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

Codex for almost everything

openai.com

Post reply on HN
Print view View original

391–400 of 600 posts

Re: Codex for almost everything

#391

Post by girvo »

jeremyjh wrote: post #376
girvo wrote: post #338

Earlier quoted context omitted.

I have an Asus GX10 that I run Qwen3.5 122B A10B on, and I use it for coding through the Pi coding agent (and my own); I have to put more work in to ensure that the model verifies what it does, but if you do so its quite capable. It makes using my Claude Pro sub actually feasible: write a plan with it, pick it up with my local model and implement it, now I'm not running out of tokens haha. Is it worth it from a unit…

GLM 5.1 is extremely good, and ridiculously cheap on their coding plan. Its far better than Sonnet, and a fifth of the cost at API rates. I don't know if the American providers can compete long-term; what good is it to be more innovative it only buys them a six month lead andthey can't build the data center capacity fast enough for demand? Chinese providers have a huge advantage in electrical grid capacity.

True but Z.ai also just silently raised the price, and the entire Chinese frontier set is having to make profit now... hence Alibaba killing the Lite plan and not letting people sign up to their Pro one either; and why MiniMax has their non-commercial license, etc. etc.

So I agree with you, its better than Sonnet but way cheaper. I do wonder how long that will last though

Re: Codex for almost everything

#392

Post by XDataY »

ipaddr wrote: post #313
the__alchemist wrote: post #298

Earlier quoted context omitted.

Call it fall for it, but here are my two experiences, with both applications open. ($20/month plan for both) - Claude: Good for ~20 minutes of work once every 4 hours - Codex: Good for however long I want to use it. Claude nerfed their product so that it's not usable, so I use something else.

Wow the 20 dollar Claude plan sounds awful. I use Claude at work which has metered billing and have to carefully not to hit my four figure max cap. For me $20 a month is more than I want to spend I just use the free tiers. If I use AI in an app or site I use older models mostly chatgpt3.5. The challenge is more fun and it means I can do more like, make more api calls - 100x more.

I use $20 plan for my side projects and in the beginning I was hitting limits very fast but after creating proper .md files and running /clear, it seems to work fine for my use. I am really curious how people are using $100-$200 plans. Maybe I am not utilizing to its full capacity??

Re: Codex for almost everything

#393

Post by jswny »

jimbean78 wrote: post #302
woeirua wrote: post #194

Just reading the comments here it's amazing how many people seemingly don't know that Claude Desktop and Cowork basically already does all of this. Codex isn't pioneering these features, it's mostly just catching up.

I think your making assumptions without reading the entire thread and processing the general theme. This isn't about catching up or whos better. It really comes down two things. One, how far does your money go, and secondly which political narrative you subscribe too. Up until they started their beef with the u.s. government I was a subscriber. Between that and how fast my tokens depleted I switched to Codex. Best de…

You want to use the model that is potentially giving your data to the government vs the one that’s openly rejecting that partnership?

Re: Codex for almost everything

#394

Post by lsdmtme »

bitmasher9 wrote: post #360
KronisLV wrote: post #306

Earlier quoted context omitted.

I'm on the 100 USD plan with Anthropic, I hit the 5 hour limits about 75% of the time during working hours, but almost never the weekly ones - by the time they're reset I've usually used up between 50% - 75% of the quota. There are periods of more intense usage ofc, but this is the approx. situation I'm in (also it doesn't work on tasks while I'm asleep, because I occasionally like having a look at WIP stuff and inte…

The $200 openai plan feels like 10x the limit as the $100 claude plan. But Opus is both smarter and faster than GPT, so I can get a lot more done during the Claude limits.

for now... right now you are getting 2x usage as a promo

Re: Codex for almost everything

#396

Post by lsdmtme »

com2kid wrote: post #243
woeirua wrote: post #194

Just reading the comments here it's amazing how many people seemingly don't know that Claude Desktop and Cowork basically already does all of this. Codex isn't pioneering these features, it's mostly just catching up.

IMHO no one is really pioneering. A lot more is possible than what is being done. I wrote a blog post about useful agents in a business setting ( https://www.generativestorytelling.ai/blog/posts/useful-corp... ) that highlights AI being proactive. I mean table stakes stuff, why isn't an agent going through all my slack channels and giving me a morning summary of what I should be paying attention to? Why aren't all th…

You should check out https://pieces.app/ ive been using it for months and I am surprised I have never seen anyone ever talk about it.

It does exactly what you are asking for, and it can do it completely locally or with a mixture of frontier models.

Re: Codex for almost everything

#397

Post by vunderba »

culopatin wrote: post #387
vunderba wrote: post #206

Earlier quoted context omitted.

Heavily agreed - LLMs are also really good at diagnosing crash logs, and sifting through what would otherwise be inscrutably large core dumps.

Do you think this will continue growing if we stop struggling and posting our findings on forums?

Yeah, I think that's a legitimate concern. It's hard to know, even with sufficient training data, how far these systems can actually generalize their problem-solving abilities when they become data starved in the future either because of scarcity or that any potential new training data is contaminated by LLM radiation.

Too bad we don’t have a portal gun to access an infinite number of parallel universes where large language models were never invented for sources of unlimited fresh training data and unlimited palpatine power.

Re: Codex for almost everything

#399

Post by a34729t »

solenoid0937 wrote: post #218

Codex is HN's darling now because Anthropic lowered rate limits for individuals due to compute constraints. OAI has so few enterprise users they can afford to subsidize compute for this group a lot more than Anthropic. Eventually once they have more users they'll do the same thing as Anthropic, of course. It's all a transparent PR play and it's kind of absurd to see the X/HN crowd fall for it hook, line, and sinker.

Uber, but AI!

Re: Codex for almost everything

#400

Post by throw_m239339 »

All of you are ironically completely oblivious to the fact that you're training your own replacement by using these tools, you're even paying for it. Eventually, the companies you work for will just "hire" Anthropic or OpenAI agents in your place and you'll be out of job, no matter your seniority. Mark my words.
Post reply on HN