What if you use a different prompt to check the result, did this work? I am thinking to use this approach, but now I think maybe it is better to use two different LLM like you do.
They did several wrong decisions, first they started building it with old libraries, e.g. JQuery, KnockoutJS, then they they should have opened their no code builder to the public. They are now in the process of porting it to Preact and opened VBCS, but it’s too late. From UI point of view, it is the most complete library
I went little further. I could not find low or no sugar Nestle cereals at the local supermarket, then I asked their support if they have something with low sugar. Their rep wrote that they have lowered the sugar amount by 34% from 2000 to 2010, but it is still not clear if those amount are OK, when I taste the sugar amount is definitely high. I do think the government should step in and promote healthy food and habits
I am planning to build a muon catalyzed fusion reactor. Currently studying the possibility of absorption of hydrogen isotopes into the crystal lattice of certain metals, such as palladium, which can trap and localize these atoms at very high densities. As I believe, that one of the showstoppers is to increase of the density of the target.
Since the article mentions graphs, I’d like to ask what would be the advantages of graph databases over relational? Graph databases have become popular in RAG related topics, maybe mainly GraphRag related work by MS. So I wonder if the same accuracy with RAG could be achieved by traditional databases. Or if graph databases are an absolute must, then what are their limitations? Are there any successful production usage cases of graph databases?
Instead of forking popular libs, someone should think how to improve OSS model. I think it is wrong when projects with 1mln users are not self sustained
Hopefully, they will check for overemployment before allowing them to remotely control, otherwise we end up with one operator controlling several cars. I don’t know if it is good or bad
Is it a good practice when you give out blanket subsidies? Does targeted subsidies work better and are cost effective? I am researching this topic applied to taxation field.
I WFH, even work on weekends. I notice that after working weekends I feel tired on Mondays, so I decided to spend Mondays on less technical stuff, e.g. customer meetings, interviews, lead generation etc
Sorry about this comment, I read the post, it is a TSV file where the data is stored. I have been researching AirTable alternatives and I somehow thought there was an underlying database. My fault
The major state owned Kazakhstan telecom company did peering with Telegram, they say now it is 10ms is better, but the real reason might be to have means to cutoff Telegram if anything wrong happens
I know about the limits on max column number per table. The other day I was thinking about the best table layout for AirTable like systems, I finally decided to use relational tables with json fields. E.g. row is a several fields (id, name, who fields) and one json field where I can put any number of fields. Hopefully, this is going to be the best from both worlds and work good from performance view.
"just doing the work myself with AI" this is exactly my situation. This confirms that there is an impact from ChatGPT. Why would someone bother to train a junior dev, when they can offload the same task to ChatGPT. But on the other hand we still need juniors because they will someday become middle and senior developers