Hacker Newsnew | past | comments | ask | show | jobs | submit | dimgl's commentslogin

Oh my God, I thought I was the only one who remembered this game!

Why is it mean? The author is above critique?

No, but the author seems to be above being critiqued for supposedly not even knowing of the existence of the field.

Considering that he is a somewhat well known expert in the field who has been doing full time research on it for a decade.


https://scholar.google.com/citations?user=ZLnQcAsAAAAJ&hl=en This is not the google scholar of a well-known expert, I'm sorry.

It’s like saying Linus Torvalds isn’t an expert on the Linux kernel

While that might not be the largest academic footprint, I don't think you could dispute him being an expert or being 'somewhat well known'.

He seems to have a big following on AI-hype twitter, I'll grant you that.

It is interesting however, how you weren't familiar with him at all [1] 20 minutes before describing him as a well-known expert.

[1] https://news.ycombinator.com/item?id=49753179#49754358


What's interesting about it?

I looked it up, and he seems to have worked on research in that area for a decade.

The author of the blog post could have checked the same before making the claims.


There are countless people with essentially no domain knowledge to speak of after working on the domain for a decade.

I have no idea how the original authors competency is, I know nothing about them.

There is however a strong correlation between people being influencers and kinda mediocre at what they're an influencer in - which is frankly understandable, because a large part of their skillset is usually more towards attracting an audience and making the topic interesting.

Usually the true domain experts rarely interface with the public beyond their professional capacity.


Has nothing to do with AI-hype. Anyone who is interested in Lambda calculus should find his work intriguing.

Someone can be a well-known expert in a tiny niche field, and one may be completely unaware of them, or even the whole field.

You are splitting hairs for no reason, while standing on the wrong side of this discussion.

Feel free to criticize the project on its actual content.


https://scholar.google.com/citations?view_op=search_authors&... Is this?

Or perhaps a Google Scholar means jack shit? Since when is that the official measure of an expert.


What has Victor Taelin made which is any way comparable to Linus Torvalds? I'm not saying it's impossible to be a well-known expert with a shitty google scholar. I'm just not seeing any evidence at all in Taelin's case. He doesn't even have a wikipedia page!

You have a very strange definition of expert. Most people do not have a Wikipedia page, and most experts do not have a Wikipedia page.

Muh academic ivory tower

I found the post offputting because he is insinuating a few things about the author which are clearly untrue (eg, unfamiliar with the formal verification landscape) and he's using this untrue speculation as evidence of the dangers of vibe coding. Even the edit where he says swap it out with a hypothetical person who fits the description - it's still leaving in the untrue claims about the author.

It doesn't seem unreasonable to think it mean if I were to make up speculative negative assumptions about you which undermined something you've been working hard on for a long period of time.

I know nothing about the author, I'm just watching this whole spectacle unfold.


It’s a poorly researched article just looking for cheapshots.

It is mean for the last point I mentioned: Taelin is very transpparent about his work which makes it easy to attack him. And what for? This post is not even a proper criticism of Bend 2, it is just trying to paint some story that Taelim is a vinecoder who does not know what he is doing, based on no evidence. If he was not transparent it would not even be known that LLMs have been used.

Because this shitty blogs' author just called someone "vibe-coding a language with no knowledge about the field" who is literally working in that very field for a decade, long predating LLMs, with numerous high-profile works.

You are on the wrong side of this whole discussion, there is only one people here who needs calling out and it's not Bend's author.


I found 5.6 Sol to be extremely underwhelming.

I think this whole "that half" and "this half" thing makes it significantly harder to hold people in the government accountable. I know plenty of conservative people who think the corruption in the government is out of control.


Do they act on their beliefs or merely parrot them?

I ask because I've known people who were shocked at what took place 2021-01-06 but who proudly voted to re-elect Trump.

Today isn't much different: talk to a conservative voter who complains about the tariffs, Iran war, etc. and ask them whether it would be enough for them to vote Democrat, and the answer is near universally no. Lots of people have performative outrage because they're supposed to be outraged at what's going on, but the truth is that there's no line the Republican party can cross which would make them switch votes. Exceptions to this rule are still few and far between as far as I can gather.


Elections are won and lost by the people who don't vote so not voting for Trump still counts as a win.

Most politics is sold as tribal. "Our leader" and "Our team" are not the same thing. If "Our leader" is a disappointment, "Our team" can still be the good guys who need to do some house clearing, introduce some fresh blood, and all will be well again, etc.

Reality in the US is most politics is billionaire-funded. Trump didn't just happen, and he certainly didn't pull himself into the top job through his own efforts. He was groomed for decades before being crowned.

That's the level of corruption most of the population never sees. It's why the establishment is so scared of wildcard politicians and the DSA as a movement - both threaten to snip the strings of corporate funding.

As long as those strings are there, what happens in the media is kayfabe. The real decisions are made elsewhere, and the big tentpole events - 9/11 and its aftermath, the various Middle Eastern wars, financial crashes and bailouts - are the special menu the rich get to feed off, and the public never sees in advance, never mind votes on.


Do those conservative people keep voting for Trump? Will they support his blatantly unconstitutional third term run? If so I think we need more words for nuances around what conservatism has come to mean.


Do you really think he'll bother running for a third term when all he needs to do is declare the election results invalid and stay in office?


I'm sad to say I don't feel like I have a good handle on what is going to happen in the near future. Between the ongoing daily "flood the zone" from the administration and how fast AI is moving I have no idea what happens even a few months out from here.

Do I think he will run? I don't know - he said he wants to, regardless of constitution, and I think he would love the vanity of it if he was sure to win. They've done a lot of work to be able to suppress votes, throw out mail in votes, and declare the election invalid, plus the legislature seems inexplicably spineless, so I don't know if he would run again or not. Anything but release the epstein files I guess?


I'm currently working on a harness and I just integrated Antigravity support through `agy`. I can't risk my main Google account getting banned so it looks like I'll be stopping this immediately. Yikes... and I was feeling good about 3.8 Flash too...


OpenCode is a good harness that works with every token vendor


Err... the harness I'm building works just fine with Google APIs.


It sounded closer to Scion, which wraps the various harnesses. Given your reply, I'm not sure where your project sits in the stack or what you mean by `agy` support in another harness


I'll use both Muse Spark and Grok.


Switched to Arch Linux with GNOME. Whenever an issue comes up, I have an AI agent look into it and it gets done. Worth it to get off of Windows.


Yep. I have not yet had a single good experience with Sol or the 5.6 models on a variety of harnesses and configurations. It overthinks, overcomplicates and often makes my code into an unmaintainable sludge. It'll usually take 5+ turns of steering to get it in the right direction.


Why not?


Because it’s good on benchmarks but not on real usage?


But OP said they've never used it. How would they know?


Congratulations: now only AI can iterate on your codebase!


Even the AI degrades as the codebase gets shittier


Degrades? Nonsense. Sounds like you need the latest model and more tokens.


That’s probably not completely true, but it’s approximately true.


Guidelines | FAQ | Lists | API | Security | Legal | Apply to YC | Contact

Search: