Hacker Newsnew | past | comments | ask | show | jobs | submit | bytesandbits's commentslogin

I know a 10x engineer when i see one.

How can we tell who the 100x engineers are then?

In binary that's just a 10x engineer

It a hex of an engineer (no offence)

Handy with parakeet is pretty awesome by the way!


Agree. Slept on.

Wish they would do an ios version, but the creator already kind of dismissed it.


I just don't have the bandwidth to run another project, maintaining Handy is hard enough on it's own, especially for free!

I didn't just dismiss for no reason, I am a human! I have needs and I can't just sleeplessly stay in front of the computer putting out code. If I had more time I would, but alas.

Someone could easily vibe code an iOS version in a few hours. I could do the same but I do not have time to support it.


Thank you for your work, I highly appreciate it!


Thank you!!


Unlimited free Parakeet on iOS: VoiceInk

https://apps.apple.com/us/app/voiceink-ai-dictation/id675143...

(I was searching the same as you before I found this last month)


fine. I will port it myself. Real-time, sub 100ms latency. Here

https://testflight.apple.com/join/myNP5XvU


i like handy a lot, so clean


here the original NASA photos at high resolution without unnecessary ads.

https://www.nasa.gov/gallery/journey-to-the-moon/


why is a mail client needed in an onboard space computer at all?


To send email.


Until somebody remembers to read those mails, the mission will be already over and forgotten. LOL


I wonder if we could FOIA that inbox.


we constantly underestimate the power of inference scaffolding. I have seen it in all domains: coding, ASR, ARC-AGI benchmarks you name it. Scaffolding can do a lot! And post-training too. I am confident our currently pre-trained models can beat this benchmark over 80% with the right post-training and scaffolding. That being said I don't think ARC-AGI proves much. It is not a useful task at all in the wild. it is just a game; a strange and confusing one. For me this is just a pointless pseudo-academic exercise. Good to have, but by no means measures intelligence and even less utility of a model.


That's unsurprising given that a lot of our own abilities as humans come from having painstakingly acquired practices and methodologies and tools (like pencil and paper, note taking, let alone algebra, formal methods and electromechanical aids). We call this "education" but it works in a way that is more similar to agentic harnesses than to pretraining or fine-tuning. This is reflected in the fundamental different way in which children and adults learn new skills


Scaffolding is all you need. I am absolutely certain about that. It's abound finding good ways to approximate the reward function being used during post-training, but at inference time. A general enough reward that can score candidates well will inevitably improve the abilities of LLMs when put inside scaffolds.


what exactly does scaffolding mean in this context? genuine question


I'm gonna guess it means "whatever we still need humans to figure out to spoon feed the models"


anything that doesn't touch the model parameters at all once it has been compiled. for example, in streaming ASR of an encoder-decoder you can get gains in accuracy just by enhancing the encoder-decoder orchestration and ratio, frequency of fwd passes, dynamically adjusting the length of rolling windows (if using full attention). Prompting would be part of this too, including few-shot examples. Decoding strategy is also part of this (top-k, nucleus, speculative decoding, greedy or anything else). Applying signal processing or any kind of processing to the input before getting it into the model, or to the output. There are a lot of things you can do.


Also think about the program-synthesis approach proposed by Poetiq.ai. python programs are being generated and evaluated against previous examples. Then in-context learning is done programmatically via prompt concatenation. If you can "score" online the working and non working examples, then you have a very strong reward signal.


Apple



4x faster PREFILL not decode. Decode is bandwidth-bounded. Prefill is flops-constrained.


do you run two eSIMs when traveling and if so how is stability / battery life?


Always 2 SIM/esim running simultaneously. Compared to previous non-apple modem it's night and day battery-wise.

Didn't notice any issues with connection speed/stability.


incredible work


sensei karpathy has done it again


Consider applying for YC's Summer 2026 batch! Applications are open till May 4

Guidelines | FAQ | Lists | API | Security | Legal | Apply to YC | Contact

Search: