5.3 is certainly “better” than its flash variant, in my experience. I’ve moved on from both but eagerly await the next generation of each.
Better, in this context, is more capable with open ended work, planning, longer horizon “reasoning”. Flash is an absolute chad with a well defined task and accompanying guidance/guardrails/conventions provided. But not even close when it needs to deviate, runs into a “blocker” and has to reason its way out.
Uh, well, I've been maniacally obsessed with building my own harness/factory/memory & context layer/build/ship/deploy pipeline because, well.. I like to automate things.
About 6 months ago I embarked upon building a little mac native app to monitor all my claude code sessions and alert me/surface sessions that were going to go stale so I could go ping them if I wanted to keep things cached. I named it CREAM.
That eventually grew into what is now my 'software factory' and I've realized, eventually, it's still C.R.E.A.M. (I named it flower) but it's _context_ rules everything around me.
I literally launched my development and web career on the back of this service as a broke early-20s person. Just seeing that link on HN gave me goosebumps. <3
Mine was when I noticed some pages on the internet were somehow dynamic. Like they could respond to outside stimuli somehow. I have seen a bunch but dslforums was the one that actually mentioned what they were using. It was PHP of course and right around the same time VA Linux was offering free PHP hosting (with shell?). I didn't become much of a programmer but I did do web programming "professionally" for a time.
Ask claude to do it end to end, then write a solution that fits your needs from it's experience with you driving it.
I did exactly this - probably the single most valuable piece of software I've "written". It's the backbone of every piece of code coming out of any agent under my control (via MCP toolset).
> But, my biggest annoyance with most non-flash model providers - including GLM is they will dumb down the models based on load (like switching a non-flash model to flash model).
Where are you seeing this? This would be sufficient for me to stop using that provider entirely, immediately.
Better, in this context, is more capable with open ended work, planning, longer horizon “reasoning”. Flash is an absolute chad with a well defined task and accompanying guidance/guardrails/conventions provided. But not even close when it needs to deviate, runs into a “blocker” and has to reason its way out.
reply