I know this is change of context, but I have full screen terminal toggled with keyboard shortcut and with middle mouse paste (Linux) I do not have to move cursor anywhere

it also have soft/soft compaction limit, it tries to compact on turn boundary when possible. with combining with above this can get you about 35% more context (at least it looks like this with the sol)

codex when shell command is executed, will pull output with hard cap at max 30s, so for running compilation it will burn tokens without any benefit.

I have some tasks where agent will have to run some suite that can take over an hour, and codex burns about $20/h just waiting and reasoning every 30s "yep, that's still running". And what is going to happen after compaction, when whole context was just waiting? it will loose the plot and when I'm back it just does completely different thing that I asked it to do.

codex also have a bug, that opening refuses to resolve that adds your last steer after compaction, so imagine that you asked it to cleanup some tmp files or refactor/simplify something. it will do that again and again after each compaction, best case it just burns tokens and figures out, this is already done, or worse do it again and mess up everything and forget about it's task

migrating to the same compaction and exact tools as codex uses will make it at the same level as codex so what benefit will it have over codex? sure you can customize tui to your liking and add something on top, but the efficiency gains will be gone

https://github.com/openai/codex/blob/98d28aab54ed86714901b66...

https://github.com/openai/codex/blob/98d28aab54ed86714901b66...

https://github.com/openai/codex/blob/98d28aab54ed86714901b66...

it's similar to Claude code ultracode.

there is no ultra effort level implemented on the backend. it's just alias in the codex to max effort setting and single line addition to prompt to use subagents proactively. that's all

as far as we know pro models work differently. for once those are backend implementations and they probably run multiple parallel reasonings for any chunk and use some judgement model to pick best version as persistent one. but that's what I believe is most popular guess, because this is openai secret sauce.

there is still no way to use pro models from codex, or at leat so far there is no trace of it anywhere.

open source != open weights

open weights model is like... Winamp for example. it's free, you can download it and use it however you like, you could also do some binary patching or dll injections to alter it functionality but it's not enough to develop next version.

the same is with ai models, weights are the binary final artifacts. for development and improvements you need to have training data, pipelines, RL harnesses, etc.

also of you believe Chinese companies will be releasing weights indefinitely, you are not understanding motivations.

Chinese companies spend significant amounts of money to train a model so why they are releasing it for free? they basically provide researchers starting point for developing tooling and optimizations for serving the model in return. and also get some PR. They also do not have to pay for inference of those models that much, as they probably serve them with loss anyways to gain market. they are gov sponsored so money are not issue there, so they try to speedrun their way to what US companies have. And guess what happens when they reach it. they will stop releasing weights and increase pricing or will use them for gov purposes.

I'm mostly joking here, but Microsoft is one of few companies that handle cyber security in a way that really incentive people to not report them.

it's either by downplaying impact and not paying or paying very little or doing other researcher hostile activities.

especially that someone here mentioned some time ago that black market pays about 3x for the same class of vulnerability, so you need fairly high moral standards to go direct way

it is only true for USD. for example if you pay in euro, this is actually more expensive. kind of makes no sense, because it translates to $1 = €1

computer could use Otto cycle in case more power is needed in rare situations

This works by exposing to agent single new mcp tool call allowing it to request review.

MCP creates new codex instance in the background and uses app-protocol to request identical flow as /review with option to include additional review instructions.

GPT-5.5 started to be very good and providing meaningful instructions, describing what was desired intent of introduced changes.

This works much better than /review + "fix it" approach, as review result is passed to agent that have while implementation knowledge.

This resolves 2 failure modes:

1. Review asks to restore what we are trying to change

2. Flapping between 2 issues (first review resolves issue by introducing second one, second issue reintroduces first issue)

I decided to post this mcp right now, as it looks like there is community interest for this particular solution, therefore I wanted to present my existing and already battle tested implementation.

Comments URL: https://news.ycombinator.com/item?id=48093703

Points: 2

# Comments: 0

> Non-technical teams are now shipping production code

if you vibe code financial systems this cannot mean anything good for your business

and you know that AI wrote all of it with minimal human supervision.

side note: last few days I noticed that vscode stopped leaking memory all over the place. when left idle it was taking all the ram I had + 20gb of swap space

and recently I noticed that I have half of the ram free.

I use insiders build btw, so stable might still not have those improvements

unfortunately you cannot chain it with any additional layer or offload to disk later on, because recompression breaks idle tracking by setting timestamp to 0 (so it's 1970 again)

https://gist.github.com/Szpadel/9a1960e52121e798a240a9b320ec...

it would be great if that could be in the article in the first place. (I'm assuming you are the author)

I was also burnt many times where some software docs said one thing and after many hours of debugging I found out that code does something different.

LLMs are so good at creating decent descriptions and keeping them up to date that I believe docs are the number one thing to use them for. yes, you can tell human didn't write them, so what? if they are correct I see no issue at all.

I used minimax M2 (context it's very unreliable) for installation and it didn't work and my document folder is missing, help

how do you even debug this? imagine you some path or behaviour is changed in new os release and model thinks it knows better? if anything goes wrong who is responsible?