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

Unrolling the Codex agent loop

openai.com

Post reply on HN
Print view View original

151–160 of 220 posts

Re: Unrolling the Codex agent loop

#151

Post by FuckButtons »

consumer451 wrote: post #137
behnamoh wrote: post #127

Earlier quoted context omitted.

until Microsoft buys it and enshits it.

This is a fun thought experiment. I believe that we are now at the $5 Uber (2014) phase of LLMs. Where will it go from here? How much will a synthetic mid-level dev (Opus 4.5) cost in 2028, after the VC subsidies are gone? I would imagine as much as possible? Dynamic pricing? Will the SOTA model labs even sell API keys to anyone other than partners/whales? Why even that? They are the personalized app devs and hosts!…

I can run Minimax-m2.1 on my m4 MacBook Pro at ~26 tokens/second. It’s not opus, but it can definitely do useful work when kept on a tight leash. If models improve at anything like the rate we have seen over the last 2 years I would imagine something as good as opus 4.5 will run on similarly specced new hardware by then.

Re: Unrolling the Codex agent loop

#152

Post by FuckButtons »

nubg wrote: post #122
icelancer wrote: post #72

Earlier quoted context omitted.

Their compaction endpoint is far and away the best in the industry. Claude's has to be dead last.

Help me understand, how is a compaction endpoint not just a Prompt + json_dump of the message history? I would understand if the prompt was the secret sauce, but you make it sound like there is more to a compaction system than just a clever prompt?

They could be operating in latent space entirely maybe? It seems plausible to me that you can just operate on the embedding of the conversation and treat it as an optimization / compression problem.

Re: Unrolling the Codex agent loop

#153

Post by energy123 »

fragmede wrote: post #113
hhmc wrote: post #74

Earlier quoted context omitted.

git worktrees are the canonical solution

worktrees are a bunch of extra effort. if your code's well segregated, and you have the right config, you can run multiple agents in the same copy of the repo at the same time, so long as they're working on sufficiently different tasks.

How do you achieve coordination?

Or do you require the tasks be sufficiently unrelated?

Re: Unrolling the Codex agent loop

#154

Post by consumer451 »

FuckButtons wrote: post #151
consumer451 wrote: post #137

Earlier quoted context omitted.

This is a fun thought experiment. I believe that we are now at the $5 Uber (2014) phase of LLMs. Where will it go from here? How much will a synthetic mid-level dev (Opus 4.5) cost in 2028, after the VC subsidies are gone? I would imagine as much as possible? Dynamic pricing? Will the SOTA model labs even sell API keys to anyone other than partners/whales? Why even that? They are the personalized app devs and hosts!…

I can run Minimax-m2.1 on my m4 MacBook Pro at ~26 tokens/second. It’s not opus, but it can definitely do useful work when kept on a tight leash. If models improve at anything like the rate we have seen over the last 2 years I would imagine something as good as opus 4.5 will run on similarly specced new hardware by then.

I appreciate this, however, as a ChatGPT, Claude.ai, Claude Code, and Windsurf user... who has tried nearly every single variation of Claude, GPT, and Gemini in those harnesses, and has tested all the those models via API for LLM integrations into my own apps... I just want SOTA, 99% of the time, for myself, and my users.

I have never seen a use case where a "lower" model was useful, for me, and especially my users.

I am about to get almost the exact MacBook that you have, but I still don't want to inflict non-SOTA models on my code, or my users.

This is not a judgement against you, or the downloadable weights, I just don't know when it would be appropriate to use those models.

BTW, I very much wish that I could run Opus 4.5 locally. The best that I can do for my users is the Azure agreement that they will not train on their data. I also have that setting set on my claude.ai sub, but I trust them far less.

Disclaimer: No model is even close to Opus 4.5 for agentic tasks. In my own apps, I process a lot of text/complex context and I use Azure GPT 4.1 for limited llm tasks... but for my "chat with the data" UX, Opus 4.5 all day long. It has tested so superior.

Re: Unrolling the Codex agent loop

#155

Post by straydusk »

behnamoh wrote: post #21
georgeven wrote: post #17

Earlier quoted context omitted.

I found codex cli to be significantly better than claude code. It follows instructions and executes the exact change I want without going off on an "adventure" like Claude code. Also the 20 dollars per month sub tier gives very generous limits of the most powerful model option (5.2 codex high). I work on SSL bio acoustic models as context.

codex the model (not the cli) is the big thing here. I've used it in CC and w/ my claude setup, it can handle things Opus could never. it's really a secret weapon not a lot of people talk about. I'm not even using xhigh most of the time.

Yo, mind explaining your setup in a bit more detail? I agree completely - I like the Claude Code harness, but think Codex (the model) is significantly better as a coding model.

I'm struggling with landing in a good way to use them together. If you have a way you like, I'd love to hear it.

Re: Unrolling the Codex agent loop

#156

Post by skerit »

stavros wrote: post #87
frumplestlatz wrote: post #62

Earlier quoted context omitted.

At this point I just assume Claude Code isn't OSS out of embarrassment for how poor the code actually is. I've got a $200/mo claude subscription I'm about to cancel out of frustration with just how consistently broken, slow, and annoying to use the claude CLI is.

OpenCode is amazing, though.

I switched to Opencode a few weeks ago. What a pleasant experience. I can finally resume subagents (which has been Broken in CC for weeks), copy the source of the Assistant's output (even over SSH), have different main agents, have subagents call subagents,... Beautiful.

Re: Unrolling the Codex agent loop

#157

Post by barrenko »

consumer451 wrote: post #154
FuckButtons wrote: post #151

Earlier quoted context omitted.

I can run Minimax-m2.1 on my m4 MacBook Pro at ~26 tokens/second. It’s not opus, but it can definitely do useful work when kept on a tight leash. If models improve at anything like the rate we have seen over the last 2 years I would imagine something as good as opus 4.5 will run on similarly specced new hardware by then.

I appreciate this, however, as a ChatGPT, Claude.ai, Claude Code, and Windsurf user... who has tried nearly every single variation of Claude, GPT, and Gemini in those harnesses, and has tested all the those models via API for LLM integrations into my own apps... I just want SOTA, 99% of the time, for myself, and my users. I have never seen a use case where a "lower" model was useful, for me, and especially my users.…

Is Azure's pricing competitive on openAI's offerings through the api? Thanks!

Re: Unrolling the Codex agent loop

#158

Post by andy12_ »

frumplestlatz wrote: post #62
postalcoder wrote: post #56

The best part about this blog post is that none of it is a surprise – Codex CLI is open source. It's nice to be able to go through the internals without having to reverse engineer it. Their communication is exceptional, too. Eric Traut (of Pyright fame) is all over the issues and PRs. https://github.com/openai/codex

At this point I just assume Claude Code isn't OSS out of embarrassment for how poor the code actually is. I've got a $200/mo claude subscription I'm about to cancel out of frustration with just how consistently broken, slow, and annoying to use the claude CLI is.

> how poor the code actually is.

Very probably. Apparently, it's literally implemented with a React->Text pipeline and it was so badly implemented that they were having problems with the garbage collector executing too frequently.

[1] https://news.ycombinator.com/item?id=46699072#46701013

Re: Unrolling the Codex agent loop

#159

Post by e1g »

FuckButtons wrote: post #152
nubg wrote: post #122

Earlier quoted context omitted.

Help me understand, how is a compaction endpoint not just a Prompt + json_dump of the message history? I would understand if the prompt was the secret sauce, but you make it sound like there is more to a compaction system than just a clever prompt?

They could be operating in latent space entirely maybe? It seems plausible to me that you can just operate on the embedding of the conversation and treat it as an optimization / compression problem.

Yes, Codex compaction is in the latent space (as confirmed in the article):

> the Responses API has evolved to support a special /responses/compact endpoint [...] it returns an opaque encrypted_content item that preserves the model’s latent understanding of the original conversation

Re: Unrolling the Codex agent loop

#160

Post by consumer451 »

barrenko wrote: post #157
consumer451 wrote: post #154

Earlier quoted context omitted.

I appreciate this, however, as a ChatGPT, Claude.ai, Claude Code, and Windsurf user... who has tried nearly every single variation of Claude, GPT, and Gemini in those harnesses, and has tested all the those models via API for LLM integrations into my own apps... I just want SOTA, 99% of the time, for myself, and my users. I have never seen a use case where a "lower" model was useful, for me, and especially my users.…

Is Azure's pricing competitive on openAI's offerings through the api? Thanks!

The last I checked, it is exactly equivalent per token to direct OpenAI model inference.

The one thing I wish for is that Azure Opus 4.5 had json structured output. Last I checked that was in "beta" and only allowed via direct Anthropic API. However, after many thousands of Opus 4.5 Azure API calls with the correct system and user prompts, not even one API call has returned invalid json.

Post reply on HN