@ChatGPTapp PPS: Here's another before/after illustration for how we may think about AI, AGI and it's impacts (Originally from Rem Kolhaas' Delirious New York)
Before 1930: What we think this is
After 1930: What the future actually is and means
Lol. This is wild.
Wanted to dip my toes in https://t.co/ZSDGMufAkd, CC with Opus 4.6 built the editor of my dreams instead: "The beefy love-child of emacs and iA Writer. "
My favorite emacsen bindings + iA Writer's clean typography. I LOVE IT SO MUCH!
Stress-tested with a 100M text file:
- Opens the file in half a second
- Scrolling is instant and lag-free
- Search and scroll-to-first occurrence is instant
- Select, cut and paste of all text takes ~1s
In short: Bonkers.
Oh, yeah, and of course, it's 100% portable C. Zero Swift: microui, SDL2, OpenGL and stb_truetype.
And finally, for anyone interested, the bindings and chords for writing, in the order of my personal muscle-memory-ness:
- C-a (beginning of line)
- C-e (end of line)
- C-f (forward one character)
- C-b (backward one character)
- C-n (next line)
- C-p (previous line)
- M-f (forward one word)
- M-b (backward one word)
- M-> (end of buffer sets mark)
- M-< (beginning of buffer sets mark)
- C-k (kill to end of line, consecutive kills append)
- C-y (yank, paste from kill buffer)
- C-/ (undo)
- C-Space (set mark)
- C-w (kill region, cut)
- C-g, ESC (cancel mark)
- C-s (start/next forward search)
- C-r (start/next backward search)
- C-f / C-b (next/prev match while searching)
- C-g (cancel search)
- C-x C-s (save file)
- C-x C-c (quit)
- Enter/Escape (exit search, keep position)
- Backspace, Delete, Enter work as expected
Alright! "Loop Engineering" is the term we're using? Works for me. Here's my latest loop engineering project. Built on @NimaSiboni's recent "The Heuristic Scientist: Open-Ended Algorithm Discovery with LLMs" workshop at @TUBerlin.
I think my take on it came out nice AND I found some nifty new levers that proved to be super useful, especially the auto-pivoting facility.
"Auto-Pivoting on patience"
Give the agent a patience — how many rounds it may go without a new best. Spend it, and it must pivot: drop the current line for a genuinely different groundrule. Our main guard against rabbit-holes.
"Runs that build on runs"
A search isn't one fixed run. Each new run inherits the champion — the best groundrule so far — and climbs from there, while you change the model, the patience, the library around it.
"Hand-curated inspo"
The library is an optional, human-written input — notes, framings, even a personality handed to the agent before it thinks. It doesn't fix the answer; it shapes the frame the search starts from.
"Run it on your own hardware"
The loop talks to any OpenAI-compatible endpoint, so the proposing model can run locally — LM Studio, or anything serving the same API. Point it at your own hardware and the search runs unmetered: no rate limits, no quota walls.
https://t.co/cMbVXFLqfE
Yesterday I organised Europe’s first community Cafe Compute with @cerebras in Berlin!
We had over 200 signups and ~80 people join us to talk about fast inference and running frontier intelligence at the speed of 1000+ tokens per second.
Special thank you for Cerebras and @communidiyi for entrusting me with the Ambassadorship and @WigetJanette with @aicampusberlin for hosting us and helping me organise this evening.
In the first half we had Zigfrid (Solutions Architect at Cerebras) join us and answer all the questions we had about what they do and how their chips work.
And in the second half we had great demos from the community:
@slobkebap presented a real time GenUI flow to build UI in realtime by talking to it using @OpenAIDevs's realtime v2 api combined with Cerebras GLM-4.7
@SpringStreetNYC presented his autonomous AI research lab experiment in which he tried to teach a small model to ask great questions on the level of frontier models.
Hoang Minh showcased how he finds vulnerabilities in big OSS projects very fast and helps patch them.
And my personal favourite demo that night: @leolurch, who showed us his machine learning pipeline to find lost art pieces on auction platforms. Basically face recognition but for art, to recover potentially stolen or simply lost art from the last centuries.
I had so many cool chats and am glad that so many very talented people showed up.
Thank you everyone for coming!
And thank you so much @0xSero for sharing the event!
Me, trying to touch the future while giving a quick demo of "'Which city in Paris are you staying in?'–Can an LLM autoresearch loop teach a phone-sized small language model (SLM) to ask frontier-quality questions? Can it? Does it? Let's find out!"
Hey @LumaHQ! You app is absolutely fantastic. In only three weeks, I've been to five top-notch events meeting new, totally cool people.
But now that you've solved meeting new people for (thank you), I have a NEW problem:
As the events start to wrap up, we often want to stay in touch. Cool! Yay!
Now, to "connect-connect", the norm is to use LinkedIn. So, now I've to go back to (*shudder*) LinkedIn as well. You know, that place. And it's super-duper awkward: their app has a QR-code contact scan thing that gets more embarrassing every passing second while you're both fiddling with your phone ("...oh, doesn't work, there's a glare on your screen. Oh, it's my camera?...")
After yesterday's event (awesome btw.), I seriously consider printing contact cards. But then, what do I put on there? My phone? My email? My Twitter? And then?
What actually HAS worked a few times: I meet them, memorize their first name, then go to Luma, check the participant list (when it's visible) for their first name, when there are multiple "Davids", deduce based on first impressions which one and then try to find them online. Somehow.
So, team Luma, as a huge fan: I would like to ask you to let me find and connect and stay in touch with these new peers via your app. Thank you so much :)
@iGayProMax Found it! She's Lost Control from Bains Douches Paris 1979 remastered complete version (free CD version out of print) by JOY DIVISION at https://t.co/mgNRFEvlg1
LOL, you mean like ship those beautiful translucent iMacs in 1999 or bring FreeBSD to the masses without anyone even noticing?
I don't know what the analogies for that are today but tweaking icons is not that. 🤪
Dear #wwdc
Right now and somewhere, the next Kane Parsons/Jony Ive/Steve Jobs is graduating from/dropping out of college. Given today's demos, they're CLEARLY NOT anywhere near SV but I'm sure you can find them.
PLEASE do and put them on those same $840k/year salaries. Give them a year or so. Let them define the next two decades IN and ON their own terms.
Thank you.
Dear #wwdc
Right now and somewhere, the next Kane Parsons/Jony Ive/Steve Jobs is graduating from/dropping out of college. Given today's demos, they're CLEARLY NOT anywhere near SV but I'm sure you can find them.
PLEASE do and put them on those same $840k/year salaries. Give them a year or so. Let them define the next two decades IN and ON their own terms.
Thank you.
@thomaspaulmann Hah! That's exactly what I would like. 1h of my time back, please.
Each demo was backrooms-stale-air-empty-eyed-gaze weirder than the one before. Like what.
@_ralRo@SchallerDomenic@tim_cook Jupp. Ich bin auch sprachlos.
Ein kleiner Teil in mir will glauben, dass das alles AI-generierten Figuren waren und es deswegen so ein Uncanny-Valley Gefühl ausgelöst hat.
I don't know. Einfach weird.
@LPirro93 No, you're not getting old. In my opinion, this was really, really uninspired.
Been an Apple customer for 26 years myself. There was nothing about today that would have resonated with me way back in 1999.
(And I wasn't even a Jobs-fan, tbh.)