am17an

Asymptotically, prompting is a programming language.

> Perhaps you meant to say “UNhelpful”?

Yes, thanks for pointing it out!

In the future there will be safe havens where LLM generated code has not been merged. It will marketed as “hand-crafted” by Romanian programmers or something like that, akin to Swiss watches. It will be extremely high quality, but too expensive to mass produce.

There's going to a wrapper around github PRs to summarize these issues, the mess they created in the first place. BTW this is the same guy which has famously stopped hiring engineers

Another quirk inserting random whitespace when generating code. Seem to be tokens for different lengths of whitespace

Typically you want to measure both things - time it takes to send an order and time it takes to calculate the decision to send an order. Both are important choke points, one for latency and the other for throughput (in case of busy markets, you can spend a lot of time deciding to send an order, creating backpressure)

The other thing is that L1/L2 switches provide this functionality, of taking switch timestamps and marking them, which is the true test of e2e latency without any clock drift etc.

Also, fast code is actually really really hard, you just to create the right test harness once

One thing I despise about LLMs is transferring the cognitive load to a machine. It’s just another form of tech debt. And you have repay it pretty fast as the project grows.

I'm not arguing which model is better for your use-case. I'm saying in general as it's "powerful" as GPT 4.1 in a lot of benchmarks, and you can peak underneath the hood, even make it better for your said use-case

Deepseek-R1 is at the level of GPT 4.1 already, it's open-weight, open-source and they even open-sourced their inference code.

I actually don't understand how you can offload the instruction pointer of the program to another program, permanently. How are you accountable for anything then? You can't debug, you can't program, just a tourist in your own home. Own your code, even if AI wrote it.

You get CC when you sign up for their $20 plan also.

With all the tools around, I think I've maybe become 20% more productive, but 50% less happy in arguing and babysitting the LLMs.

Do indoor HIIT 20 minutes a day, and find a better way to eat. Your post seems like you the very little mental fortitude to change tbh.

All the world's smartest minds are racing towards replacing themselves. As programmers, we should take note and see where the wind is blowing. At least don't discard the possibility and rather be prepared for the future. Not to sound like a tin-foil hat but odds of achieving something like this increase by the day.

In the long term (post AGI), the only safe white-collar jobs would be those built on data which is not public i.e. extremely proprietary (e.g. Defense, Finance) and even those will rely heavily on customized AIs.

This book seemed like a labor of love before I read this blog post. Now it seems just more so. Thank you Robert, I wrote my interpreter in C++ and learned so much about the language through my tiny Lox (I've been writing C++ for 8 years now :))

I really want to just play with this tech- it’s frightening but also the future, but I’m still waiting to be accepted on the GitHub copilot waitlist. I wonder how long this will take for people who don’t know someone who knows someone…

I'd love to see what Richard has to say about this.

Yeah, that's true. But you can limit the secret key to an IAM user with only perms to uploading to that particular bucket. I know it can still cause damage, but nothing like disclosing your root key. If you do a cost-analysis taking into account development on the back-end, doesn't seem so bad, till of course, it does.

> I think a lot of competitive advantage of Google/Facebook in ML is because they have staffed their engineering with people who have studied these things for years (by PhD).

This is not entirely true. Most of their advantage comes from the corpus of data. Of course, I'm not discounting the fact that they're pioneers in the field, but at this stage data is their competitive advantage (hence they open sourced Tensorflow.)

I feel the present state of ML libraries or even distributed system libraries not being a black-box solution and not the "just works" type is a growing pain, and will be evolve into something more accessible/robust in the future. The whole point of it being a "layer of abstraction" is that you don't need to know the details.