Viewing profile — diwank

you lose CoT monitorability which is a big issue since models have become quite powerful and also often deceptive but i do think that efficiency pressure will keep nudging us towar…

I feel like recent models have been consistently getting more sloppy and increasingly claude-ism heavy (load-bearing seams galore) with every new release. I was hoping this trend w…

[flagged]

this is surprisingly high delta. to make matters worse, reasoning tokens account for the majority of tokens and they are completely opaque so it's hard to tell how much of that is …

i'm not happy with how openai is trying to pit 5.6 sol as a cheaper equivalent to fable here for one thing, they said that on AA, sol is "within one point of fable" at 58.9 vs 59.9…

where did you find that? weird coz their post announcing this also mentioned Claude Code: > Fable 5 will be available starting tomorrow, Wednesday, July 1, to users globally on the…

""" It remains unclear whether Anthropic’s engineers are assisting the NSA in active operations. However, one person close to the situation said Mythos would be useful for infiltra…

in order for us to get there, i think we need a standardized api at the os layer for local models so that the os could optimize, batch and safely allocate resources. something like…

and device dependent. this is a very tricky thing to get rendered consistently

this is actually a surprisingly rich area of debate in philosophy of mind. see: https://plato.stanford.edu/entries/qualia-inverted/

had a bad experience with pg_search (paradedb) in the past

we have been using pg_textsearch in production for a few weeks now, and it's been fairly stable and super speedy. we used to use paradedb (aka pg_search -- it's quite annoying that…

this is so disingenuous on symbolica's part. these insincere announcements just make it harder for genuine attempts and novel ideas

tl;dr * If you need an LLM to parse OR emit a timestamp, use: RFC 3339 ( e.g. 2024-03-26 10:30:00-05:00 ) * python date format also works well * Do NOT use unix epoch or javascript…

Angels & Demons anyone?

opus 4.6 gets it right more than half the times

I've spent the past year building a theory of phenomenal experience (consciousness) that's designed to be falsifiable. It identifies phenomenal quality with a specific mathematical…

Working on Memory Store: persistent, shared memory for all your AI agents. https://memory.store The problem: if you use multiple AI tools (Claude, ChatGPT, Cursor, etc.), none of t…

I dont think this is Cerebras. Running on cerebras would change model behavior a bit and it could potentially get a ~10x speedup and it'd be more expensive. So most likely this is …