Hacker News: AgentMasterRace

New comment by AgentMasterRace in "Show HN: Abralo – Free, easy way to run several Claude Code agents in one window"

AgentMasterRace — Thu, 09 Jul 2026 20:05:54 +0000

or use herdr, or the many other options that don't force you to use Claude code.

New comment by AgentMasterRace in "Opinionated and easy Pi.dev configuration"

AgentMasterRace — Thu, 09 Jul 2026 20:04:34 +0000

if you know what you're doing your results will actually be good. what a dumb take.

New comment by AgentMasterRace in "GPT-5.6"

AgentMasterRace — Thu, 09 Jul 2026 19:44:21 +0000

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.

New comment by AgentMasterRace in "GPT-5.6"

AgentMasterRace — Thu, 09 Jul 2026 19:37:45 +0000

so the answer is use grok ?

New comment by AgentMasterRace in "GPT-5.6"

AgentMasterRace — Thu, 09 Jul 2026 19:00:34 +0000

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.

New comment by AgentMasterRace in "GPT-5.6"

AgentMasterRace — Thu, 09 Jul 2026 18:58:29 +0000

did you use Claude design, their tool meant for Web design? because if not then you're the problem .

New comment by AgentMasterRace in "GPT-5.6"

AgentMasterRace — Thu, 09 Jul 2026 18:56:18 +0000

he's writing novels

New comment by AgentMasterRace in "GPT-5.6"

AgentMasterRace — Thu, 09 Jul 2026 18:55:16 +0000

better, use oh my pi.

New comment by AgentMasterRace in "Grok 4.5"

AgentMasterRace — Thu, 09 Jul 2026 07:33:08 +0000

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.

New comment by AgentMasterRace in "Grok 4.5"

AgentMasterRace — Thu, 09 Jul 2026 07:31:24 +0000

The harness is commonly ranked one of the best. what specifically had you hating it?

New comment by AgentMasterRace in "EVE Online's Carbon engine is now open source: Fenris Creations explains why"

AgentMasterRace — Wed, 08 Jul 2026 16:17:18 +0000

you're the perfect victim

New comment by AgentMasterRace in "Kernel anti-cheat is an overreach"

AgentMasterRace — Tue, 07 Jul 2026 01:45:49 +0000

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.

New comment by AgentMasterRace in "GLM 5.2 and the coming AI margin collapse"

AgentMasterRace — Tue, 07 Jul 2026 01:34:01 +0000

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.

New comment by AgentMasterRace in "GLM 5.2 and the coming AI margin collapse"

AgentMasterRace — Tue, 07 Jul 2026 01:30:23 +0000

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 .

New comment by AgentMasterRace in "Herdr: Agent multiplexer that lives in your terminal"

AgentMasterRace — Tue, 30 Jun 2026 04:16:48 +0000

time to ask AI what the best features in yours and Ops are and then merge them into my also similar project .

New comment by AgentMasterRace in "Herdr: Agent multiplexer that lives in your terminal"

AgentMasterRace — Tue, 30 Jun 2026 04:14:20 +0000

Damm, looks a lot like my almost abandoned "foreman", except the mine has a background "foreman" that watches for issues and corrects them.

New comment by AgentMasterRace in "Show HN: Chess-Inspired Roguelike"

AgentMasterRace — Fri, 26 Jun 2026 00:37:57 +0000

Wait until you see my curling rogue like. Spoilerz curling fucking sucks solo.

New comment by AgentMasterRace in "A game where you're an OS and have to manage processes, memory and I/O events"

AgentMasterRace — Fri, 26 Jun 2026 00:33:01 +0000

The absolute bane of my existence, I had a time a week ago repairing my bootloader after I (stupidly) did 3 months of windows updates after running a bunch of disk repairs and other recovery based things after I (again, stupidly) fell for a fake repo for deepseek tui and infected myself

New comment by AgentMasterRace in "SpaceX to buy Cursor for $60B"

AgentMasterRace — Thu, 25 Jun 2026 17:40:29 +0000

Yes, but it requires a subscription to use it.

New comment by AgentMasterRace in "Writers and Drugs"

AgentMasterRace — Thu, 25 Jun 2026 06:08:44 +0000

Hashish is a form of cannabis.