Depends how you use LLMs. I didn’t say use LLM to solve the problem, I have it breakdown the documentation and make it easier to read/provide examples of usage + explain the steps.
Stackoverflow also has incorrect answers always marked as correct and isn’t a great source to learn from, the best way to learn is just reading documentation and having breakpoints to read the data coming in.
I had to make a stackoverflow back in the day to correct so many incorrect answers.
I don’t pay for a single one, I’ll use their free services for a specific question to have it summarize the internet basically. I try and avoid chatgpt.
At work we have an internal AI system, and Claude. I utilize both of these to make my workload smoother - but have been finding myself just coding more often than using them because they almost all eventually produce garbage and refuse to listen when you say it’s wrong.
That eventually you have to say goodbye to parents, grandparents, animals, and loved ones - and there will always be a void you can’t fill that they filled.
For programming questions why not use an LLM? The days of searching a specific problem are long done. LLM+Documentation is all you really need now days.
Hard to escape Google for its consistency. At work though I use bing(it’s trash) 😂
Edit: haters gonna hate, bing at work because I’m too lazy to switch defaults. Google for consistency, whether you like it or not 99% of the comments all says they use DDG and then admit they still use Google for consistency.
You’ll find yourself always back to Google.
https://www.anthropic.com/news/statement-comments-secretary-war
Earlier today, Secretary of War Pete Hegseth shared on X that he is directing the Department of War to designate Anthropic a supply chain risk. This action follows months of negotiations that reached an impasse over two exceptions we requested to the lawful use of our AI model, Claude: the mass domestic surveillance of Americans and fully autonomous weapons.
Guess who our government is switching to? OpenAI. Fuck Sam.
Trump wants to use Grok for all things government, but isn’t Grok one of the most biased and poorly performative AIs?
I gotta give it to Apple, they refused the FBI requests to create “backdoor” access. I feel Google would just bend the knee
A tad fucked that you only think of the current and not the length of their impact on your life. Yes, the current can be bad, but you have think about the impact they have - especially if someone has dementia.