back
user profile
helloplanets
2,649karma·541submissions·September 15, 2020
recent activity (541 total)
comment
I'd imagine 99% of ChatGPT users see the app as the former. And then the rest know how to turn the memory off manually. Either way, I think memory can be especially sneakily bad when trying to ge…
comment
Yeah, not sure what the author was thinking there. Definitely not 'reaffirming of both your and their humanity'. I mean, I get that it's supposed to be just a general pointer or somethi…
comment
Whether the tokens are created manually or programmatically isn't really relevant here. The order and amount of tokens is, in combination with the ingestion -> output logic which the LLM API &…
comment
Would be interesting to see an in depth breakdown on a project that has went through the vibe code to cleanup pipeline in full. Or even just a 'heavy LLM usage' to 'cleanup needed'…
comment
That's a sneaky switch from we to you . Meaning: Collectively, humanity definitely have done and proven the latter, more so than necessary. And if we were to dive deeper into the Philip K. Dic…
comment
Definitely not much of a chef! > When I get up, I have a cappuccino - that's breakfast. I don't have any food till lunch. I get into phases where I'll have the same thing every day. …
comment
The iMac mouse looks amazing though! Ergonomics, not too sure about those.
comment
Not all LLM based applications are a user facing free form chat. If you take an LLM that makes 10 tool calls in a row for an evaluation, any reduction in unpredictable drift is welcome. Same applies t…
comment
Ah, the site's bugged on Safari and wouldn't scroll. Worked on Chrome. Tried to look for it on the actual chat page, and wasn't in the source there. Not clear from the original post: It…
comment
Could you provide a link to that system prompt? Becuase I'm confused. I typed in "Are you smart?" and got this back: > That’s a thoughtful question! I’d describe my "smartness&q…
comment
Don't forget the millions of years of pre-training! ;)
comment
You could argue that the suggested system is actually much simpler than the one we currently have for the sites that are "free", aka funded with ads. The lengths Meta and the like go to in o…
comment
Most of those look like context issues to me. Repo map (using Tree-sitter, etc) and documentation would already do wonders. Feeding 32-64kTok of context directly into a model like Gemini Pro 2.5 is so…