jatora

The self-servedness vs intensity of the management of said goal is what is different. Wanting your child to be healthy is good. Steering your child to be a D&D player is questionable.

"Ranks second" is their statement. What is it's rank, in your opinion?

agreed. horrible.

Gee I wonder if this is marketing for that 1 MCP server? Yep! I won't advertise it for them, but you can safely skip this drivel.

as i said. keep thinking along those lines. more compute for those that arent fear mongered or mongering.

This sounds psychotic. An over-controlling fedora's approximation of what good academic parenting looks like. You just want to create your D&D partner. You'll probably succeed lol.

Anyone looking to use frontier SOTA on the $20 plans is going to have a bad time

damn so brave

have fun with your sub-tier models then. More compute for me

isnt native english speaker

"i really wish this thing in my non native language was easier to decipher"

huh? if you dont know the words then read them in your native language. Sol/Terra/Luna are immediately unambiguous to an english speaker with any sense.

I'll correct myself. 1 Skill for helping refine your plan/spec with propositional yes/no questions. After that no more skills needed to emulate superpowers honestly. Workflows do the rest and claude will do that for you. ultracode is 90% of superpowers

Codex has been comparable for a while. 5.1-5.5 have competed closely with 4.5-4.8. Fable blew them all out, now Sol comparable to Fable again. Some slight tooling differences with skills and hooks but for the most part I think if people are so engineered into one CLI that swapping to another inhibits them, then that is an error in usage habits.

Codex historically will follow tasks more closely with less creativity, whereas Opus will do more than you specify. I wouldnt consider either one better due to this fact, just makes them useful for different situations. Generally they'll perform similarly for most tasks.

Opus and Fable dominate 5.5 in artistic design (pixel art, ascii art), and edge out 5.5 slightly in general UI design taste. Have not tested Sol in that regard yet.

So far in my usage Sol has been superior to Fable at graphics rendering engine optimization.

Codex will work longer, and in single sessions without as much subagent usage.

Codex only has 256k context but its compaction is absolutely next level. You will not notice compactions and they will happen multiple times during a complex task or set of tasks without you ever having to notice or care. Claude code on the other hand still has fairly poor compaction.

Codex has more generous usage limits, and they also give you usage resets (weekly+5h resets) that you can bank for a month or so. Not sure how often they give these out.

Codex also seemingly never has outages or weird delays like Claude code does.

OpenAI randomly resets usage just like Anthropic does

I would use both if you code often

No thats probably because you misread what you were replying to and your comment was out of left field. They didnt imply models get better intra-releasally at all.

Short term higher profit for IPO

It does not make LLM work predictable. Try it on the same type of project twice and see. You think you're saving time but youd accomplish similar results with 2 or 3 skills.

Exactly. It really is such a ridiculous waste of time

Good call. Break up with her first before she breaks up with you.

The quoted phrase is one of the hallmarks of LLM-isms. He is 100% correct

Seconded. What a moron. Also, neoengineer... it's just an engineer. And probably a pretentious one.

No going back now.

no thx

Did you read my other comment? Seems kinda oblivious

haha woops. guess im the chinaman now

This is evidence of a bug, not the purposeful enshittification people are referencing

I could vibe code 1:6

Not sure if you're being purposely intellectually dishonest or just unaware, but the common thread on the water usage argument is literally about quantity of usage and rising prices for local areas. So as I said, somewhat related, but still two completely separate discussion topics.

I assume they are lying and still think you can use gpt 5.5 non-codex within codex cli. And they outed themselves. A lot of nonsense. And the very poor communication skills just seem like the typical chinese astroturfing you see pretty often now when discussing OAI/Claude.

The vibe-assumed claude code performance regression, yep. People should stop expecting consistent performance from non-deterministic systems. There is zero empirical corroboration of performance degredation.

There has been a step change... in the amount of whining and complaining coders exhibit lately.

Data center water use is a fairly separate topic from what this article covers. Related of course but the conversation on USE centers around actual volume use, not contaminants.

It's no secret LLM's can disseminate news in a superior fashion to 99% of human writers, when instructed properly