lackoftactics

I think this is one of the most popular patterns seen nowadays. We approach problems that we didn't before because they were absurdly stupid and touched so many places that it seemed risky, hacky, costed too much time. It would be nice to go back to simpler problem solving and saying no to things that extend team skills

I don’t believe they are better at Ruby. Agents got better overall and people draw bad conclusions from their anecdotal evidence. Ruby on Rails is mostly DHH cult with people praising Ruby as poetry.

This is coming from someone working 13 years as Ruby dev. I love the language, but I want to be honest that I didn’t had experience with other languages before and seeing statically typed languages (Java, TypeScript), Elixir opened my mind to the amount of cargo cult inside Ruby community stemming mostly from people limited to knowing only 1 language.

Those are strong claims and I think we need better evidence to support it. Most of the backend frameworks are batteries included to extent like Django, Laravel, Phoenix. Also many decisions made by Rails team are quite debatable, hotwire and getting rid of TypeScript being top ones recently.

Tbh we need to do some real research about it, because all those articles are just feelings that it seems to work better. But mostly it feels better, because we got stronger models and improved agent harnesses

I had so much bad experience with their dedicated app, consuming 1GB of memory being just one of them

It reminds of Fun with Flags segments in Big Bang Theory

That could be true for novel problems from Deep Tech industries and not everybody can solve those.

If you are doing another app, the product experience and marketing will probably win. Many companies with better products lost, beaten to death example is Betamax

That’s interesting there was creativity experiment results proving that could be true.

https://austinkleon.com/2020/12/10/quantity-leads-to-quality...

I showed some old Olga Tokarczuk essays to my friends to pick what was ai slop and what was not as experiment, pre- 2020 ones from Czuły Narrator to be exact. Guess what, they picked the ai one as human and her as most ai. Maybe because she uses a lot of big words and em dashes.

We are at the point, when there is too much cognitive energy needed to discern writing from human, human ai assisted and all ai. Should we know make mistakes on purpose to avoid being labelled as ai slop? :)

I guess it's dating app fatigue makes us promote old articles :)

Fun fact, I learned yesterday that Bumble will delete swipes in their upcoming app reset and go ai assistant way. Not that that I am fan of dating apps, it's one of the worse inventions ever, but seems pretty interesting seeing their stock price plummeted 93% since IPO

as much as I love analogy with humans using super-shoes, not everybody can be a world-class expert in their industry. There should be a place at the table for average people to take part; otherwise, it won't be sustainable.

As a programmer, I am mostly interested in whether my role is sustainable long-term and whether the models will get better. I don't feel in jeopardy yet, but two more years like this and the calculus of hiring software engineers could shift even further. QAs are already overwhelmed with work

Yep, he is a PR stunt guy, and the number of videos that come up when you type Ed Zitron into YouTube should tell you how many people are eager to feed their cognitive biases.

My thoughts too. The LLMs made me understand that the world had been working like that long before LLMs. Luck plays an enormous part in life. We gravitated toward a discipline that seemed free of all those problems, when in fact it had those downfalls better disguised.

rant first: oh, I recently heard about you from a friend working in a company after I mentioned that I also got into photography. Nice work on pixelpeeper.com

to the article: Yeah, it's different world out there. We need to filter ideas instead of focusing on more features, as lack of staggering revenue growth suggests it might be that more doesn't equal better. The stability of apps is getting worse lately. I couldn't pair my sony camera and it was stuck on pairing screen :(

Not only buggier, but less usable overall. We can not blame everything on AI. For example events discovery platforms and ticket platforms were way better decade ago, you could search by popularity, friends going to the same event and there wasn’t as much fragmentation. That part you could blame on Cambridge Analytica scandal and late capitalism love of algorithmic feeds

also the conseqeunces of implementing it badly from scratch don't make sense if you can use battle-tested solution

It's one of those things you shouldn't trust LLMs to such an extent; that part should be very solid because the consequences of bad practices are getting to front page of hacker news :)

