STE is very hyped for AI but has its own smells. It's designed for aircraft maintenance manuals, not software - the two don't share the same vocabulary used to "simply" describe something. I've had a coworker try and "simplify" our documentation with Claude applying STE and the results were equally appalling to read as the Claude-ism laden docs that came before, despite the reading level metrics going down on paper.
I've taken a liking to pointing agents at the Simple English Wikipedia editorial guidelines...but so much of that is for making up for shortcomings of modern Anthropic models. Codex running 6.1-sol explains things so much more clearly that I don't feel I need to assert a style guide on its output.
Gemini 3.8 for me always outputs in a concise way at the level understandable for any computer science masters graduate. Clear, to the point, a bit of formula for background when really required instead of the same formula in Prose, etc.
- Gemini 3.8 has a beautiful answer. Typography, use of lists, brevity, style, even the font choice on the web harness -- all of it is A tier or even S tier. Notice I didn't say answer quality. The answer is always extremely mid, and the harder the question (or more effort needed to answer it), Google just quits. I give it a "C" on answer quality
- ChatGPT (Chat, pre 6, I assume 5.6 although they commonly hide the model picker): Ugly answer. Runs on printing page after page of unnecessary side notes. Mostly just walls of texts in paragraphs with little thought to information design. However, inside of that mess of text is almost always the answer I'm looking for, and it's almost always incredibly better than the truncated, desgined Gemini answer.
For a while I ran all of my question queries on Gemini and ChatGPT, but I noticed that I basically always picked ChatGPT's answer head to head.
Interesting that this hasn’t been my experience. ChatGPT has often gave me with pages of text dripping with confidence about a solution for my problem. Diving very quickly into implementation details. Even if I tell it to stay in the problem and product fit level.
Gemini on the other hand somehow always outputs at the level that I am expecting and reasoning.
I even found it was capable of stepping back from code implementation and bug hunting to “hang on, it’s not the algorithm that is incorrectly implemented, it is the wrong algorithm for the goal.” GPT Sol (5.6,6 and 6.1) just kept hammering in the problem.
To be clear, I'm discussing non-technical use of Gemini and ChatGPT through the web harness.
While I do rarely use the web harnesses for technical research, nearly all of my technical questions are going through coding harnesses and layers of my local context, skills, etc, so what I produce from codex/claude code is not comparable to what others produce.
So my comparison of the web harnesses is me asking questions about caring for my baby, or product comparisons of new televisions, or visualizing a room organized differently (google sucked at this so bad, chatgpt did great), or asking for help in a video game, or other normie AI uses lol
I will say, Gemini is the best for asking about google services, such as Flights or Youtube.
Isn't this just using SMTP through whatever mail server you have connected to Gmail?
Either way, this is likely going to stop me from using Gmail as my mail aggregator, I've used this feature for nearly a decade to send and receive from 6 different addresses, Gmail recognizes the to address and automatically sets the from address to the correct account.
Is Thunderbird still decent nowadays? What's a decent mobile + desktop replacement?
I've had this happen to me personally on vacation - we were locked out of our rental car, asked a person at the nearby place to call a locksmith to get me back in, and they didn't quote price over the phone. When they got there, they popped the lock and then wanted $200, cash only so you couldn't chargeback, which I learned after the fact is completely outrageous for that service. They had a lot of fake Google reviews that were glowing, overshadowed by the real ones calling out the scam.
I've heard worse happening in other cases where they drill locks and then quote much higher than $200 after they do it, it's sadly common.
That's exactly what I would think if I were in trouble and hadn't done any research, but in fact it is not. When I needed a locksmith a few years ago, at night, it cost $70.
Probably depends highly on location, company and type of lock. I needed to get into my mailbox after losing the keys. They wanted 150 for literally 5 minutes with a screwdriver (lesson learned!). Of course I'm paying for those years of experience as well as the drive over. I was able to talk them down to 120. Oh and it was during the weekday! I also did research prior and called a few places, they all basically said the same thing: "depends on the lock but probably minimum 100".
The DOE does a lot of "energy consuming" or less than environmentally friendly work, to include, historically, nuclear tests, and also has had ownership of some of the largest TOP500 supercomputers over the years.
Large compute projects such as an open language model aren't too far from their usual. You could easily argue the race to AGI is the closest thing to a modern Manhattan Project we've had in some time.
Whether that's a good allocation of resources is debatable, but from a national strategic perspective this makes sense, since private industry has pulled out of government contracts before in the LLM space (see Anthropic), this is just hedging their bets.
I've taken a liking to pointing agents at the Simple English Wikipedia editorial guidelines...but so much of that is for making up for shortcomings of modern Anthropic models. Codex running 6.1-sol explains things so much more clearly that I don't feel I need to assert a style guide on its output.