Hacker News new | past | comments | ask | show | jobs | submit
loading story #48849198
loading story #48849608
Ok long time Claude Code user here; lately I've started to realize there's other great models out there I should be trying, but I'm hesitant to leave Claude Code behind for something new.

What's the consensus today on codex vs claude code, does it really matter anymore?

Codex has arguably been better than Claude Code for months now, but it's flown under the radar because it just didn't capture the same viral marketing effect and OpenAI in general has had more optics / PR issues than Anthropic amongst the online developer crowd. I use the word "better" not in the sense that the underlying GPT models are fundamentally smarter or more intelligent, but rather that as a product Codex is just simpler, cheaper, and abundantly reliable and low-drama.
loading story #48849545
loading story #48850201
loading story #48850269
loading story #48849841
loading story #48849887
loading story #48849202
loading story #48849496
loading story #48850530
loading story #48849910
loading story #48849572
loading story #48849981
loading story #48849229
loading story #48850441
loading story #48850419
loading story #48849156
loading story #48850353
loading story #48849148
loading story #48849854
loading story #48849281
loading story #48849831
loading story #48849918
loading story #48850102
loading story #48849366
loading story #48849191
loading story #48849242
loading story #48850047
loading story #48849255
loading story #48849186
loading story #48849849
loading story #48849620
loading story #48849818
loading story #48849320
loading story #48849455
loading story #48849153
loading story #48849581
loading story #48850295
loading story #48849812
loading story #48849356
loading story #48849174
loading story #48849267
loading story #48849243
loading story #48849536
loading story #48849204
loading story #48849466
loading story #48849385
loading story #48849215
loading story #48849208
Consensus itself does NOT matter, omp is objectively the best harness for power users yet it has 0 hn posts about it, zero.

You're fully free to use and try anything and without caring about what others think is right

I figured pi itself would be the best harness because it's barebones and you make it what you want. omp is to pi what doom is to emacs is what lazyvim is to neovim.
The fact that I thought that this was amp misspelled until i someone validate omp and the checked myself indicates it's a subjective assertion at best.
omp is really good.

I have one non technical people in my firm using it. One is using it to assist with editing books, basically using it to gather up manuscripts from e-mail / Google Doc etc. submissions, and then switch models between a cheap one and Opus (for actually analysing the manuscript).

The other non-technical person has done really surprising things with it AI, like a long-running GPT 5.5 Pro chat session which is basically her expense tracker - it has an .xlsx file "carried" in the chat, and she just tells ChatGPT (or scans a receipt) whenever she has a new expense, and then prompts it in natural language when she needs a report. I'm looking forward to seeing what she can do with omp.

Absolutely. It's the only harness that is actually RSI and not run by idiots.
How can this be "objective"? Surely its subjective.

I've tried a fuck load of harnesses but keep coming back to Codex as my harness.

> omp is objectively the best harness for power users

Care to detail this?

"objectively the best"?
loading story #48849668
loading story #48849236
loading story #48849343
loading story #48849218
loading story #48849637
loading story #48849629
loading story #48849519
loading story #48849260
loading story #48850271
loading story #48849146
loading story #48849280
loading story #48849223
loading story #48850084
loading story #48849285
loading story #48849220
loading story #48850435
loading story #48849712
loading story #48850443
loading story #48849598
5.6 Terra (mid tier model) as good as Fable on DeepSWE while cheaper than Opus API pricing. Seems like a homerun.
loading story #48849251
DeepSWE seems to strongly, strongly prefer ChatGPT models. There were also major flaws in its methodology pointed out recently, that overlap strongly with the flaws OpenAI pointed out in its SWE Verified report.

I use both ChatGPT and Claude for engineering work on a daily basis, touching performance critical code to application backends to frontend work, and I've found that DeepSWE scores don't reflect my reality when I assess high quality output from the models/harnesses.

Not that Opus always beats GPT 5.5., but that 5.5 is ahead of Opus on a general benchmark smells off to me.

loading story #48849562
loading story #48850207
loading story #48849168
loading story #48849731
loading story #48849937
loading story #48849259
loading story #48849521
loading story #48849708
loading story #48849958
Dirac (https://github.com/dirac-run/dirac, https://dirac.run/) now supports gpt-5.6. This thing does now seem to be on the chatGPT/codex accounts yet.

UPDATE: it is now available in chatGPT account also, they rolled it out

Will be there soon according to the last commits in the codex repo: https://github.com/openai/codex/pull/31684/changes

Also, confirmed it works for me by using --model gpt-5.6-sol

loading story #48849487
loading story #48849120
loading story #48850174
loading story #48850497
loading story #48850130
loading story #48849417
loading story #48849111
loading story #48849653
loading story #48849414
loading story #48849972
loading story #48849921
loading story #48850037
loading story #48849225
loading story #48849458
loading story #48849256
loading story #48849423
"GPT‑5.6 is available starting today across ChatGPT, Codex, and the OpenAI API. The rollout is starting globally now and will continue gradually toward full availability over the next 24 hours."
loading story #48849759
My Codex app got upgraded to the new unified ChatGPT app. I don't see Sol available though. Only Terra and Luna. I'm on the Pro plan. Anyone else see it?
loading story #48849868
loading story #48849947
loading story #48849322
loading story #48850030
loading story #48849289
loading story #48849235
loading story #48849323
loading story #48849557
loading story #48850448
i'm not happy with how openai is trying to pit 5.6 sol as a cheaper equivalent to fable here

for one thing, they said that on AA, sol is "within one point of fable" at 58.9 vs 59.9 but don't clarify that the latter is with safeguards where ~8% of the tasks got routed to opus

i'm not rooting for either and genuinely think that the token efficiency and cheaper price are important but this sort of thing just feels disingenuous :-/

loading story #48849273
loading story #48849250
loading story #48849234
loading story #48849861
loading story #48849779
loading story #48849290
loading story #48850053
loading story #48850019
loading story #48849136
loading story #48849159
loading story #48849863
loading story #48849465
loading story #48849272
loading story #48849427
loading story #48849658
loading story #48849254
loading story #48849217
loading story #48849213
loading story #48849165
loading story #48849679
loading story #48849210
loading story #48849602
loading story #48849721
loading story #48849253
loading story #48849118
loading story #48849212
loading story #48849103
loading story #48849167
loading story #48849443
loading story #48849164