Brian Chew
Useful little systems.
X
Stream of consciousness, no filter — opinions are my own.
-
me love
-
Reposted · @agrimsingh
how fast is @OpenAI's gpt-realtime-2? fast enough that i can dj live with it 😅😎 here's a demo of me controlling traktor using only my voice including loading songs, playing them and mixing them in properly by manipulating the eq bands. codex was able to build the bridge to run the pipeline: mic → gpt-realtime-2 → tool calls → node bridge → virtual midi → traktor "turn sync on deck B" "bring the mids in" "swap the bass" - it just does it. eq ramps are server-side so the blends are actually smooth. the dj mixer is just an api now. demo 👇 @OpenAIDevs @thsottiaux @romainhuet @reach_vb @gabrielchua
-
Reposted · @skirano
MagicPath is now available as an official plugin for Cursor. Give Cursor an infinite canvas where you can view and edit interactive code, build apps that are instantly sharable. Use your local files, skills, etc. And with Composer 2.5 you can design at the speed of thought ⚡️
-
Reposted · @Dimillian
A new update for Codex Mobile in ChatGPT iOS is available, and this one is packed with goodies! We got /goal UI support, more /side chat features, worktree and git branches for new threads, inline code review, and more! You can find the changelog here: https://developers.openai.com/codex/changelog?type=codex-mobile
-
Reposted · @timsneath
One of my personal favorite features announced at WWDC will I suspect be a sleeper hit: container machines, allowing your Mac to run a lightweight, persistent Linux environment with your home directory and repos automatically mounted: https://github.com/apple/container/blob/main/docs/container-machine.md -
yooooooooooo!!!
-
Reposted · @VictorTaelin
this is my personal singularity moment this post may sound like a paid ad. I only wish. I'm concerned, more so than happy. the world is changing, and, among the scenarios where AI goes terribly wrong, inequality is the most realistic, yet, the one Anthropic seems to be the least concerned about. I'm glad OpenAI is taking the opposite stance: *personal AGI for everyone*. I think this is a commendable position in the times we live. but who am I in the queue of the bread? anyway, Fable is here, so I'll just report my first-hour experience first of all, all my pet prompts are solved. → λ-calculus puzzles → bug questions → one-shot apps all are trivial to it. I don't have anything harder other than my ongoing work so, in the last several days, I've been toying with HVM5, a new interaction net evaluator with a faster loop. after writing the first version, I left 32 GPT-5 agents working for ~20 hours each. this resulted in up to 2x speedups, but the file size increased by 2-fold and quality decreased significantly. I then simplified the whole thing into an even simpler core, and left Opus 4.8 and GPT 5.5 optimizing it for 8 hours. Opus got a legit 6% - 34% speedup in most benches. GPT got better results, but, sadly, an unusable file. I then asked Fable to optimize it. 2 hours later, it landed a 1770% speedup in one case, 100%+ in other 4, and 22% in average. yes, in 2 hours it outperformed me, opus 4.8 and a swarm of gpt 5.5 agents, by one order of magnitude. that could not possibly be legit. "it must be hardcoding the benchmarks" (GPT trauma). so I read its explanation and what it did was, indeed, the most high impact optimization one could try first. seems like HVM5 was wasting a lot of time garbage-collecting unused branches of pattern-match nodes. I had optimized that for static mats, but not for dynamic mats. skill issue. Fable figured how to do it for these, resulting in a massive speedup in some benches but wait, is that *correct*? I'm not sure yet, it is credible, but this is the kind of thing that is very easy to get wrong on interaction nets. the problem is, when I was ready to start auditing Fable's solution so I could tell whether it was buggy or legit, it interrupted me to tell me it had found a massive bug on the code *I* had written. ... wait, what? so... for garbage collection purposes, I stored a bit on lambda term pointers that meant "the variable bound by this lambda has been freed, so, its lambda must free whatever argument it is applied to". that's fine. yet, on duplicator nodes, I also used the same bit to mean "one of the duplicated variables was freed, so, treat this dup as a passthrough no-op". so, if a lambda entered a duplicator, it would mistake the lambda's collection bit for its own, resulting in corrupted interaction! that's a mouthful, why I'm writing this? just so you can appreciate the sheer absurdity of what just happened. I didn't ask it to find bugs. I asked it for an optimization. and even if I did ask it to find bugs, this bug is so astonishingly subtle and specific, identifying it takes mastering the domain to an extent that it beyond even me. I'd easily need hours or days to fix it, *if* I ever came across it. chances are it would just go unnoticed. and Fable found it and fixed it like it was nothing, while it was busy adding a 17x speedup to a file that neither I, nor Opus 4.8, nor a fleet of GPT 5.5 managed to barely make 2x faster. oh and there is also another tab where it is also ripping through Bend's codebase and finishing everything I had to do I don't know what to say anymore this isn't about Anthropic or OpenAI, this is about our collective future as a species. the world is changing, and we need to be aware of it, and discuss how to handle this change. receipt below . . .
-
a super long day today, and... only one thing worth posting about: @cursor_ai Singapore🇸🇬: Build Night!
together with the legendaries @agrimsingh and @SherryYanJiang!
here's a short(or medium😁) recap in case you missed it! 🧵👇
