One thing I can say about the Wolfram language is that is actually Lisp with syntax that looks weird at first sight.
However when you look at rule processing, it's like pattern matching on steroids that I haven't seen in lisp world. It looks quite powerful and applies throughout the language (eg the "Query" book).
Too bad the whole language is closed and so heavily licensed .
I also use the Kagi assistant, and one thing that this post inspired me to do was to test out some of the models with and without web access, and I encourage you to do the same. Qwen, for example, behaves completely differently when it's summarizing searches vs operating without that tool. I assume this has to do with how Kagi tells it to respond, but it seems to impact some models more than others.
I think that would require some testing and evaluation according to personal preference. My opinion is that Qwen 3 and Deepseek Chat v3.1 become much more concise when summarizing searches, but much less detailed. When used without the web search tool, they become more verbose (and express more "personality"), which may be less desirable in some contexts, but they also gave more informative answers. With Kimi K2 I seem to find the opposite; it really does well when analyzing search results (and really likes inserting tables to give break down its findings), and its "offline" version was much less detailed.
Oh, and an interesting finding: Kagi's selector indicates that they're offering Deepseek Chat v3.1's non-reasoning version, but when I ran it without web search it appears to have messed up and output some of its chain of thought, so it clearly is thinking.
The FBI tracks active shooting cases-where individuals attempt to kill people in public places, excluding those tied to robberies or gang violence. This study is the first to systematically compare how uniformed police and civilians with concealed handgun permits perform in stopping these attacks. Civilians with permits stopped the attacks more frequently and faced a lower risk of being killed or injured than police. Officers who intervened during the attacks were far more likely to be killed or injured than those who apprehended the attackers later.
Through incredible human ingenuity, we have convinced the two most abundant elements in the earth's crust to give us free energy. Once they are no longer effective, after several decades of service, we put them back in the earth where we got them.
Is this a problem worth solving?
Is it a problem worth giving any amount of thought to at all, when the alternative is killing people both directly through pollution and indirectly through climate change?
1. If you can easily write boring code with LLM, you might not have the incentive to refactor it.
2. If you let someone else solve your problems, and you don't reflect in the solution, you won't learn.
3. I rarely read the fine print, but are all LLM IDEs really the same when it comes to intellectual property of the code? Or the responsibily of bad code?
I think the problem that people don't see anymore is using tests themselves. A clever idea is worth more than a single tick in the correct checkbox. This applies to maths as well. Tests are faster to check and, supposedly, objective, but a viva voce exam is still superior imho.
However when you look at rule processing, it's like pattern matching on steroids that I haven't seen in lisp world. It looks quite powerful and applies throughout the language (eg the "Query" book).
Too bad the whole language is closed and so heavily licensed .
reply