Hacker News: phh

New comment by phh in "Rob Pike’s Rules of Programming (1989)"

phh — Wed, 18 Mar 2026 13:25:21 +0000

Unironically. Every time I asked a LLM to make something faster, they always tried blind code optimisations, rather than measure.

New comment by phh in "Show HN: Mcp2cli – One CLI for every API, 96-99% fewer tokens than native MCP"

phh — Mon, 09 Mar 2026 10:15:24 +0000

Absoultely.

I'll add to your comment that it isn't a bug of MCP itself. MCP doesn't specify what the LLM sees. It's a bug of the MCP client.

In my toy chatbot, I implement MCP as pseudo-python for the LLM, dropping typing info, and giving the tool infos as abruptly as possible, just a line - function_name(mandatory arg1 name, mandatory arg2 name): Description

(I don't recommend doing that, it's largely obsolete, my point is simply that you feed the LLM whatever you want, MCP doesn't mandate anything. tbh it doesn't even mandate that it feeds into a LLM, hence the MCP CLIs)

New comment by phh in "Converting a $3.88 analog clock from Walmart into a ESP8266-based Wi-Fi clock"

phh — Mon, 09 Feb 2026 17:06:51 +0000

An ESP32-C3 Super Mini can be found for below 3$ (cheapest I had was 1.58€). Since the original clock is 3.88$, it can't be that much cheaper.

New comment by phh in "When compilers surprise you"

phh — Wed, 24 Dec 2025 16:33:25 +0000

Since GCC is lacking such an essential optimization, you should consider have one of your junior interviewee contribute this basic optimization mainline.

New comment by phh in "A supersonic engine core makes the perfect power turbine"

phh — Wed, 10 Dec 2025 03:13:58 +0000

You can make frequency inertia with solar (even without batteries if you accept running with a constant reserve so with reduced efficiency). Spain showed that there is a learning curve, that's for sure, but their issue was a "simple" oscillation problem that can be fixed by adjusting frequency-follow rate and grid-disconnect rules. It wasn't like a peak of energy consumption or loss of energy production that only a rotating mass could compensate.

New comment by phh in "Implications of AI to schools"

phh — Mon, 24 Nov 2025 18:55:51 +0000

80% is catastrophic though. In a classroom of 30 all honest pupils, 6 will get a 0 mark because the software says its AI?

New comment by phh in "High-resolution efficient image generation from WiFi Mapping"

phh — Wed, 01 Oct 2025 10:49:41 +0000

Is there a survey of SoTA of what can be achieved with CSI sensing you would recommend?

What is available on the low level? Are researchers using SDR, or there are common wifi chips that properly report CSI? Do most people feed in CSI of literally every packet, or is it sampled?

New comment by phh in "That Secret Service SIM farm story is bogus"

phh — Wed, 24 Sep 2025 09:36:14 +0000

I'm curious why they are using actual modems rather than just doing it with VoWifi that merely requires a SIM card reader (pretty much just an UART)

New comment by phh in "OpenAI and Nvidia announce partnership to deploy 10GW of Nvidia systems"

phh — Mon, 22 Sep 2025 19:16:15 +0000

Except I'm guessing they are not selling their equity, they are making debt backed by their equity?

New comment by phh in "Finnish City Inaugurates 1 MW/100 MWh Sand Battery"

phh — Wed, 03 Sep 2025 08:18:15 +0000

Well you can't really do -600C sand (or anything), so the benefits of sand VS water largely diminished. "just" freezing water already gives you around 300C equivalent of sand (if my napkin is correct).

Also the point of this plant is to exploit the counter-correlation of cheap electricity and cold. Usually there is a bigger correlation between cheap electricity and heat.

New comment by phh in "OpenRouter is down"

phh — Thu, 28 Aug 2025 12:03:49 +0000

Well in FP4

New comment by phh in "Kiwi.com flight search MCP server"

phh — Wed, 27 Aug 2025 16:31:43 +0000

I dream of getting mcp with interoperable micropayments before ads.

New comment by phh in "Why tail-recursive functions are loops"

phh — Tue, 12 Aug 2025 11:43:00 +0000

> > Tail recursion IME is a bigger foot gun

> This is true for some languages, but not all.

Useless anecdote that tail-recursive can be a foot gun even in Scala.

I did a (screening) job interview at Datadog, they asked for "give the spare change back on that amount of money" exercise (simple variant), "in whichever language you want". I did my implementation in tail-recursive Scala (with the annotation). I ended up trying to explain that tail-recursivity doesn't explode in memory for the rest of the call (and failed)

New comment by phh in "Show HN: Kitten TTS – 25MB CPU-Only, Open-Source TTS Model"

phh — Wed, 06 Aug 2025 08:31:13 +0000

It depends on espeak-ng which is GPLv3

New comment by phh in "Open models by OpenAI"

phh — Tue, 05 Aug 2025 21:42:32 +0000

You can technically run it on a 8086 assuming you can get access to a big enough storage.

More reasonably, you should be able to run the 20B at non-stupidly-slow speed with a 64bit CPU, 8GB RAM, 20GB SSD.

New comment by phh in "Open models by OpenAI"

phh — Tue, 05 Aug 2025 21:37:39 +0000

Well if nVidia wasn't late, it would be runnable on nVidia project Digits.

New comment by phh in "Our Farewell from Google Play"

phh — Fri, 01 Aug 2025 16:23:50 +0000

> - Gesture navigation steals user input when swiping on the left/right edges of the screen,

Well I've seen even 1B+ dl apps failing to handle that (on a Google Pixel), so at this point I'm putting the blame on Google. I've switched back to three button navigation. Though even some trivial OS gestures like screen unlock fail reliably on my Pixel 6a. (As in, I do the gesture, it fails to register the gesture, i try to make the gesture "with more conviction" through the whole screen and it still fails, and after few minutes it ends up okay somehow)

New comment by phh in "Show HN: Shoggoth Mini – A soft tentacle robot powered by GPT-4o and RL"

phh — Wed, 16 Jul 2025 07:49:57 +0000

Kyutai's unmute has great latency, but requires a fast small-ish, non-thinking, non-tooled LLM. What I'm currently working on is merging both worlds. Take the small LLM for instant response, which will basically just be able to repeat what you said, to show it understood. And have a big LLM do stuff in the background, and feeding back infos to the small LLM to explain intermediary steps.

New comment by phh in "Hugging Face just launched a $299 robot that could disrupt the robotics industry"

phh — Wed, 09 Jul 2025 15:16:16 +0000

So, my brain defaulted to "people are smart, so it makes sense", so it understood it as "it's the toy you keep within reach". But if you look at Pollen Robotics product, you see they have a "Reachy", which can indeed move, and has arms to interact with its environment. So yeah, it's a weird name. It reaches your heart through the feeling it communicates to you with its antennas?

New comment by phh in "Hugging Face just launched a $299 robot that could disrupt the robotics industry"

phh — Wed, 09 Jul 2025 15:12:34 +0000

Looking at the BOM (6 cheapest servos, one usb camera, a usb hub, a microctronller ,two mics, 30cm-high low-precision plastic) the price looks fairly realistic to me. I could imagine it at half the price on aliexpress. The manufacturing or sourcing doesn't seem complicated. So overall it looks like a very realistic endeavor.

The only negative point I see: Pollen Robotics doesn't seem used to do mass market/cheap products. But as I said, it seems to be a pretty simple production (I mean, they are probably running everywhere like crazy because nothing is ready and everything is broken, but they should be able to accomplish this)