Max Wolf

serendipity maxxing

[Max Wolf @MaxWolf_01]

yapit.md turns urls and pdfs (even research papers) into clean, listenable markdown. @kepano's defuddle handles websites, a vision LLM handles PDFs and e.g. gives math spoken alt text. Free TTS in your browser, open source, self-hostable - and I didn't make UI/UX an afterthought.

[Max Wolf @MaxWolf_01]

@davidad the LLMisms got worse with each 4.x

[Max Wolf @MaxWolf_01]

@isjuustadream past weeks me is in this picture and I dont like it

[Max Wolf @MaxWolf_01]

@thdxr yes, especially since you can just think out loud.
and send that when ure stuck.
or even if you arrive at something precise, gives more nuance.

I used to have up to 5k token prompts back in jan/dec when i vibecoded stuff.

currently i like to be more in the loop, think twice

[Max Wolf @MaxWolf_01]

@_wallfacer @VictorTaelin - not all relevant knowledge is that easy
- a giant list of facts/rules does not help to generalize well

[Max Wolf @MaxWolf_01]

@VictorTaelin either we get 100mio ctx that actually works, or we'll need a new paradigm.

[Max Wolf @MaxWolf_01]

@badlogicgames 100% my experience

[Max Wolf @MaxWolf_01]

@__tinygrad__ @sama There is no (democratic) control without (democratic) ownership. Open source alone does not change that.

[Max Wolf @MaxWolf_01]

@kepano https://t.co/VgK4UFOO1X
https://t.co/zRhq5yQrSn

Some examples beyond the in-app demos:

Neuroevolution https://t.co/qfWXuhQRQX
Active Inference https://t.co/AaTplVOYNz
Tweet https://t.co/p4ccyVIedw

[Max Wolf @MaxWolf_01]

yapit.md turns urls and pdfs (even research papers) into clean, listenable markdown. @kepano's defuddle handles websites, a vision LLM handles PDFs and e.g. gives math spoken alt text. Free TTS in your browser, open source, self-hostable - and I didn't make UI/UX an afterthought.

[Max Wolf @MaxWolf_01]

@simonw ok I guess i didnt consider these might not be the highest quality data streams for many.
https://t.co/bCcKSbacMh

[Mario Zechner @badlogicgames]

@dexhorthy claw has a 30 minute heartbeat. agent gets unconditionally invoked. mutiply by a million claw instances and you have yourself a nice load on the infra.

[Max Wolf @MaxWolf_01]

@simonw how does this even make sense for them - all the data they are loosing out on?

[Max Wolf @MaxWolf_01]

@thdxr corporate needs you to find the difference

[Max Wolf @MaxWolf_01]

@badlogicgames *pianists

[Max Wolf @MaxWolf_01]

@effectfully https://t.co/MQIurjPdod

[Max Wolf @MaxWolf_01]

@zzznah Spotted in Vienna.

[Max Wolf @MaxWolf_01]

@dejavucoder claude deserves credit

[Max Wolf @MaxWolf_01]

@__tinygrad__ Minibox

[Max Wolf @MaxWolf_01]

@VictorTaelin good idea. so far ive had this spread out in task (issue) and knowledge files, but a) claude is lazy b) he's (absolutely) right because the 200k ctx window is too small c) I thought about a centralized file like goals/decisions.md, but questions might be more natural for this

[Max Wolf @MaxWolf_01]

yess this is exactly what I wanted to build myself - or am still building because, looking at the repo, i think this can be much more bitter-lesson-pilled. the main challenge i face is sloppyfication without careful oversight, but i bet 10-100x longer contexts completely solve this. I've also only used my setup interactively due to this. Having the agent dream and so on in the background is also simply bottlenecked on context (and token costs...) still, in my experience.