Viewing profile — aghilmort

this is great! xmlppm was big part of xml study which did years ago and which uses expat for parsing xml; was first fond memory of expat / keep up great work

really great work

one interesting use case is surface management in ways that cant be solved easily by swapping desktops or which is clunky this happens most on single-screen where have to swap apps…

nice work

[dead]

fully local transcribe.cpp in your browser at https://mic.sloop.ai/ github repo soon, finalizing ggml / emscripten magic simd, pthreads, etc. parakeet for now, adding models, webgp…

LTS is really useful framing even if increasingly distilled or slower on older hardware etc vs disappearing model acts

Time Machine movie reboot did this in opposite direction into future decently well dude wind hundreds of thousands of years into future, sands of time, etc. modulo two warring biol…

this is really great like collecting bottle caps except is buttons

audio.cpp @ github repo has good collection of TTS models

wip WASM-tested baseline models yesterday / doing webgpu binds required pinned ggml patch & OMP,SIMD,etc. tweaks to make all models efficient, this work meshes well with other buil…

super cool roster! niche text generators come to mind, e.g., text version of regex train tracks / git traces come to mind. png/svg version https://regexper.com/#%5Cd%7B5%7D%28-%5Cd…

interesting. tried it on iPhone SE. hard to do safari keeps thinking want to exit page. sliding one touch left right or u/d both might be good alt? certainly better than trad click…

one nice thing may be way to enhance penetrative ultrasound eg smaller immersive ultrasound tomography in smaller dip tank hey stick your leg in this thinner immersive tunnel , e.g…

we can do tomography on any round-robin-rectify multi-pov source, doesn't have to be x-ray is just de facto use in medicine, closer to at min marketing ed problem

this is great / will try!

ya, brain just noisy channel in same way we can treat LLMs; anything possible exists we are just sampling it, which distills to "mere" clock syncing L1 & L2 constraints unwind that…

one approach that can work is to tell model to load read skill and/or call shell script that overloads default, there are variety of ways to attempt this with any harness, claude s…

curious: wdym by "getting separators right when generating multiple files in a single inference call" context: created hypertokens an even more robust hashing mechanism to create c…

we dug into those sorts of questions with hypertokens, a robust hash for lines, code, tables/rows or any in-context token tagging to give models photographic memory one mechanism w…

been wondering about treesitter grepping for agents how do plans compare with and without etc. evven just anecdotally what you've seen so far etc

[dead]