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

111–120 of 415 posts

Re: GPT‑5.3‑Codex‑Spark

#111

Post by p1esk »

zozbot234 wrote: post #98
p1esk wrote: post #89

Earlier quoted context omitted.

The real question is what’s their perf/dollar vs nvidia?

I guess it depends what you mean by "perf". If you optimize everything for the absolutely lowest latency given your power budget, your throughput is going to suck - and vice versa. Throughput is ultimately what matters when everything about AI is so clearly power-constrained, latency is a distraction. So TPU-like custom chips are likely the better choice.

By perf I mean how much does it cost to serve 1T model to 1M users at 50 tokens/sec.

Re: GPT‑5.3‑Codex‑Spark

#112

Post by orochimaaru »

beklein wrote: post #62
orochimaaru wrote: post #53

Earlier quoted context omitted.

How do you handle the diagrams?

In my AGENTS.md file i have a _rule_ that tells the model to use Apache ECharts, the data comes from the prompt and normally .csv/.json files. Prompt would be like: "After slide 3 add a new content slide that shows a bar chart with data from @data/somefile.csv" ... works great and these charts can be even interactive.

What about other ad hoc diagrams like systems architecture, roadmaps, mind maps, etc.

These are the bane of any staff engineers life - lol. Because people above need to know a plan in art form.

So seriously interested on how I can make it easier

Re: GPT‑5.3‑Codex‑Spark

#113

Post by bearjaws »

throwup238 wrote: post #2

Your move, Anthropic. (Yes I know they released /fast last week but I’m loving the constant oneupsmanship)

/fast is insanely expensive.

Last night it got stuck in a loop (in plan mode, I use vanilla CC) and burnt through $22 in 15 minutes.

Re: GPT‑5.3‑Codex‑Spark

#115

Post by system2 »

I stopped using OpenAI tools recently after they increased the censorship. I can't even tell it to read a screencapture software I am building because it thinks I might use it for evil purposes.

Re: GPT‑5.3‑Codex‑Spark

#116

Post by jorgenveisdal »

beklein wrote: post #41

I love this! I use coding agents to generate web-based slide decks where “master slides” are just components, and we already have rules + assets to enforce corporate identity. With content + prompts, it’s straightforward to generate a clean, predefined presentation. What I’d really want on top is an “improv mode”: during the talk, I can branch off based on audience questions or small wording changes, and the system p…

As an associate professor who spends a ridiculous amount of time preparing for lectures, I would love to try this in one of my courses

Re: GPT‑5.3‑Codex‑Spark

#117

Post by clickety_clack »

sva_ wrote: post #65
beklein wrote: post #41

I love this! I use coding agents to generate web-based slide decks where “master slides” are just components, and we already have rules + assets to enforce corporate identity. With content + prompts, it’s straightforward to generate a clean, predefined presentation. What I’d really want on top is an “improv mode”: during the talk, I can branch off based on audience questions or small wording changes, and the system p…

I love the probabilistic nature of this. Presentations could be anywhere from extremely impressive to hilariously embarrassing.

It would be so cool if it generated live in the presentation and adjusted live as you spoke, so you’d have to react to whatever popped on screen!

Re: GPT‑5.3‑Codex‑Spark

#118

Post by p1esk »

latchkey wrote: post #101
xnx wrote: post #90

Earlier quoted context omitted.

Or Google TPUs.

TPUs don't have enough memory either, but they have really great interconnects, so they can build a nice high density cluster. Compare the photos of a Cerebras deployment to a TPU deployment. https://www.nextplatform.com/wp-content/uploads/2023/07/cere... https://assets.bwbx.io/images/users/iqjWHBFdfxIU/iOLs2FEQxQv... The difference is striking.

Oh wow the cabling in the first link is really sloppy!

Re: GPT‑5.3‑Codex‑Spark

#119

Post by foobar10000 »

nikkwong wrote: post #72
wahnfrieden wrote: post #46

Earlier quoted context omitted.

It worked for me several times. It's easy to say that these increasingly popular tools are only able to produce useless junk. You haven't tried, or you haven't "closed the loop" so that the agent can evaluate its own progress toward acceptance criteria, or you are monitoring incompetent feeds of other users.

I'm definitely bullish on LLM's for coding. It sounds to me as though getting it to run on its own for hours and produce something usable requires more careful thought and setup than just throwing a prompt at it and wishing for the best—but I haven't seen many examples in the wild yet

It needs a closed loop.

Strategy -> [ Plan -> [Execute -> FastVerify -> SlowVerify] -> Benchmark -> Learn lessons] -> back to strategy for next big step.

Claude teams and a Ralph wiggum loop can do it - or really any reasonable agent. But usually it all falls apart on either brittle Verify or Benchmark steps. What is important is to learn positive lessons into a store that survives git resets, machine blowups, etc… Any telegram bot channel will do :)

The entire setup is usually a pain to set up - docker for verification, docker for benchmark, etc… Ability to run the thing quickly, ability for the loop itself to add things , ability to do this in worktree simultaneously for faster exploration - and got help you if you need hardware to do this - for example, such a loop is used to tune and custom-fuse CUDA kernels - which means a model evaluator, big box, etc….

Re: GPT‑5.3‑Codex‑Spark

#120

Post by seunosewa »

johnfn wrote: post #76
nikkwong wrote: post #29

> Our latest frontier models have shown particular strengths in their ability to do long-running tasks, working autonomously for hours, days or weeks without intervention. I have yet to see this (produce anything actually useful).

The other day I got Codex to one-shot an upgrade to Vite 8 at my day job (a real website with revenue). It worked in this for over 3 hours without intervention (I went to sleep). This is now in production.

How did you verify it?
Post reply on HN