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

A Research Preview of Codex

openai.com

Post reply on HN
Print view View original

141–150 of 487 posts

Re: A Research Preview of Codex

#141

Post by bmcahren »

fabrice_d wrote: post #98
fourside wrote: post #89

Earlier quoted context omitted.

> You still need to do a lot of work to get it production ready, but it's as if you have an infinite number of junior engineers at your disposal now all working on different things. One issue with junior devs is that because they’re not fully autonomous, you have to spend a non trivial amount of time guiding them and reviewing their code. Even if I had easy access to a lot of them, pretty quickly that overhead would…

They wrote "You still need to do a lot of work to get it production ready". So I would say it's not much better than real colleagues. Especially since junior devs will improve to a point they don't need your hand holding (remember you also were a junior at some point), which is not proven will happen with AI tools.

Counter-point A: AI coding assistance tools are rapidly advancing at a clip that is inarguably faster than humans.

Counter-point B: AI does not get tired, does not need space, does not need catering to their experience. AI is fine being interrupted and redirected. AI is fine spending two days on something that gets overwritten and thrown away (no morale loss).

Re: A Research Preview of Codex

#144

Post by Rudybega »

IXCoach wrote: post #83
IXCoach wrote: post #79

Earlier quoted context omitted.

Hey there! Lots missing here, but I had the same issues, it takes iteration and practice. I use claude code in terminal windows, and text expander to save explicit reminders that I have to inject super regularly because anthropic obscures access to system prompts. For example, I have 3 to 8 paragraph long instructions I will place regularly about not assuming, checking deterministically etc. and for most things I hav…

Its a total of about 30 snippets, avg 6 paragraphs long, that I have to inject. for each role switch it goes through i have to re inject them. its a pain but it works. Even TDD it will hallucinate the mocks without management. and hallucinate the requirements. Each layer has to be checked atomically, but the text expander snippets done right can get it close to 75% right. My main project faces 5000 users so I cant le…

You could just use something like roo code with custom modes rather than manually injecting them. The orchestrator mode can decide on the other appropriate modes to use for subtasks.

You can customize the system prompts, baseline propmts, and models used for every single mode and have as many or as few as you want.

Re: A Research Preview of Codex

#145

Post by ilaksh »

criddell wrote: post #112
johnjwang wrote: post #80

Some engineers on my team at Assembled and I have been a part of the alpha test of Codex, and I'll say it's been quite impressive. We’ve long used local agents like Cursor and Claude Code, so we didn’t expect too much. But Codex shines in a few areas: Parallel task execution: You can batch dozens of small edits (refactors, tests, boilerplate) and run them concurrently without context juggling. It's super nice to run…

If you aren't hiring junior engineers to do these kinds of things, where do you think the senior engineers you need in the future will come from? My kid recently graduated from a very good school with a degree in computer science and what she's told me about the job market is scary. It seems that, relatively speaking, there's a lot of postings for senior engineers and very little for new grads. My employer has hired…

I don't think jobs are necessarily a good plan at all anymore. Figure out how to leverage AIs and robots as cheap labor, and sell services or products. But if someone is trying to get a job, I get the impression that networking helps more than anything.

Re: A Research Preview of Codex

#146

Post by lurking_swe »

hintymad wrote: post #116
criddell wrote: post #112

Earlier quoted context omitted.

If you aren't hiring junior engineers to do these kinds of things, where do you think the senior engineers you need in the future will come from? My kid recently graduated from a very good school with a degree in computer science and what she's told me about the job market is scary. It seems that, relatively speaking, there's a lot of postings for senior engineers and very little for new grads. My employer has hired…

> If you aren't hiring junior engineers to do these kinds of things, where do you think the senior engineers you need in the future will come from? Unfortunately this is not how companies think. I read somewhere more than 20 years ago about outsourcing and manufacturing offshoring. The author basically asked the same: if we move out the so-called low-end jobs, where do we think we will get the senior engineers? Yet c…

ahh, the classic “i shall please my investors next quarter while ignoring reality, so i can disappoint my shareholders in 10 years”. lol.

As you say, happens all the time. Also doesn’t make sense because so few people are buying individual stocks anyway. Goal should be to consistently outperform over the long term. Wall street tends to be very myopic.

Thinking long term is a hard concept for the bean counters at these tech companies i guess…

Re: A Research Preview of Codex

#147

Post by gizmodo59 »

tough wrote: post #34

so i just upgraded to pro plan but yet https://chatgpt.com/codex doesnt work for me and asks me to -try chatgpt pro- and shows me the upsell modal, even if already on the higher tier sigh

It says "Rolling out to users on the ChatGPT Pro Plan today" So it ll happen throughout the day

Re: A Research Preview of Codex

#148

Post by ilaksh »

sudohalt wrote: post #120

When it runs the code I assume it does so via a docker container, does anyone know how it is configured? Assuming the user hasn't specified an AGENTS.md file or a Dockerfile in the repo. Does it generate it via LLM based on the repo, and what it thinks is needed? Does it use static analysis (package.json, requirements txt, etc)? Do they just have a super generic Dockerfile that can handle most envs? Combination of di…

I think they mentioned it was a similar environment to what it trains on, so maybe they have a default Dockerfile. Of course containers can also install additional packages or at least python packages.

Re: A Research Preview of Codex

#149

Post by ai-christianson »

tough wrote: post #139
ai-christianson wrote: post #135

Earlier quoted context omitted.

> rather than looking at simulations You mean like automated test suites?

automated visual fuzzy-testing with some self-reinforcement loops There's already library's for QA testing and VLM's can give critique on a series of screenshots automated by a playwright script per branch

Cool. Putting vision in the loop is a great idea.

Ambitious idea, but I like it.

Re: A Research Preview of Codex

#150

Post by HappMacDonald »

bmcahren wrote: post #141
fabrice_d wrote: post #98

Earlier quoted context omitted.

They wrote "You still need to do a lot of work to get it production ready". So I would say it's not much better than real colleagues. Especially since junior devs will improve to a point they don't need your hand holding (remember you also were a junior at some point), which is not proven will happen with AI tools.

Counter-point A: AI coding assistance tools are rapidly advancing at a clip that is inarguably faster than humans. Counter-point B: AI does not get tired, does not need space, does not need catering to their experience. AI is fine being interrupted and redirected. AI is fine spending two days on something that gets overwritten and thrown away (no morale loss).

Counter-counter-point A: If I work with a human Junior and they make an error or I familiarize them with any quirk of our workflow, and I correct them, they will recall that correction moving forward. An AI assistant either will not remember 5 minutes later (in a different prompt on a related project) and repeat the mistake, or I'll have to take the extra time to code some reminder into the system prompt for every project moving forward.

Advancements in general AI knowledge over time will not correlate to improvements in remembering any matters as colloquial as this.

Counter-counter-point B: AI absolutely needs catering to their experience. Prompter must always learn how to phrase things so that the AI will understand them, adjust things when they get stuck in loops by removing confusing elements from the prompt, etc.

Post reply on HN