A non-technical client of mine has built an entire app with a very large feature set with Opus. I declined to work on it to clean it up, I was afraid it would have been impossible and too much risk. I think we are at a level where it can build and auto-correct its mistakes, but the code is still slop and kind of dangerous to put in production. If you care about the most basic security.
I'm late to the party and I'm just getting started with Antrophic models. I have been finding Sonnet decent enough, but it seems to have trouble naming variables correctly (it's not just that most names are poor and undescriptive, sometimes it names it wrong, confusing) or sometimes unnecessarily declaring, re-declaring variables, encoding, decoding, rather than using the value that's already there etc. Is Opus better at this?
> Mostly I’m just there to press the big “I’m accountable” button on the screen
This is going to be way harder now vs. when we used to write the code ourselves. In contracting space, the problem now is that you may have a client that vibe coded an app and be very out of touch about the costs involved to have a developer approve it. It's going to be a hard sell, when the client builds the entire thing themselves and you are a mare peasant doing QA review.
I'm using it via Copilot, now considering to also try Open Code (with Copilot license). I don't know if it's as good as Claude Code, but it's pretty good. You get 100 Sonnet requests or 33 Opus request in the subscription per month ($20 business plan) + some less powerful models have no limits (i.e. GPT 4.1), while extra Sonnet request is $0.04 and Opus $0.12, so another $20 buys 250 Sonnet requests + 83 Opus requests. This works for me better since I do not code all day, every single day. Also a request is a request, so it does not matter if it's just a plain edit task or an agent request, it costs the same.
Btw. I trust Microsoft / GitHub to not train on my data more (with the Business license) than I would trust Antrophic.
> Why isn't Trump bombarding the Kremlin? Isn't Putin a much larger threat to world peace than any leader of Iran?
Russia is not a threat to the US per MAD doctrine. If Iran had nukes, you might believe that they could actually be mad enough to use them and because Russia has nukes, no one would try this with Putin.
> Also, it's never "morally okay" to kill anyone, ever; the fact that the US still has the death penalty shows how little they understand about morals and logic.
Never, ever? Even self-defence? Or what would you do if you were living in a hunter-gatherer society that did not have the capability to imprison someone for life and you had a murdering psycho in your tribe? Expel him so he can come back and kill more people? Logic?
There are bunch of tedious / routine tasks that AI can automate.
I think the big hurdle is mostly education / shift in mindset. We are so used to doing the task manually that most of us (including me) don't pause to think if I should be doing this or can I give to an agent.
I had browseros do a bunch of data validation for me in my Dolibarr ERP system. It cross checked my new master data against our old ERP, flagging bad links and filling in missing data. I could have done it much quicker overall with the api and some scripting, but it was easy to just write a two line prompt telling it where the data is and how to manage disagreements. Then I just watched it run on a second monitor for a few hours while I worked other projects.
I used a local Ollama model and though it was kind of amazing that it worked. I couldn't turn a typical user lose with something like this yet, but I think I see the vision. I image a lot of automation could happen this way in the future. I put less effort into the prompt than I would have needed to spend teaching someone from the office pool to accomplish the same goal, and got a good enough result.
In practice I have found that I can accomplish the same results in a stricter, more accurate, and faster way just using codex on the command line with some scripting and API access, but that's not going to work for a lot of people and putting it in the browser is pretty convenient... The MCP server that's built in can also become a bit of an API for the entire web if you're careful in how you use it, which opens up possibilities for things that don't have real APIs.
It depends on what you are pursuing. Software was never a true moat for the really hot stuff. See books Zero to One, 7 Powers. It can be moat when you have something extremely complex, like for Unreal Engine, software actually is the moat. However, when it comes to regular software, everything was always prone to being copied. Will it be copied, it depends entirely on what's for the grabs for someone else to copy it. If you have a mature SaaS, that already has some competitors, what does anyone gain by copying it if the projection for building a sustainable business is very small? Personally I am building something that is relatively complex (much more complex / non-standard than a CRUD and likely not in Claude training data, and something that would be a very bad idea to write it in AI slop due to security issues) and relatively niche, something that a well funded startup would never dream about building, yet something that a smaller team would have a difficult time to compete with me, LLMs or not.
