Nate Meyvis

Notes on Flash 3.8

Flash 3.8 is out, as I discovered when it showed up in my Antigravity terminal.

A few notes after perhaps an hour of use:

  1. As I discussed earlier today, I use the latest Flash models heavily because they combine power and speed in such a valuable way.
  2. Flash 3.8 with high thinking did well on the first tough task I gave it, but it was slow (probably not faster than Fable). I'm likely to keep using Fable 5.1 instead of Flash for tougher tasks.
  3. Flash 3.8 with low thinking is addressing simpler tasks, both coding and non-coding, quickly and accurately. I believe that it's more powerful than 3.7, but I haven't yet felt that difference.
  4. So far, there's (still) a big latency difference between low and high thinking.
  5. I have a standard content-extraction task that I like to use as a benchmark. Over a small sample, Flash 3.8 with low thinking gave results ~25% faster than Flash 3.7 low thinking; those results are different but, in my judgment, not clearly better or worse.
  6. "Not better, but faster and a bit different" fits my experience across the ten or so little projects I've done with it so far. Again, given how I use Flash and how important speed is, it would be great if this were true.

Happy New Flash Day!

#generative AI #models #software