Hacker Newsnew | past | comments | ask | show | jobs | submit | dharma1's commentslogin

Yes the voice part of OpenAI realtime/voice mode is great but it’s pretty dumb compared to newer models and often gets stuck repeating itself.

Google’s Gemini flash live 3.1 is better, especially used via the API - it can do tool calling (including to other, even smarter LLMs if you set it up yourself), you can set the reasoning level (even high is still close enough to realtime) and it can ground answers in google search. I love bidirectional voice and right now it’s probably the best option. You can try it in AI studio


Thanks, I’ll try it, even if my experience wasn’t that great with Google models lately (503s)

Give it a shot, 3.1 live one in AI studio/API and max out reasoning - not the one in Gemini app it’s an older model.

Another option is to use pipecat with their VAD and separate STT and TTS and any (fast) LLM of your choice - but it’s more plumbing and not a true speech to speech model


Haha, wow, I never thought I'd see a voice model that was too quick, but 3.1 live felt like it responded unnaturally quickly! I'm kind of blown away, I'd want to insert a 100ms delay to make it sound more natural, wow. I never thought I'd see that.

> Give it a shot, 3.1 live one in AI studio/API and max out reasoning - not the one in Gemini app it’s an older model.

Do you know why this is a thing? Despite the app technically being Gemini, I find it quite crap, while the AI Studio thing with thinking is my favorite LLM. Very jarring tbh.


this kind of thing is super cool to close the loop.

waiting for FPAA to get better so we can vibecode analog circuits

https://www.eetimes.com/podcasts/making-analog-chip-designs-...


I mean yeah FPAA’s would be awesome and I used to wish for something like it coming from a discrete analog hobby electronics.

But in a my short two years in Analog IC design industry, i have been so divorced from the actual silicon that I rarely got a chance yet to go in lab and probe around the teeny tiny block I worked on in the complex labyrinth of the SoC. I don’t wish for it (I learnt the hard way, be careful what you wish for; and in this case, if I am in lab debugging something in silicon, means something terrible has happened to what I worked on and it might have cost the company about $200k or more), but someday soon i will get into the lab just to play around with the fancy ass oscilloscope.

In the meanwhile, I did realize the invaluable power of having a python frontend API for querying basic details of your devices. (Python and not SKILL/Lisp since it pretty much works with any AI, and is very well worked on) and AI has been okayish with it. I feel AI would be a good aid in actual circuit design if it understood the Topology of the circuit, which at this point I am tempted to say might require something akin to AST but for SPICE. However, AI has been awesome at regexes and scripting which is also the meh and boring part of the circuit design process.


The AST idea for spice is something i've thought about too. a netlist is already a graph, the LLM just can't see it that way when it's flat text. serializing it with topology intact, adjacency, port polarities, device semantics is basically what your python frontend is doing implicitly, which explains why it behaves so much better than dumping a raw netlist into the prompt.


“Eric Schmidt, who founded Google” no he didn’t


I can understand the confusion since he was CEO for the companies most critical years.


That kind of reporting is awful.

How is it they can’t either go to Wikipedia or one of the LLMs (despite hallucinations, tend to get simple things right) and get some corroborating evidence before making such basic mistakes on an article?


Man I can’t even trust simple things these days from LLM’s. Hardly scientific but I just decided to do my own little test one time when I was on discord talking to some friends about The Game Awards back in December or so. ChatGPT would simply omit winners and/or categories - got it wrong (twice the same way, one unique way) 3 times. We tried Gemini, it gave 1 wrong answer and omitted 2 categories. It was impressive how much worse than a basic search they were at a simple “what were the results of the 2025 Game Awards?”


You are right. ChatGPT doesn’t catch this, instead catches things like CERN having 25 member states instead of 24.

I would have expected it to catch it but it did not. I’m sure pro version would have though.


[flagged]


Do you have a source on that?

I can't find anything besides he went to a Gala where he was in a photo with Maxwell and made an investment in a company her brother ran.


Schmidt is a notorious SV playboy but all of his known extra marital partners have been well into their 20s


Easy install, discord/whatsapp/tg out of the box. And some agent orchestration out of the box where the main LLM can farm out tasks to different models/agents - yes Claude code has some of this too but I think this has more


Always take d3 with k2


put the APP3 through a washing machine recently by accident and they had the high pitched feedback if NC was used until they were fully dry after a couple of days. Have also put APP2 through washing machine before but never had this


Give them enough time and they will. EUV will hit limits anyway in a decade.

For china it's DUV+packaging for now, NIL/DSA mid-term, and MoS₂/2D chips long term. But wafer scale, defect free 2D logic is 20–30 yrs out, so no EUV shortcut anytime soon


Mid 90s efnet #philosophy was great. And undernet too


Can be a couple of hundred years with trees and wood used for housing. Long enough to figure things out


Script fonts don’t really look like handwriting - too regular.

But one of the early deep learning papers from Alex Graves does this really well with LSTMs - https://arxiv.org/abs/1308.0850

Implementation - https://www.calligrapher.ai/


ooo -- thanks for the link!


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

Search: