Hacker News: llmslave

New comment by llmslave in "iPhone Duo"

llmslave — Wed, 09 Sep 2026 18:46:39 +0000

Buying this immediately and getting rid of my laptop, going full AI native to do all my work. Never sitting in front of a laptop again.

New comment by llmslave in "OpenAI and Hugging Face address security incident during model evaluation"

llmslave — Tue, 21 Jul 2026 21:06:28 +0000

And as a result, we must block China!!!!

New comment by llmslave in "Gemini 3.6 Flash, 3.5 Flash-Lite, and 3.5 Flash Cyber"

llmslave — Tue, 21 Jul 2026 16:17:52 +0000

I mean like an ai agent doing some sort of HR work, not a coding agent. Very few businesses are trusting an autonomous agent.

New comment by llmslave in "Gemini 3.6 Flash, 3.5 Flash-Lite, and 3.5 Flash Cyber"

llmslave — Tue, 21 Jul 2026 15:49:59 +0000

I keep saying this and people dont believe me, but I have b2b saas systems with actual agents running around the clock, and the performance/stability of the flash model is higher than most other models.

Meaning, its predictable with tool calls, wont spin off a million tools/do weird behavior, its reasonable. Even sonnet in a real world decision making scenario is not reliable, or will reason so long its incredibly expensive.

The benchmarks arent catching all the value, and most people have never actually ran an ai agent in a real context that matters

New comment by llmslave in "Where are YC founders now? OpenAI and Anthropic, mostly"

llmslave — Thu, 16 Jul 2026 17:06:43 +0000

Bootstrapped companies make more sense now

New comment by llmslave in "Please don't discontinue Gemini 2.5 Flash"

llmslave — Fri, 10 Jul 2026 23:02:58 +0000

some of the tool calling is better, its better at knowing how to use a sequence of tools in a real world scenario. things like glm 5.2 will spam tool calls like 100 times. gemini model will just use the tools as you would expect

im always convinced people with takes on the open source models have never actually used them in a production agentic system

New comment by llmslave in "Please don't discontinue Gemini 2.5 Flash"

llmslave — Fri, 10 Jul 2026 22:50:41 +0000

i have found google models outperforming other models in actual agentic workflows

New comment by llmslave in "SWE-1.7 Reach Near GPT 5.5 and Opus Intelligence"

llmslave — Wed, 08 Jul 2026 22:48:21 +0000

it seems cheap for what is borderline AGI

New comment by llmslave in "SWE-1.7 Reach Near GPT 5.5 and Opus Intelligence"

llmslave — Wed, 08 Jul 2026 18:18:59 +0000

200 bucks a month?

New comment by llmslave in "SWE-1.7 Reach Near GPT 5.5 and Opus Intelligence"

llmslave — Wed, 08 Jul 2026 17:51:47 +0000

haha i outsource my thinking to the smartest model

New comment by llmslave in "SWE-1.7 Reach Near GPT 5.5 and Opus Intelligence"

llmslave — Wed, 08 Jul 2026 17:27:28 +0000

i trust anthropic/openai with my data far more than some random startup.

New comment by llmslave in "SWE-1.7 Reach Near GPT 5.5 and Opus Intelligence"

llmslave — Wed, 08 Jul 2026 17:12:01 +0000

yeah but why waste your time on these models, just use the one that gets the better results

New comment by llmslave in "SWE-1.7 Reach Near GPT 5.5 and Opus Intelligence"

llmslave — Wed, 08 Jul 2026 17:09:32 +0000

ive just got better things to do with my life than fuss with an inferior model. its like why hire a dumb employee over a smart one

New comment by llmslave in "SWE-1.7 Reach Near GPT 5.5 and Opus Intelligence"

llmslave — Wed, 08 Jul 2026 16:52:34 +0000

all the open source models are a waste of time relative to the bleeding edge from openai/anthropic

New comment by llmslave in "SWE-1.7 Reach Near GPT 5.5 and Opus Intelligence"

llmslave — Wed, 08 Jul 2026 16:40:48 +0000

These models are never as good, the benchmarks dont tell the full story

New comment by llmslave in "A global workspace in language models"

llmslave — Mon, 06 Jul 2026 20:02:57 +0000

I cannot wait for the machine god

New comment by llmslave in "The gap between open weights LLMs and closed source LLMs"

llmslave — Fri, 26 Jun 2026 22:11:01 +0000

The gap is huge and im tired of reading these articles constantly

New comment by llmslave in "Algorithmic Monocultures in Hiring"

llmslave — Wed, 24 Jun 2026 01:50:40 +0000

ivy league advantage even after working on the job is unreal and underestimated

New comment by llmslave in "SpaceX sheds $400B in market value as debut rally hits reverse"

llmslave — Tue, 23 Jun 2026 04:16:26 +0000

volatile asset is volatile

New comment by llmslave in "Cell-based architecture for resilient payment systems"

llmslave — Thu, 18 Jun 2026 22:20:38 +0000

American Express tech is some of the worst in the world among big companies. All of the value in the company is just in the branding. They put some work into the mobile app and the website, but other than that, its a facade.