I noticed how ChatGPT got progressively worse at helping me with my research. I gave up on ChatGPT 5 and just switched Grok and Gemini. I couldn’t be happier that I switched.
It's amazing how different are the experiences different people have. To me every new version of chatgpt was an improvement and gemini is borderline unusable.
A lot of people still have a shallow understanding of how LLMs work. Each version of a model has different qualities than the last, each model is better or worse at some things than others, and each responds differently to different prompts, styles. Some smaller models perform better than larger ones. Sometimes you should use a system prompt, sometimes you shouldn't. Tuning settings for the model inference (temperature, top_p, penalties, etc) significantly influence the outcome. (https://www.promptingguide.ai/introduction/settings, https://platform.openai.com/docs/guides/optimizing-llm-accur...)
Most "big name" models' interfaces don't let you change settings, or not easily. Power users learn to use different interfaces and look up guides to tweak models to get better results. You don't have to just shrug your shoulders and switch models. OpenAI's power interface: https://platform.openai.com/playground Anthropic's power interface: https://platform.claude.com/ For self-hosted/platform-agnostic, OpenWebUI is great: https://openwebui.com/
Gemini has a great model, but it's a bad product. I feel much happier using ChatGPT because Gemini just seems so barebones and unpolished. It has this feeling of a tech demo.
Scientific research and proof-reading. Gemini is the laziest LLM I've used. Frequently he will lie that he searched for something and just make stuff up, basically never happens to me when I'm using gpt5.2.
The way I summed it up to a friend recently is that Gemini 3 is smarter but Grok 4 works harder. Very loose approximation, but roughly maps to my experience. Both are extremely useful (as is GPT-5.2), but I use them on different tasks and sometimes need to manage them a bit differently.
Maybe they messed something up in the official interface then. I've heard that the PDF processing capabilities are also significantly worse in Gemini UI compared to using it through the API or Google AI Studio.
Any coding task produces some trash, while I can prototype with ChatGPT quite a lot, sometimes delivering the entire app almost entirely vibe-coded. Gemini, it takes a few prompts for it to get me mad and just close the tab. I use only the free web versions, never agentic ‘mess with my files’ thing. Claude, is even better than that, but I keep it for serious tasks only, so good it is.
Gemini loves to ignore Gemini.md instructions from the first minutes, to replace half of the python script with "# other code...", or to try to delete files OUTSIDE of the project directory, then apologise profusely, and try it again.
Utterly unreliable. I get better results, faster, editing parts of the code with Claude in a web ui, lol.
Odd, I've found that Gemini will completely fabricate the content of specific DOIs despite being corrected and even it providing a link to a paper which shows it is off about the title and subject of a paper it will cite. This obviously concerns me about its effectiveness as a research aide.
The old chat gpt models scanning the nih pub med repositories with proper prompting (e.g. …backed by randomized control trial data) was an amazing health care tool. The stripped down cheaper versions today are junk and I’ve had to start relying on grok :-( I’m not convinced OpenAI can make this work
Are we going to subsidize a broad array fruits/vegetables instead of corn to the point they become cheaper than processed foods? If not I think many americans will ignore this pyramid and do as they currently do.
The single reason I use apple maps instead of google maps is because of the lack of ads. For me, it is really the only competitive advantage offered by apple maps
How much does it cost to host a tarball of an app? Maaaaaybe 15 cents?
> Steam for example takes $100 PER GAME.
Well that's not true.
> What we should be pitchforking about is why Apple isn't taking all that 30% to IMPROVE the App Store for USERS
That's exactly what I'm saying.
They're taking 30% and then doing fuck-all. I can maybe, MAYBE, buy the 30% if the appstore was some paradise on Earth and my iPhone gave me a blowjob. But that's not the case. So what are we paying for?
They already get paid to do that - the 30% is completely unrelated to that.
That's also optional. Apple chooses to develop iOS because it becomes a new pathway for siphoning money from consumers and developers, and allows them to create their walled garden.
They could just stop at any point and use android or even off-the-shelf Linux with an OS mobile environment.
Phone and laptop batteries probably make up a tiny fraction of the battery market. My EV battery is almost 5000 times the size of my iphone.
Sodium batteries, if the technology works, would replace EV batteries and provide support to the electrical grid, and would be purchased at thousands of times the volume of iphone ad laptop batteries
Since their energy density is still lower, it will probably take a while for them to be adapted in EVs.
But their impact on energy storage to stabilize the grid, both technically and in terms of prices, can not be overstated. Cheap, safe storage is the key component missing in Europe for using more renewables. Without that you need to keep gas plants in reserve, should there be a few days without sun and wind.
I bet we (well, China, at least) will see some lower range but cheaper EVs using sodium batteries pretty much right away. A lot of people would be fine with having something that can only do 100 miles as their daily commute vehicle as long as it was cheap, especially in 2 vehicle families.
A small bush fire is not supposed to cause 60 billion in damage. Also, innocent until proven guilty. The evidence against the guy seems weak… like generating images on ChatGPT
A significant amount of that damage was due to government policy, or rather failures of government policy.
Fire hydrants literally went dry in the middle of firefighting. Fire Departments were critically understaffed, and were using critically outdated dispatching systems that didn't share information or communication effectively.
The fire was started by arson, and it ravaged the city due to government failures.
But what if AI succeeds and it’s the rest of the economy that implodes? Long-term, I’m sure AI will lead to massive productivity gains. Short-term, I think it’s going to be chaotic. I don't know which will implode, AI or repetitive white collar work or something else
I wonder how much variability there is in the product from batch-to-batch. Could one batch be producing unwanted by products at a much higher quantity than another batch?
It's a bacteria that's meant to colonize your mouth, the concern isn't byproducts in the initial dose, it's whether the bacteria after colonization produce harmful byproducts.
According to the article as I understand it, the bacteria in question directly produces formate, the suspected culprit behind the vision loss. Ethanol being produced by the bacteria is not the relevant information here
my point is about selling proposition of that probiotic - production of ethanol which i'd not expect to be long term healthy on its own merits, even without formate.
Various metabolic processes in the body already produce methanol and ethanol. Now as to the relative quantities involved, I have no idea what can be produced by bacteria in the mouth.
Yeah, that is the big question here... how much is being produced. Also, how variable is the product from batch to batch? Could one batch be producing byproducts at much higher quantities than another batch?
reply