There was a recent interview with Dax Raad on the Pragmatic Programmer podcast, and they talked briefly about it. We would like a future where we do just a bit more work and are happier with legacy codebases or work on getting rid of tech debt, but that definitely won't be something our employers are interested in.

other thing could be also true, if you are great developer who spent decade honing their craft (vim, working on hobby projects, grinding when your friends party) you would hold cognitive bias against it as it flips the script. I don't think our profession is going away, but the shift is happening and it's not very comfortable one.

definitely hard to beat Bun at the moment, the live reload is crazy good

they introduced static typing (Sorbet) to avoid problems, it's completely different app and looks nowhere close to what you experience in standard Rails app

Why do you think that follows?

I was on team dynamic typing for about 12 years, and Ruby was a big part of that. I still think dynamic languages can be wonderful to read and write.

But after using modern statically typed languages with good inference, I changed my mind. Many of my old objections were really objections to verbose type systems, not static typing itself. With inference, you can keep a lot of the readability while gaining safer refactoring, better tooling, and earlier feedback.

That doesn’t mean dynamic languages can’t produce high-quality software. They obviously can. But I don’t think appreciating modern static typing is just evangelism.

And yes, I understand what this library is about, it's for "beautiful" easy to use interface to AI providers for Ruby apps. It's the popular play nowadays with litellm, bifrost, gomodel and vercel gateway. We have at least couple AI gateways, libraries like that every week on HN.

Even as rails dev, I am seeing that you might be right. It’s really hard to find specific pros nowadays that Ruby brings to the table. All that talk about conventions over configurations and vast presence of Rails in weights is fun, but if writing speed isn’t an issue anymore, then Ruby on Rails has serious problems with larger codebases

there are only limited number of patterns for ui,ux, CTA. It sucks to be stolen from, but we build on top of each other most of the time

Two questions.

How do you handle the competition like https://github.com/ENTERPILOT/GOModel and Bifrost? They already moved to more performant languages like Go.

What is the moat of litellm currently and why such a radical move?

And the effort to produce valid benchmarks is tremendous. You are probably right and that’s very annoying. We already had flame wars over frameworks and this is way worse, your vibes vs. my vibes. Who would thought non-deterministic outputs would lead us here?

Thanks for the link! I thought I know every obscure law and I was so wrong.

Looked at your repo, even starred. On the surface, I like your approach a bit better. It looks like your idea sits at the space between semantic search and compressing tokens. I was into semantic search before, but mostly trying to vectorize codebase instead of tree sitter and couldn’t make the semantic search work for me. Thanks for sharing!

1. Are you sure no one is fooled? It’s the main thing managers are praising rtk for and using as an argument for it’s validity. If this is gamed, then it paints a very different picture. 2. No, I didn’t vet all the reports. But they paint quite convincing picture of the problems present in the library, which has a very ambitious goals of handling every popular command and making it less verbose. 3. You know this is not a valid point. Engineers tanking performance and choosing based on hype is nothing new. Github stars and usage is not a valid argument, when the tool is not very transparent and could quietly fail. If it’s only couple percents less accuracy, most wouldn’t easily recognize it with the whole stack of skills, mcps and agents.md 4. Is it something more than a feature? If the benefit is $3 on $900 as other commenter pointed out using maybe better and well researched article than mine from codepointer, why would I risk that for all the possible bugs and worse accuracy. 5. Hard to address this one. Tough problem domain to handle with endless cli commands to capture and process properly.

Congratulations on your accepted PR. I didn’t want to make you grumpy today. If you feel I am wrong, it’s very possible. I am just a guy who wrote my point of view, it doesn’t automatically make it valid. Once again sorry for making you grumpy.

As an author of the text, I can say you are „absolutely” not correct. I might be already spending too much time with llms and they start to shape my texts, so I am not proud of that either. But thanks for bringing very valuable insight to otherwise interesting discussion.

Tbh I could buy into what you are proposing more than rtk. It feels sane in comparison