I am currently working with a non-dev startup CEO that's fully embraced Claude Code and vibe coding.
90% of my work is to run code review workflows and steer his CLAUDE.md into the correct architecture choices and away from past mistakes.
So far it's working pretty well -- I'm able to unslopify the code and maintain the agent's performance. And the CEO is happy, he's able to develop his product pretty fast and not hit any walls.
In my experience, the delta in agent performance is substantial if the codebase is littered with dead code, redundant code, unreachable fallbacks, leaking abstractions and half-baked design patterns vs if the code is well-organized, with clear data flow, with good encapsulation and clean architecture. Like, I've seen all the frontier models have to do several rounds of code review / QA and fix when the code is bad vs just getting it right at the 1st/2nd attempt.
This is like what you can setup with Hermes or OpenClaw within a few minutes with your ChatGPT subscription or an open weights model, except they handle the Slack setup for you and bill you at API rates.
That's true, but a lot of these people are also competitors. I can't imagine it'll be attractive going to the OpenAI media channel to talk about Gemini or Grok.
To be honest, until a month ago, I hadn't even heard of TBPN or seen any of their content. But, seemingly, out of nowhere, they managed to get all the leaders in AI to appear in their programming.
The core of the information they present isn't much different than what you'd hear on Dwarkesh or other industry podcasts, the presentation is some weird mix of ESPN and Mad Money that I personally don't get, but maybe makes sense to a US audience.
I don't see why that is interesting to OpenAI, but maybe I'm missing something.
I thought about it for a moment, but the real reason I got the new M5 Pro with 64GB is to be able to run several large projects concurrently in Docker envs.
I didn't go for a Max chip because I value the better battery life on the Pro more than I value the additional GPU cores.
Personally, I think until the LLMs start to plateau, it will always be more valuable to run a frontier LLM vs just a very capable local LLM. I have no idea when that will happen, so I simply decided to not overbuy the hardware now.
> I've consistently found Gemini to be better than ChatGPT [ because ] Google has crawled the internet so they have more data to work with.
This commonly expressed non-sequitur needs to die.
First of all, all of the big AI labs have crawled the internet. That's not a special advantage to Google.
Second, that's not even how modern LLMs are trained. That stopped with GPT-4. Now a lot more attention is paid to the quality of the training data. Intuitively, this makes sense. If you train the model on a lot of garbage examples, it will generate output of similar quality.
So, no, Google's crawling prowess has little to do with how good Gemini can be.