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

A week of using Codex more than Claude

allaboutcoding.ghinda.com

Post reply on HN
Print view View original

221–230 of 311 posts

Re: A week of using Codex more than Claude

#221

Post by timr »

defrost wrote: post #210
socalgal2 wrote: post #209

Earlier quoted context omitted.

Elon is not a literal Nazi.

Sure, way to young for that; but he is very much cut from the Nazi adjacent, racist, antisemitic, antidemocratic, technocratic views of his whole heartedly apartheid embracing grandfather Joshua N. Haldeman. His grandfather wrote his tracts to raise an alarm about what he called “mind control,” on the radio and television, where “an unconditional propaganda warfare is carried on against the White man.” ~ https://www.…

So, your argument is that his grandfather wrote something, once, so therefore we can't use Grok? Is that about right?

Man, politics are a hell of a drug. Guilt-by-association tu quoque logic is just fine when it's someone you don't like.

Re: A week of using Codex more than Claude

#222

Post by seanmcdirmid »

lostmsu wrote: post #194
seanmcdirmid wrote: post #139

Earlier quoted context omitted.

If politics isn’t a concern, why not just use deepseek?

DeepSeek is much dumber at the moment. It's barely better than Qwen3.8 27B that you can run locally.

I run both (I have an max with 64GB if ram, so local models get used a lot) and DeepSeek is definitely smarter in my experience. But again, I have my own way of using it that works for me.

Re: A week of using Codex more than Claude

#223

Post by greenavocado »

jmaker wrote: post #99
217 wrote: post #10

while everyone is somehow still stuck on and fascinated by claude, heres your quick update on the sota of coding models and harnesses mid august 2026 codex is good, both cli and desktop app, you get lots of usage on any plan. sol is good! and gets the job done, write or dictate a very long and thoughtful prompt, and leave sol xhigh or max fast working on it for an hour or so omp is an amazing harness, any feature cla…

I don’t get how Claude is considered providing “unlimited” quotas. I use up my 5h on Max $100 and Team Premium in 2-3h of relaxed use of Opus 5 high+ on fresh sessions with just a couple skills/plugins. And my weekly quotas are gone in 3 days of such relaxed use. With Codex my $100 weekly quota is used up within 3 days with Sol high+ too. Im not convinced to pay $200 for Claude’s models. With Claude, I have to interv…

I'd start by disabling all plugins and MCPs. You'd be surprised how quickly those can annihilate usage and cache coherency

Re: A week of using Codex more than Claude

#224

Post by jsmith99 »

felipeerias wrote: post #133

I use Claude Code with a MCP that lets it communicate with Codex and tell it to “iterate until both of you are happy”. The agents then go for several rounds criticising each other plans and implementations, catching big and small issues on each other’s work. The end result is not perfect, but it is a lot better than what I can get from relying on only one model.

I do a similar thing manually and you have to watch it very carefully to avoid over engineering, ironically you need judgement here not vibe, otherwise (codex especially) will ratchet the project into some complicated enterprise grade over engineered monstrosity by eg coming up with minor visual-only concurrency bugs that would need you to be Facebook scale.

Re: A week of using Codex more than Claude

#225

Post by mindwok »

joddystreet wrote: post #216

I have completely moved away from Claude to Codex. OpenAI models are better at following instructions and skill use. Claude generates more code, tries to build things that are not planned or needed, repeats same mistakes over and over. Chatgpt on the other hand just does enough, within a project would not repeat the same mistakes, tries to guess your workflow, so you don’t have to ask it to run the same. If you need…

I think the conclusion is a little too strong but mostly agree, Codex feels like a chisel and Claude feels like a wrecking ball.

Re: A week of using Codex more than Claude

#226

Post by andai »

c0rruptbytes wrote: post #117
217 wrote: post #10

while everyone is somehow still stuck on and fascinated by claude, heres your quick update on the sota of coding models and harnesses mid august 2026 codex is good, both cli and desktop app, you get lots of usage on any plan. sol is good! and gets the job done, write or dictate a very long and thoughtful prompt, and leave sol xhigh or max fast working on it for an hour or so omp is an amazing harness, any feature cla…

Pi by itself is more than capable, OMP is okay but you really don't need much for a great harness (these models are RL trained to hell to be a coding agent, sometimes less is more) I run a lot of SlopCodeBench - https://github.com/michaelasper/benchmarks Fable/Sol/GLM 5.3/Kimi are its league (in that order) Deepseek/Opus is solid Qwen 27B is the floor - there's no reason to use Sonnet/Terra/Haiku For everyday activit…

> you really don't need much for a great harness (these models are RL trained to hell to be a coding agent, sometimes less is more)

To be precise, you need a while-loop, user input and bash.

It's about 50 lines of Python: https://minimal-agent.com/

I built my own agent based on this and use it every day.

Re: A week of using Codex more than Claude

#227

Post by rossant »

slopinthebag wrote: post #40

Kinda interesting reading people comment with completely contradictory anecdotal experience with the various models.

I was about to say the same thing. I wish people gave some indication on the type of tasks they use the models with. Which kind of software, industry, programming languages, or even non-coding tasks. I suspect the experience might be vastly different from one type of task to another.

Re: A week of using Codex more than Claude

#228

Post by rossant »

aleksiy123 wrote: post #7

Agree with most of these. One thing I don’t love about codex/sol is I find it tends to overengineer and be overly cautious. I was using it to do create some scraping + data processing. It went kind of crazy on the provenance, need at least 3 sources of consensus before promoting facts type bullshit. defined a bunch of enums and gates. I just wanted scrape some site data and put it into a SQLite dB. Like chill codex.…

Yes, codex/sol is extremely meticulous and obsessed with details. It will happily massively over engineer things to reduce the number of failure modes as much as possible. It's up to the user to instruct it to "chill" if this level of robustness is not necessary for a given task.

Re: A week of using Codex more than Claude

#229

Post by ptrl600 »

transdev12 wrote: post #44
beering wrote: post #2

> Changes created by Codex had fewer comments in Ruby/Ruby on Rails code. I liked that a lot, and I will soon share some experiments I ran on this. Why is fewer comments a good thing?

Claude comments look like this //add returns the sum of x and y //per section 2.1 of addition-implementation-plan.md sum is designed as the seam for user addition interfaces. //previously sum added numbers, now it adds numbers def add(x, y): return x + y

Not subtraction, not division.

Re: A week of using Codex more than Claude

#230

Post by cromka »

socalgal2 wrote: post #209
sharlos201068 wrote: post #204

Earlier quoted context omitted.

There's a difference between not trusting a company because it's a company driven to chase profit at the expense of everything else, versus the same thing but it's run by a literal nazi that uses his companies as leverage to undermine democracy and enrich himself.

Elon is not a literal Nazi.

He does the same exact literal Nazi things that Nazi did and has Nazis in his family tree. You'll need better arguments to defend him than just "I don't agree".
Post reply on HN