Here's an alternative perspective: https://x.com/rauchg/status/1949197451900158444

Not a professional developer (though Guillermo certainly is) so take this with a huge grain of salt, but I like the idea of an AI "trained" on security vulnerabilities as a second, third and fourth set of eyes!

While I agree with the idea of vetting things, I too get a chuckle when folks jump straight from "we can't trust this unknown code" to "let's trust AI to vet it for us". Done it myself.

They work better in small, well-commented code bases in popular languages. The further you stray from that the less successful they are. That's on top of the quality of your prompt, of course.

> I don't understand how anyone can use LLMs and not see this instantly

Because people in general are not thorough. I've been playing around with Claude Code and before that, Cursor. And both are great tools when targeted correctly. But I've also tried "Vibe" coding with them and it is obvious where people get fooled - it will build a really nice looking shell of a product that appears to be working, but then you step into using it past the surface layer and issues start to show. Most people don't look past the surface layer, and instead keep digging in having the agent build on the crappy foundation, until some time later it all falls apart (And since a lot of these people aren't developers, they have also never heard of source control.)

If you know that LLMs are not thorough going into it, then you can get your failure rates way lower than 50%. Of course if you just paste a product spec into an LLM, it will do a bad job.

If you build an intuition for what kinds of asks an LLM (agent, really) can do well, you can choose to only give it those tasks, and that's where the huge speedups come from.

Don't know what to do about prompt injection, really. But "untrusted code" in the broader sense has always been a risk. If I download and use a library, the author already has free reign of my computer - they don't even need to think about messing with my LLM assistant.

My suggestion is to try CC, use a language like Go, and read their blogs how they use it internally. They are transparent what works and what does not work.

Aka VSCode DevContainer?

Could work I think (be wary of sending .env to the web though)

I tried quite a few of them, including the cheap / free models but the only one that was really working was claude. The others were hanging whenever the model needed a confirmation for action. Mind you, this was some time ago.

200 k is the lowest among any frontier llm

It depends on your usage patterns, presumably.

In my case, I ended up accruing $100/day w/ Claude Code (on github workflows) so Max x20 was an easy decision.

Pro seems targeted at a very different use case. Personally, I’ve never used the chat enough to break even. But someone who uses it several times per day might.

ETA: I get that the benefits transfer between the two, just with different limits. I still think it’s pretty clear which kind of usage each plan is intended for.

Mariosechner post looks very promising.

We may finally get to the devs doing lock-in using ultra complex syntax languages in a much more efficient way using LLMs.

I have already some ideas for some target c++ code to port to C99+.

The todo and porting "programs" are unrelated. The blog post shows the full porting pipeline.

Aider is good at one-shotting Git commits, but requires a human in the loop for a lot of iteration. Claude Code is better at iterating on problems that take multiple tries to get right (which is most problems IMO). I was really impressed by Aider until I started using CC.

Given the vast space of AI research results since the 1950s, I would not say that we dont have transistors yet. Just that we are not applying them.

I am not disputing that it improves the tools. But looking at the entire picture, the whole concept of using LLMs as a general purpose utility is a dead-end. Just the basic arithmetics of it does not add up. If you told your manager you had spent 20,000 dollars on a project, generating a pre-tax revenue of 100 dollars, i.e. creating net loss of 19,900 USD, you'd be fired right away. But somehow the GenAI industry has a similar investment-to-revenue ratio on a much larger scale and still the wishful thinking is in it's fifth year? I get it that people want to get in on the ride but just that having to add so much on top of it, constantly new plugins, tools, concepts, whatever all so that we can avoid seeing this for what it is - building TVs with vaccuum tubes, when what we desparately need are transistors, not improved vaccuum tubes. Just as we did not need faster horses in the era of Ford T-Model.