AgentMasterRace
AgentMasterRace on Hacker News
I used this service very briefly, but it's too slow as it relies on the cloud and it's way too expensive since most developers use a subscription service.
Even just Claude with basic prompts is better, but even better with skills.. and then even better with maestro scripts.
damn, I 2015 I used this as a reference for my procedural dungeon crawler. fun flashback.
you're getting robbed on the fee's
Models are trained on the same stuff, the responses are not surprising especially when it's not an jailbroken model. dumb article.
I don't see a way to edit my post.You are born with ADHD and it does not get better, so the "rare" in adults is not factual, some people just get better at managing it.
odds are you don't have severe ADHD.
What mental health and special care privileges are you talking about ? Other than having to have a special aid in school nothing has been of benefit.
Absolutely, as someone diagnosed at 6, and 33 now. Being on medication allows me to actual live my life. Ive tried to be "normal" and not be medicated various times in my life, but it's just been bad every time. Our brains are wires differently, you can't just overcome it.
My family has a long history of alcohol and substance abuse, I'm the first to be diagnosed and medicated for ADHD. If you're not medicated and have ADHD the risk of substance abuse is much higher, and there is a strong link to alcoholics being undiagnosed with ADHD.
I'm always scared of the long term effects of the medication, but without it I can't work or hardly even function.. I'm not sure of these benefits another user mentioned, but whatever they are is not worth the trade off at all.
your understanding of ADHD is outdated. say what you said to ai to get informed.
none of these are multiplexers
you're comparing apples to oranges here...
you're living in the 2020s bro
I compared it to Jev in my current use cases and it's very inaccurate. 70% vs 94% . for classification, it's unacceptable.
The website literally says they are SLM's .. derp af
his 128gb Ram laptop is quite extreme
hell yeha bro, I still rock qwen 0.1
or use herdr, or the many other options that don't force you to use Claude code.
if you know what you're doing your results will actually be good. what a dumb take.
because they're stealing from the frontier models. they're gaming the benchmarks. look how bad glm 5.2 is on cursors evals. gmhit garbage , but it gets glazed as God tier.
so the answer is use grok ?
I never have have the issues most people talk about ... I feel like most were never Devs before ai and don't know what they actually need done when prompting. that on top of not utilizing good tools such as a codebase indexer, lsp and a project scaffold.
did you use Claude design, their tool meant for Web design? because if not then you're the problem .
give it a structured plan and it it does really well compared to similar priced models. I'd never use it for anything that required heavy reasoning and it's not built for that.
The harness is commonly ranked one of the best. what specifically had you hating it?
you're the perfect victim
what a goof. yes it's a privacy risk, but so is half the things people do on the internet.
cs2 is infested with hackers, arc raiders died because of hackers... many games I've played and loved are dead because of hackers.
they're not near opus at all, anyone using the models in a real working environment will tell you the same thing. on paper they have impressive benchmarks, but that's not realistic to actual use.
I don't think the writer has used top tier models very much. I have subscriptions to basically every provider, the difference between glm5.2 and opus is not even close, the gap is huge. raw benchmarks glm is impressive , but in practice these models are lacking so much. I had fable create a detailed implementation guide that explained how to implement everything in immense detail, it included all the libraries to use and versions. I then had deepseek v4 pro execute and it used old versions , different libraries and cut corners. Fable said about 80% was implemented wrong.
I had GLM 5.2 do the same, and it performed exceptionally better, but when it got stuck on something it would be trial and error mode going forward and have zero foresight for future issues that might occur due to fixes it was trying. the model severally lacks prompt understanding, and testing .