Hacker News Board Hacker News, browsed like a classic message board
Live data from Hacker News

GPT-5.2

openai.com

Post reply on HN
Print view View original

131–140 of 1001 posts

Re: GPT-5.2

#131

Post by sosodev »

dragonwriter wrote: post #116
sosodev wrote: post #73

Earlier quoted context omitted.

Does elevenlabs have a real-time conversational voice model? It seems like like their focus is largely on text to speech and speech to text. Which can approximate that type of thing but it's not at all the same as the native voice to voice that 4o does.

> Does elevenlabs have a real-time conversational voice model? Yes. > It seems like like their focus is largely on text to speech and speech to text. They have two main broad offerings (“Platforms”); you seem to be looking at what they call the “Creative Platform”. The real-time conversational piece is the centerpiece of the “Agents Platform”.

It specifically says in the architecture docs for the agents platform that it's STT (ASR) -> LLM -> TTS

https://elevenlabs.io/docs/agents-platform/overview#architec...

Re: GPT-5.2

#132

Post by minimaxir »

simonw wrote: post #125

Wow, there's a lot going on with this pelican riding a bicycle: https://gist.github.com/simonw/c31d7afc95fe6b40506a9562b5e83...

Is that the first SVG pelican with drop shadows?

Re: GPT-5.2

#133

Post by ipsum2 »

ionwake wrote: post #83
JanSt wrote: post #42

The benchmarks are very impressive. Codex and Opus 4.5 are really good coders already and they keep getting better. No wall yet and I think we might have crossed the threshold of models being as good or better than most engineers already. GDPval will be an interesting benchmark and I'll happily use the new model to test spreadsheet (and other office work) capabilities. If they can going like this just a little bit fu…

it was only about 2-3 weeks when several HNers told me "nah you better re-check your code", when I explained I have over 2 decades xp of coding, yet have not manually edited code (in memory) for the last 6 or so months, whilst performing daily 12 hour daily vibe code seshes

It really depends on the complexity of code. I've found models (codex-5.1-max, opus 4.5) to be absolutely useless writing shaders or ML training code, but really good at basic web development.

Re: GPT-5.2

#135

Post by sureglymop »

How can I hide the big "Ask ChatGPT" button I accidentally clicked like 3 times while actually trying to read this on my phone?

I guess I must "listen" to the article...

Re: GPT-5.2

#136

Post by barrkel »

lxgr wrote: post #101
sosodev wrote: post #87

Earlier quoted context omitted.

You can test it by asking it to: change the pitch of its voice, make specific sounds (like laughter), differentiate between words that are spelled the same but pronounced differently (record and record), etc.

Good idea, but an external “bolted on” LLM-based TTS would still pass that in many cases, right?

The model giving it text to speak would have to annotate the text in order for the TTS to add the affect. The TTS wouldn't "remember" such instructions from a speech to text stage previously.

Re: GPT-5.2

#137

Post by minimaxir »

granzymes wrote: post #121
minimaxir wrote: post #40

Earlier quoted context omitted.

Note that GPT 5.2 newly supports a "xhigh" reasoning level, which could explain the better benchmarks. It'll be noteworthy to see the cost-per-task on ARC AGI v2.

> It'll be noteworthy to see the cost-per-task on ARC AGI v2. Already live. gpt-5.2-pro scores a new high of 54.2% with a cost/task of $15.72. The previous best was Gemini 3 Pro (54% with a cost/task of $30.57). The best bang-for-your-buck is the new xhigh on gpt-5.2, which is 52.9% for $1.90, a big improvement on the previous best in this category which was Opus 4.5 (37.6% for $2.40). https://arcprize.org/leaderboar…

Huh, that is indeed up and to left of Opus.

Re: GPT-5.2

#138

Post by sheeshe »

ipsum2 wrote: post #133
ionwake wrote: post #83

Earlier quoted context omitted.

it was only about 2-3 weeks when several HNers told me "nah you better re-check your code", when I explained I have over 2 decades xp of coding, yet have not manually edited code (in memory) for the last 6 or so months, whilst performing daily 12 hour daily vibe code seshes

It really depends on the complexity of code. I've found models (codex-5.1-max, opus 4.5) to be absolutely useless writing shaders or ML training code, but really good at basic web development.

Which is no surprise as the data for web development stuff exists in large amounts on the web that the models feed off.
Post reply on HN