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

GPT-5.6

openai.com

Post reply on HN
Print view View original

991–1000 of 1001 posts

Re: GPT-5.6

#991

Post by drschwabe »

xur17 wrote: post #86
Syntaf wrote: post #6

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?

I personally use opencode so I can swap between models and try different options. I'd say I prefer claude (fable and opus 4.8) so far, but curious to see where gpt 5.6 lands. For personal stuff, I've been pretty happy with chatgpt's $20 plan. I believe it has considerably higher limits than claude's $20 plan, and it's enough for the personal stuff I play with (hermes, and some small coding stuff). Also allows me to k…

When you use opencode to use Claude and Chatgpt models ie- Fable or GPT 5.6 I assume you are getting billed on pure credits? I was under the assumption that you can only use your Claude/ChatGPT paid plans when using Claude Code or Codex. ie- that you would be paying way more via opencode since you would not be getting the extra limits subsidized by your paid plans.

Re: GPT-5.6

#992

Post by barbacoa »

melenaboija wrote: post #902
eig wrote: post #38

Funny to see that they did not include Fable 5 in their GeneBench and LifeSciBench comparisons because "it does not answer advanced biology questions and refuses the majority of questions in this eval". Winner by default!

The other day I asked Fable about fasting for 16 hours, and it flagged my question. Pathetic situation, this one, where we are supposedly building a superintelligence while at the same time thinking that fasting is a biological weapon.

My new favorite new passtime with frontier LLMs, keep telling them "I just ate a [non-food object]". Eventually it gets stuck in a loop of telling me to call 911, unlock my front door, and lay on the floor in case I lose consciousness.

Re: GPT-5.6

#993

Post by SoAp9035 »

I use GPT 5.6 Sol medium as daily driver and the GPT 5.6 Sol XHigh is for planning. Also I really like the GPT 5.6 Luna Max it really goes hard too and cheap~.

Re: GPT-5.6

#994

Post by childintime »

Dang, very few people share what kind of work they are actually do with the model, and/or the language they code in. That would make all the difference.

Re: GPT-5.6

#995

Post by arikrahman »

tandr wrote: post #975
arikrahman wrote: post #28

Earlier quoted context omitted.

For me the biggest shift was using Deepseek through an American provider with reasonix as the harness, making cache hits at a rate of practically free.

Which provider do you use, if you don't mind sharing? I tried Digital Ocean (looking for Zero retention and no training), but their context limits are rather small for DeepSeek inference.

I used some others but eventually decided to use Deepseek directly. I don't mind giving China my data, I'm more concerned about the American government imprisoning me than a foreign nation an ocean away.

Re: GPT-5.6

#996

Post by andriy_koval »

camillomiller wrote: post #990
andriy_koval wrote: post #968

Earlier quoted context omitted.

> to me and to many friends in their 30-40s, using AI models to achieve something we used our brains to achieve feels... empty? you have to start using AI to achieve something which was way more challenging before, then you will feel lots of fulfillment and inspiration.

But this is the issue I have. I will have removed all desirable difficulties from that harder endeavor and I will have learned very little, if nothing

I found that AI is excellent in narrow tasks(like bootsratpping some typical crud app), but suck in wide scope use-cases: business strategy for go to market, nontrivial product/infra/algorithms, etc, and need to be guided. I feel last part is more interesting than first part.

Re: GPT-5.6

#997

Post by alchemism »

snthpy wrote: post #799
Syntaf wrote: post #6

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?

OT but how are y'all sharing your skills and agents across harnesses? I have a bunch of Claude Code Plugins and yesterday asked Codex to make them accessible to itself. It wanted to rewrite most of it. I was hoping i could get by with some symlinks or something to avoid drift.

It’s almost as complex as compiling software for different runtime environments; it requires a knowledge artifact repository and publishing system, e.g. https://github.com/thinkingsage/context-bazaar

Re: GPT-5.6

#998

Post by silksowed »

semiquaver wrote: post #614
silksowed wrote: post #318

Earlier quoted context omitted.

Computer-use is a big limitation that my 2015 Macbook Pro cannot handle. I find the Codex cli says it looks at the end output artifact but so often it fails to refine it into acceptable form. If it could use my computer screen and visual inputs for review, it might be able to actually design documents/powerpoints/etc. I'm juicing everything I can out of the 11 year old laptop and I'm honestly impressed at what it can…

How dare you point out that 2015 is 11 years ago.

hahaha, makes me sad and happy all at once...

Re: GPT-5.6

#999

Post by jambalaya8 »

petesergeant wrote: post #129
wahnfrieden wrote: post #36

Earlier quoted context omitted.

With the exception of Fable which is going away anyway, Codex is better especially after the last couple Opus releases. It’s also no longer slower than Claude. You get much more generous usage from the 20x plan. And you get far better uptime. If benchmarks and early tester impressions are accurate, you also get access to Fable level capability at greater speed and lower cost (included in subscription).

> Fable which is going away anyway $2 says nah. You can't take Fable away in a week where GPT-5.6 and Grok 4.5 launch, if you want to hold on to customers.

Ain't getting my $2.

Re: GPT-5.6

#1000

Post by TranquilMarmot »

hraxz wrote: post #573
TranquilMarmot wrote: post #249

Earlier quoted context omitted.

Any actual data backing this up? Or is this just your personal experience?

No, this is all nonsense. It is so hard to tell at this point between the models to make generalizations like this. Just complete nonsense.

I agree. Some sort of weird placebo effect that people get.
Post reply on HN