One thing people go through as they age is an elevation of cynicism and general misanthropy. After decades of being disappointed when naive idealism and speculative optimism fail, one can just get down on it all.

It is really hard not to succumb to this. It requires active effort and sometimes even a willful ignorance. "turn a blind eye" is the idiom here. Monty Python's "Always look on the bright side of life" kind of thing.

Mr Rogers said it: look for the helpers. They may be few, but they are there. Find them and focus on them.

Is anyone tracking how the different distros are coming down on the question?

I was curious how Fedora is moving on this question, but I don't know where to look. And if one wants to hop distro either towards or away from AI, it would be nice to have a place to see the relative adoption.

Linux distros are the perfect place to have a wide marketplace of options to suit every person, from completely anti-AI to completely YOLO vibe-code.

I think 10 levels here is too much and hints that someone anchored on 10 as a round number and then forced the levels to fit after the fact.

I don't really see much value beyond the 3 levels of AI disclosure that have been floating around:

- fully human - ai assisted - ai generated

What doesn't follow? Who said we should repeal section 230? Or to do so without replacing it?

Not me, I said I was ambivalent about it; don't put words in my mouth. My words were: "there would have to be some similar provision [to KYC]". Similar, not the same. Not nothing.

Everything else sounds like you imagining/speculating about what some future provision would look like. And your imagined fears don't play into my ambivalence.

You are mostly right about my ambivalence (re: liability) but wrong about the conclusion.

> no website could accept user content, ever, and you are effectively suggesting the end of public communication on the internet?

That does not follow. Just like financial services are forced to KYC, there would have to be some similar provision. For example, a site might choose not to have anonymization and then liability passes through a KYC chain. If a site wanted anonymous then the burden would be on moderation before it became public. I think this probably already happens in large extent where images are scanned to avoid bad things appearing on public sites and there is already liability around that.

I know that isn't a popular position. It would change the entire character of the Internet. And it couldn't just be thrust upon people since the current contract is one of promised anonymity (even if that is probably not true wrt state actors).

I believe there is a double standard here compared to section 230 of the communications act.

Platforms can't be held liable for speech on their platforms for a reason. For full disclosure: I feel ambivalent about that.

I don't know of an equivalent legal protection for I2P-like infrastructure.

I suppose it is a question of balance between: the entire web being better for all those that require accessibility vs. a subsection of that community holding their jobs. And it raises the possibility that the increased accessibility could lead to more job opportunities.

But I'm not really a consequentialist and think of things in virtue ethics terms. And using technology to scale benefits to a wider group of people doesn't conflict for me. YMMV.

The state of affairs in the last 6 months bears almost no resemblance to the state of affairs in the last decade.

No need to apologize, neither of us can predict the future. I am optimistic Fable-level models can succeed where the old not-actually-AI models failed. No shame in being pessimistic about the same.

I think people outside of enterprise have no idea the cost to audit and fix a massive website.

The law is a forcing function here. Lawsuits can and do happen when sites of a certain size fail to implement government-mandated laws. This is a good thing, IMO, but it only comes into force in the largest cases.

If there is a credible path to 1/10th the cost (while still providing liability insurance which is a critical piece) then that will likely encourage more enterprise to do it proactively, and will open the door for startups and mid-sized companies.

I have no idea why anyone would choose to see this as bad.

I believe AI can be huge here. Things like ADA are often mechanical (adding the correct attributes to the most important page elements). It is the perfect work to audit and fix using agents.

It is a business opportunity as well. I worked at a company that paid for an audit before LLMs. There is tremendous cost savings possible here.

I also wonder if WebMCP will be the ultimate final incarnation of this.

Having a SotA model do that sounds expensive. Who is paying for that?

I think if OSS maintainers start pushing that financial burden out to potential contributors then there will be a big outcry.

OSS may become pay-to-play.