hasufell has been a wonderful person in haskell land. hes got very clear headed ideas about stuff and so forth.
also the stuff i can now build in haskell with computer aid is epic. earlier this week i stood up what i believe is one of the/ if not the: best step file format reader writer on like every axis. some c ones are 20-30 percent faster on the largest possible cad assemblies i could try out.
an important axis that folks neglect to consider: the main way llms are getting scaled up for better coding is metric megatons of reinforcement learning traces, and type checking thats fancy gives a cheaper and faster training feedback loop.
with an llm as a sortah insane manic intern im looking over the shoulder, so to speak, im able to build the apis and designs i can see but cant type anywhere near the same scale. but i can specify the keystones for the exact designs quite compactly and then the agent kinda acts as a compiler inhave to correct and iterate running
yeah ive never heard anyone say they like doing productive coinduction in lean. agda almost has a story, but the ergonomics and semantics arent trivial.
i actually recently stood up my own end to end step reader writer as part of my own cad shenanigans, where i can have time to first geometry be in milliseconds even if the overal file is half a gig and physically needs a few seconds to parse. is there some reason why you dont have step export?
at this point im seriously pondering how to build a dvcs code forge thats not dog shit, versions its own state, and actually is semantically grounded rather than a rails app gone awry
You don’t need to (and should not) forward your SSH agent just to set up a tunnel, especially with the default OpenSSH ssh-agent. It allows the intermediate host to decide what operations to do with your key(s). `ProxyJump` is a way safer default.
A normal ssh feature that a lot of people consider a really clever maneuver, but many highly locked down environments expressly forbid because it’s a liability.
im midday through building a 3rd party multi device coding and everything harness with some unique hard to replicate features that should really help for successfully building amazing stuff reliably.
despite some of the stuff ill need to do as a consequence of wanting to keep some of those tricks private necessarily requiring that i kinda have my own byok open router for zdr providers endpoints only, i think its worth it.
theres a lot more i could say, but i hoping it can wind up being a cult favorite in techy/professional circles even if im planning to do something like 50/month for core plus pass through with hair cut on usage based costs. cause despite the large theoretical market, i think taking a page from sublime text for product stuff is likely the best way to roll.
i just want nice tools and recurrent income thats stable and mine. if both groove together, thats the dream.
every time i accidentally use flash versions of deep seek i get really frustrated with the model till i realize that it was the wrong model. im also a little confused because it seems like at least comparisons make it sound like ds is no longer focusing on their high reasoning model family …
I'm still unimpressed with the latest DS4 flash, it makes more mistakes or misses things. Very much like Ember-1 (Kimi K3 fine-tune to reduce thinking), it is not a reliable or trustworthy assistant (ime)
I have had the same experience with DS4 flash (basically all versions) but I really liked Ember-1 as a assistant, because it is to the point. Follows instructions and is capable enough to not get to haywire all the time.
in my case it very much is. im now deliberately leaving slightly off from correct writing, or exaggerated slightly. as a sort of organic behavioral kintsugi
reply