GPT‑5.3‑Codex‑Spark • Hacker News Board

Re: GPT‑5.3‑Codex‑Spark

#411

Post by xyproto » Mon, Feb 16, 2026, 4:45 PM UTC

wvbdmp wrote: post #361

xyproto wrote: post #358

Earlier quoted context omitted.

Space is also confusing! Then it looks like two separate numbers. Underscore (_) is already used as a decimal separator in programming languages and Mathematics should just adopt it, IMO.

You mean thousands separator, yes? Agreed, it’s annoying when languages don’t have this feature.

Ah yes, thousands separator.

Re: GPT‑5.3‑Codex‑Spark

#412

Post by arisAlexis » Tue, Feb 17, 2026, 1:11 PM UTC

latchkey wrote: post #387

arisAlexis wrote: post #328

Earlier quoted context omitted.

How do you know the price of a unit ?

I remembered $1m from when I was in their booth at SC24, but when I just looked, I was wrong. It is worse... https://www.datacenterdynamics.com/en/news/cerebras-unveils-...

You have no idea of the value this brings. Asml machines cost dozens of times more. So?

Re: GPT‑5.3‑Codex‑Spark

#413

Post by latchkey » Tue, Feb 17, 2026, 4:34 PM UTC

arisAlexis wrote: post #412

latchkey wrote: post #387

Earlier quoted context omitted.

I remembered $1m from when I was in their booth at SC24, but when I just looked, I was wrong. It is worse... https://www.datacenterdynamics.com/en/news/cerebras-unveils-...

You have no idea of the value this brings. Asml machines cost dozens of times more. So?

Ok, tell me the value.

Re: GPT‑5.3‑Codex‑Spark

#414

Post by dalemhurley » Tue, Feb 17, 2026, 8:23 PM UTC

SamDc73 wrote: post #143

dalemhurley wrote: post #138

This is a win for agents, speed and intelligence is crucial to the loop. If the time and token cost is small you can iterate many times to correct mistakes. Got to wonder why Wall Street is dumping NVIDIA.

I mean they are only running a small version of codex can they run the full one? Or the technology isn't there yet?

1000 tokens/sec for a highly specialised model is where we are going to see agents requiring.

Dedicated knowledge, fast output, rapid iteration.

I have been trying out SMOL models as coding models don't need to the full corpus of human history.

My most recent build was good but too small.

I am thinking of a model that is highly tuned to coding and agentic loops.

Re: GPT‑5.3‑Codex‑Spark

#415

Post by dehugger » Tue, Feb 24, 2026, 12:38 AM UTC

cheema33 wrote: post #25

dehugger wrote: post #15

Earlier quoted context omitted.

I built something similar using an MCP that allows claude to "outsource" development to GLM 4.7 on Cerebras (or a different model, but GLM is what I use). The tool allows Claude to set the system prompt, instructions, specify the output file to write to and crucially allows it to list which additional files (or subsections of files) should be included as context for the prompt. Ive had great success with it, and it r…

Why use MCP instead of an agent skill for something like this when MCP is typically context inefficient?

Late reply, but the answer is: 1) there is a fair amount of behind the scenes work going on that I dont want the agent to have access too or know about. Tools make it very easy to have strong control over what can and cannot be done. File system access is built directly into the tool, which makes it much easier to be confident about what it has access too, since the thing that actually has the permissions is the tools code, not the agent. 2) Portability, I can host it from a single spot and serve it to multiple models on different machines easily, which is very desirable for me. 3) I can update the configuration of the tool independent of a skill.

A skill wouldn't be a bad option though, and I highly recommend creating one yourself! The ability to customize our workflows and tools to a high degree is one of the largest strengths of agentic coding.