451–460 of 634 posts
I've been listening to the insane 100x productivity gains you all are getting with AI and "this new crazy model is a real game changer" for a few years now, I think it's about time I asked: Can you guys point me ton a single useful, majority LLM-written, preferably reliable, program that solves a non-trivial problem that hasn't been solved before a bunch of times in publicly available code?
Earlier quoted context omitted.
I'm personally 100% convinced of the opposite, that it's a waste of time to steer them. we know now that agentic loops can converge given the proper framing and self-reflectiveness tools.
Maybe some day, but as a claude code user it makes enough pretty serious screw ups, even with a very clearly defined plan, that I review everything it produces. You might be able to get away without the review step for a bit, but eventually (and not long) you will be bitten.
Every mistake is a chance to fix the system so that mistake is less likely or impossible.
I rarely fix anything in real time - you review, see issues, fix them in the spec, reset the branch back to zero and try again. Generally, the spec is the part I develop interactively, and then set it loose to go crazy.
This feels, initially, incredibly painful. You're no longer developing software, you're doing therapy for robots. But it delivers enormous compounding gains, and you can use your agent to do significant parts of it for you.
Earlier quoted context omitted.
More importantly, this is the early steps of a model self improving itself. Do we still think we'll have soft take off?
Exponential growth may look like a very slow increase at first, but it's still exponential growth.
(= it might take an order of magnitude of improvements to be perceived as a substantial upgrade)
So the perceived rate of change might be linear.
It's definitely true for some things such as wealth:
- $2000 is a lot of you have $1000.
- It's a substantial improvement of you have $10000.
- It's not a lot you have $1m
- It does not matter if you have $1b
Earlier quoted context omitted.
Exponential growth may look like a very slow increase at first, but it's still exponential growth.
Sigmoids may look like exponential growth at first, until they saturate. Early growth alone cannot distinguish between them.
Earlier quoted context omitted.
When using it in VSCode? The browser system running its own container seems like it would be the most demanding on their resources. The stand-alone client is Mac-only but I don't know if it makes a difference. My goal is to do it within the usage I get from a $20 monthly plan.
Why would you use it in VSCode? OpenAI are offering double the normal usage limits for Codex for two months. Go with them and do it in the terminal or the Mac OS codex app if you have a Mac.
Earlier quoted context omitted.
Only people who haven't had a secretary would think it's a personal secretary. Like, it can't even answer the phone.
There are plenty of companies that sell an AI assistant that answers the phone as a service, they just aren't named OpenAI or Anthropic. They'll let callers book an appointment onto your calendar, even!
I'm sure there are research demos in big companies, I'm sure some AI bro has done this with the Twilio API, but no one is seriously doing this.
All it takes is one "can you take this to the post office", the simplest, of requests, and you're in a dead end of at best refusal, but more likely role-play.
Whats interesting to me is that these gpt-5.3 and opus-4.6 are diverging philosophically and really in the same way that actual engineers and orgs have diverged philosophically With Codex (5.3), the framing is an interactive collaborator: you steer it mid-execution, stay in the loop, course-correct as it works. With Opus 4.6, the emphasis is the opposite: a more autonomous, agentic, thoughtful system that plans deepl…
Earlier quoted context omitted.
I'm personally 100% convinced of the opposite, that it's a waste of time to steer them. we know now that agentic loops can converge given the proper framing and self-reflectiveness tools.
> it's a waste of time to steer them It's not a waste of time, it's a responsibility. All things need steering, even humans -- there's only so much precision that can be extrapolated from prompts, and as the tasks get bigger, small deviations can turn into very large mistakes. There's a balance to strike between micro-management and no steering at all.
Anthropic mostly had an advantage in speed. It feels like with a 25% increase in speed with Codex 5.3, they are now losing that advantage as well.
I just asked Opus 4.6 to debug a bug in my current changes and it went for 20 minutes before I interrupted it. Take that as you will.
I want to recompile a Rust project to be f32 instead of f64. Am I better off buying 1 month of Codex, Claude, or Antigravity? I want to have the agent continuesly recompile and fix compile errors on loop until all the bugs from switching to f32 are gone.