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

GPT‑5.3‑Codex‑Spark

openai.com

Post reply on HN
Print view View original

341–350 of 415 posts

Re: GPT‑5.3‑Codex‑Spark

#341

Post by aurareturn »

jychang wrote: post #334
HumanOstrich wrote: post #326

Earlier quoted context omitted.

Uh, the combined offering (smaller model + ~800 tps on cerebras) is nothing like the previous mini offerings, and you're hallucinating details about their process of creating it. Read more about how Cerebras hardware handles clustering. The limit is not 44 GB or 500GB. Each CS-3 has 1,200 TB of MemoryX, supporting up to ~24T parameter models. And up to 2,048 can be clustered.

Yeah, it's pretty clear you're loud mouthed and don't know anything about distilling ML models or anything Cerebras. Distilling ML models into smaller mini versions is basic stuff. How do you think Qwen 3 235b and Qwen 3 30b were made? Or GLM 4.5 355b vs GLM 4.5 Air 105b? Or Meta Llama 4 Maverick and Scout? And everyone knows that the reason Cerebras never served Deepseek R1 or Kimi K2 or any other model bigger than…

Yes. In order to serve 1k/s, they must be fitting the entire model on SRAM and not reaching out to off chip RAM. This means they’re likely chaining multiple wafer chips together to serve this model or they shrunk the model to fit one wafer chip. It’s uneconomical for many use cases but for highly valuable tasks, it could be worth it.

This is one area Nvidia chips have not been able to do, ultra fast, ultra high value tasks. Hence, the Grog acquisition.

Re: GPT‑5.3‑Codex‑Spark

#342

Post by c0balt »

ash_091 wrote: post #319
dotancohen wrote: post #277

Earlier quoted context omitted.

> 46,255 mm² To be clear: that's the thousandths separator, not the Nordic decimal. It's the size of a cat, not the size of a thumbnail.

*thousands, not thousandths, right? The correct number is fourty six thousand, two hundred and fifty five square mm.

or about 0.23 furlongs

Re: GPT‑5.3‑Codex‑Spark

#343

Post by c0balt »

zozbot234 wrote: post #276
elorant wrote: post #233

Earlier quoted context omitted.

There have been discussions about this chip here in the past. Maybe not that particular one but previous versions of it. The whole server if I remember correctly eats some 20KWs of power.

A first-gen Oxide Computer rack puts out max 15 kW of power, and they manage to do that with air cooling. The liquid-cooled AI racks being used today for training and inference workloads almost certainly have far higher power output than that. (Bringing liquid cooling to the racks likely has to be one of the biggest challenges with this whole new HPC/AI datacenter infrastructure, so the fact that an aircooled rack ca…

> Bringing liquid cooling to the racks likely has to be one of the biggest challenges with this whole new HPC/AI

Are you sure about that? HPC has had full rack liquid cooling for a long time now.

The primary challenge with the current generation is the unusual increase of power density in racks. This necessitates upgrades in capacity, notably getting 10-20 kWh of heat away from few Us is generally though but if done can increase density.

Re: GPT‑5.3‑Codex‑Spark

#344

Post by hackrmn »

capevace wrote: post #30

Seems like the industry is moving further towards having low-latency/high-speed models for direct interaction, and having slow, long thinking models for longer tasks / deeper thinking. Quick/Instant LLMs for human use (think UI). Slow, deep thinking LLMs for autonomous agents.

Like different parts of the brain. Frontal cortex, speech center (in the back), motorics etc.

Re: GPT‑5.3‑Codex‑Spark

#345

Post by HumanOstrich »

jychang wrote: post #334
HumanOstrich wrote: post #326

Earlier quoted context omitted.

Uh, the combined offering (smaller model + ~800 tps on cerebras) is nothing like the previous mini offerings, and you're hallucinating details about their process of creating it. Read more about how Cerebras hardware handles clustering. The limit is not 44 GB or 500GB. Each CS-3 has 1,200 TB of MemoryX, supporting up to ~24T parameter models. And up to 2,048 can be clustered.

Yeah, it's pretty clear you're loud mouthed and don't know anything about distilling ML models or anything Cerebras. Distilling ML models into smaller mini versions is basic stuff. How do you think Qwen 3 235b and Qwen 3 30b were made? Or GLM 4.5 355b vs GLM 4.5 Air 105b? Or Meta Llama 4 Maverick and Scout? And everyone knows that the reason Cerebras never served Deepseek R1 or Kimi K2 or any other model bigger than…

Yea, it's pretty clear you're loudmouthed and an aggressively arrogant know-it-all (at least you think). You keep moving the goalposts too. First you're acting like they can't run models that don't fit in 44GB or 4x44GB. Then you say they can "only" run a larger model at 500 tps but that wouldn't be profitable.. Lol

Cerebras CURRENTLY serves GLM-4.7. I've used it through their API. Look up how big it is. 1,000-1,700 tps. https://www.cerebras.ai/blog/glm-4-7

Not interested in further conversation, so have a nice day! You can go ahead and get in the last word though.

Re: GPT‑5.3‑Codex‑Spark

#346

Post by bothlabs »

The Cerebras partnership is the most interesting part of this announcement to me. 1000+ tok/s changes how you interact with a coding model. At that speed the bottleneck shifts from waiting for the model to keeping up with it yourself.

Curious how the capability tradeoff plays out in practice though. SWE-Bench Pro scores are noticeably lower than full 5.3-Codex. For quick edits and rapid prototyping that's probably fine, but I wonder where the line is where you'd rather wait 10x longer for a correct answer than get a wrong one instantly.

Also "the model was instrumental in creating itself" is doing a lot of heavy lifting as a sentence. Would love to see more details on what that actually looked like in practice beyond marketing copy.

Re: GPT‑5.3‑Codex‑Spark

#348

Post by gizmodo59 »

antirez wrote: post #20

The search for speed is vain. Often Claude Code Opus 4.6, on hard enough problems, can do the impression of acting fast without really making progresses because of lack of focus on what matters. Then you spin the much slower GPT 5.3-Codex and it fixes everything in 3 minutes of doing the right thing.

Codex 5.3 is hands down the best model for coding as of today

Re: GPT‑5.3‑Codex‑Spark

#349

Post by ewuhic »

bothlabs wrote: post #346

The Cerebras partnership is the most interesting part of this announcement to me. 1000+ tok/s changes how you interact with a coding model. At that speed the bottleneck shifts from waiting for the model to keeping up with it yourself. Curious how the capability tradeoff plays out in practice though. SWE-Bench Pro scores are noticeably lower than full 5.3-Codex. For quick edits and rapid prototyping that's probably fi…

More like shifts from waiting for the model to https://xkcd.com/303/ .

Unless you use garbage languages, of course.

Re: GPT‑5.3‑Codex‑Spark

#350

Post by fifilura »

c0balt wrote: post #342
ash_091 wrote: post #319

Earlier quoted context omitted.

*thousands, not thousandths, right? The correct number is fourty six thousand, two hundred and fifty five square mm.

or about 0.23 furlongs

More like one thousanth percent of an acre.

(wow, that is not much?)

Post reply on HN