Hacker News: siliconc0w

New comment by siliconc0w in "Pro Max 5x quota exhausted in 1.5 hours despite moderate usage"

siliconc0w — Sun, 12 Apr 2026 14:42:34 +0000

Switched back to codex for the promotion. Opus at the start of the year was GOAT- just relentless at chewing through hard problems. Now it spins on pretty easy work (took three swings just to edit a ts file) and my session is like 1-3 prompts (downgraded to the $20 plan but still)

New comment by siliconc0w in "The future of everything is lies, I guess – Part 5: Annoyances"

siliconc0w — Sun, 12 Apr 2026 04:25:44 +0000

I'm excited for the AI lawsuits and litigation. It used to be squarely in the domain of the well financed but I can see the legal system absolutely inundated with AI generated legal slop.

New comment by siliconc0w in "How We Broke Top AI Agent Benchmarks: And What Comes Next"

siliconc0w — Sun, 12 Apr 2026 02:49:05 +0000

I would love to see a stable test over time with a hold out set of easy/medium/hard challenges. I, like many others, have noticed a large drop in recent performance w/ Claude Opus (and Sonnet) and more sites like these would hold the labs more accountable to sneaky backend changes that nerf/degrade performance.

New comment by siliconc0w in "The effects of caffeine consumption do not decay with a ~5 hour half-life"

siliconc0w — Sat, 11 Apr 2026 14:22:33 +0000

Maybe if you use the pouches but I rarely 'feel' like gum like I feel like a coffee.

If I'm on vacation I don't even think about having a gum. It's only when I'm working, notice I'm dragging, and remember the option.

New comment by siliconc0w in "Show HN: Pardonned.com – A searchable database of US Pardons"

siliconc0w — Sat, 11 Apr 2026 13:54:40 +0000

We should at least ban the "preemptive" pardon if not all pardons. Pardon means forgiveness for a specific convicted crime, not a means to grant blanket immunity.

New comment by siliconc0w in "Tech job relocation market is recovering. The competition is growing faster"

siliconc0w — Fri, 10 Apr 2026 15:54:09 +0000

It needs to be a yes-and. We need to be better about fraud (digital ID + biometric proof on delivery of services) and we need a more equitable tax system that doesn't have the top .1% paying an effective tax rate lower than a school teacher.

New comment by siliconc0w in "Tech job relocation market is recovering. The competition is growing faster"

siliconc0w — Fri, 10 Apr 2026 15:52:31 +0000

Don't forget skyrocketing employer health care costs due to Government-endorsed monopoly and fraud that is the US Healthcare system. Robots don't need healthcare.

New comment by siliconc0w in "Tech job relocation market is recovering. The competition is growing faster"

siliconc0w — Fri, 10 Apr 2026 15:44:16 +0000

There is an argument that the VC-class is actually not a very good way to direct socially productive capital deployment and it'd be better to tax the LPs and direct the research using a public (but meritocratic) process.

For example China (not without its flaws) largely skipped over the digital drug phase and went straight into funding socially beneficial things like energy and materials production, AI and robotic enabled manufacturing, and large scale infrastructure build out. So ten years later they have a lot of socially productive things and we have a lot of socially unproductive things.

New comment by siliconc0w in "The effects of caffeine consumption do not decay with a ~5 hour half-life"

siliconc0w — Fri, 10 Apr 2026 15:04:14 +0000

Nicotine is also a nice alternative to coffee. I still drink coffee but past late morning I'll usually reach for nicotine because the effect is much shorter.

It also has neuro-protective effects if you're an older gentleman.

New comment by siliconc0w in "Reallocating $100/Month Claude Code Spend to Zed and OpenRouter"

siliconc0w — Thu, 09 Apr 2026 15:49:03 +0000

I'm running out of Claude session limits in a single planning + implementation session even when using sonnet for the implementation. This isn't even super complex work - it was refactoring a data model, modifying templates/apis/services, etc. It has also gotten notably more 'lazy' like it updated the data model and not the template until I specifically pointed that out.

My backup has been Opencode + Kimi K2. It's definitely not as strong as even Sonnet but it's pretty fast and is serviceable for basic web app work like the above.

New comment by siliconc0w in "We replaced RAG with a virtual filesystem for our AI documentation assistant"

siliconc0w — Sat, 04 Apr 2026 13:26:57 +0000

I'm working on a filesystem for agents for similar reasons - https://clawfs.dev - lmk if your team would like an invite..

New comment by siliconc0w in "Tell HN: Anthropic no longer allowing Claude Code subscriptions to use OpenClaw"

siliconc0w — Sat, 04 Apr 2026 04:07:06 +0000

As the demand for GPUs grows and supply cannot match it, the GPUs are going towards the enterprise and it'll be the haves vs the have-nots.

Instead of not driving to work to save fuel, frugal companies are going to have their engineers work on weekends to save tokens.

New comment by siliconc0w in "Show HN: Sup AI, a confidence-weighted ensemble (52.15% on Humanity's Last Exam)"

siliconc0w — Fri, 27 Mar 2026 18:01:14 +0000

Do you have data for other benchmarks? +7% for HLE isn't nothing but it'd be more compelling if you could show you're consistently doing better with your method across more domains (especially coding, which seems like the primary use-case these days).

New comment by siliconc0w in "AI users whose lives were wrecked by delusion"

siliconc0w — Thu, 26 Mar 2026 14:59:41 +0000

Quitting your job is a good first step but ideally you're supposed to sink $200/mo into tokens to code your AI-generated startup idea instead of hiring app developers.

New comment by siliconc0w in "Goodbye to Sora"

siliconc0w — Wed, 25 Mar 2026 13:15:17 +0000

I'm hoping a side effect of AI Slop in that by increasing volume it decreases value and people eventually start finding all Internet slop less compelling.

New comment by siliconc0w in "I Reverse-Engineered the TiinyAI Pocket Lab from Marketing Photos"

siliconc0w — Mon, 23 Mar 2026 13:52:52 +0000

Local interference really needs $50k before you're out of "toy" capability.

Given how subsidized the subscription plans are and the oss benchmaxxing vs real life performance- you're paying much more for far worse models.

New comment by siliconc0w in "Tinybox – A powerful computer for deep learning"

siliconc0w — Sat, 21 Mar 2026 22:58:53 +0000

Tinybox is cool but I think the market is maybe looking more for a turn-key explicit promise of some level of intelligence @ a certain Tok/s like "Kimi 2.5 at 50Tok/s".

New comment by siliconc0w in "Climbing the Agentic Coding Ladder"

siliconc0w — Sat, 21 Mar 2026 15:11:16 +0000

Documenting my experiments using the 'Agent Flywheel' with my current project - https://clawfs.dev.

Climbing the Agentic Coding Ladder

siliconc0w — Sat, 21 Mar 2026 15:11:16 +0000

Article URL: https://twitter.com/siliconcow/status/2035373293893718117

Comments URL: https://news.ycombinator.com/item?id=47467750

Points: 1

# Comments: 2

New comment by siliconc0w in "OpenCode – The open source AI coding agent"

siliconc0w — Fri, 20 Mar 2026 22:06:08 +0000

I reach for OpenCode + Kimi to save tokens on lower priority stuff and because it's quite fast on Fireworks AI.