Two ways that have worked for me YMMV 1. Have one agent build it and then another check(Usually the agent that checks is a bigger model or with more effort) 2. Make it deterministic, make sure you have a list of…
Isn't that what Google just released although it is mac only for the moment. https://developers.google.com/edge/foresight
> frequently contains all too plausible nonsense, and is increasingly jargon dense. Does anyone know how to deal with the jargon part? It is getting hard to use claude and even worse when someone sends you the direct…
Ask it to create a small sample to reproduce the issue in isolation. If it can't reproduce the performance changes then it drops it. That might work better. I haven't tried it with SQL but it worked with a few complex…
Apple might be a good counter example of what happens if you don't focus entirely on AI. Right now it seems to be doing ok.
Supposedly 70% of software projects failed even before AI. So are AI projects better or worse than that? Also like people have asked about the 70% failure rate, how do you define failure/success.…
Hasn't OpenAI being doing it for a while too? https://news.ycombinator.com/item?id=48465269
Just as a counter example, Midjourney is completely self funded and profitable. But they are images, LLMs might be more expensive to train but their inference is cheaper. So the frontier model companies might have crazy…
Two ways that have worked for me YMMV 1. Have one agent build it and then another check(Usually the agent that checks is a bigger model or with more effort) 2. Make it deterministic, make sure you have a list of…
Isn't that what Google just released although it is mac only for the moment. https://developers.google.com/edge/foresight
> frequently contains all too plausible nonsense, and is increasingly jargon dense. Does anyone know how to deal with the jargon part? It is getting hard to use claude and even worse when someone sends you the direct…
Ask it to create a small sample to reproduce the issue in isolation. If it can't reproduce the performance changes then it drops it. That might work better. I haven't tried it with SQL but it worked with a few complex…
Apple might be a good counter example of what happens if you don't focus entirely on AI. Right now it seems to be doing ok.
Supposedly 70% of software projects failed even before AI. So are AI projects better or worse than that? Also like people have asked about the 70% failure rate, how do you define failure/success.…
Hasn't OpenAI being doing it for a while too? https://news.ycombinator.com/item?id=48465269
Just as a counter example, Midjourney is completely self funded and profitable. But they are images, LLMs might be more expensive to train but their inference is cheaper. So the frontier model companies might have crazy…