Hacker News: CSMastermind

New comment by CSMastermind in "Claude Fable 5"

CSMastermind — Wed, 10 Jun 2026 05:23:52 +0000

I mean yes that is what you'd say if you were writing a blog post about your new benchmark.

New comment by CSMastermind in "Claude Fable 5"

CSMastermind — Tue, 09 Jun 2026 21:17:38 +0000

DeepSWE is the benchmark you want to actually look out for. Only one that aligns with actual user reported results from trying the models.

New comment by CSMastermind in "AI is slowing down"

CSMastermind — Tue, 09 Jun 2026 06:40:39 +0000

There was a point in time when this would have been untrue of Google. They didn't manifest into this market position, they rose there over the years after starting with a relatively modest product offering. Nothing saying someone else can't do the same.

Ask HN: What are the best examples of good technical writing you know of?

CSMastermind — Mon, 08 Jun 2026 01:27:18 +0000

Comments URL: https://news.ycombinator.com/item?id=48440382

Points: 6

# Comments: 6

New comment by CSMastermind in "Pokemon Emerald Ported to WebAssembly (100k FPS)"

CSMastermind — Sat, 06 Jun 2026 23:26:17 +0000

I couldn't get trading working but maybe I'm doing something wrong.

New comment by CSMastermind in "New U.S. college grads now have higher unemployment than the average worker"

CSMastermind — Sat, 06 Jun 2026 23:25:24 +0000

I'd argue the value of college has been steadily declining ever since we tried to push more and more people through it. When it's a filter it's a good signal, when it's a participation trophy far less so.

New comment by CSMastermind in "Uber's $1,500/month AI limit is a useful signal for AI tool pricing"

CSMastermind — Wed, 03 Jun 2026 22:27:12 +0000

A blanket cap makes no sense to me. There's a power distribution of AI use in my company and I'd imagine it's the same at a much greater scale at Uber.

I'd guess there should be a few people Uber is bascially allocating unlimited AI spending to and a large swath they're giving basically nothing.

New comment by CSMastermind in "OpenAI frontier models and Codex are now available on AWS"

CSMastermind — Tue, 02 Jun 2026 03:58:28 +0000

One of the most attractive things a company can offer its engineers right now is a large token/compute budget.

New comment by CSMastermind in "Codex just found a "workaround" of not having sudo on my PC"

CSMastermind — Sun, 31 May 2026 20:23:37 +0000

I realize this is supposed to be a post about how scary the security vulnerabilities these agents will find are.

But personally I love when agents do things like this and appreciate the help. Last thing in the world I want is for them to nerf the models.

New comment by CSMastermind in "OpenRouter raises $113M Series B"

CSMastermind — Sat, 30 May 2026 20:09:32 +0000

What's the business model? Their core functionality, while useful, seems like something that will just be an open-source package. I assume there will be some Saas layer on top of it?

New comment by CSMastermind in "MCP is dead?"

CSMastermind — Fri, 29 May 2026 23:18:38 +0000

Was this written by AI?

MCP is essentially just JSON RPC with a few special fields that must be included. I have reservations about JSON RPC, but there needs to be some 'service discovery' layer for LLMs to interface with.

It needs to be available in places like websites, desktop applications, backend services, etc. The CLI is only one place that these systems interface with.

Whatever you replace MCP with will be in a similar shape even if you specify a different communication protocol or different fields for tool discovery.

New comment by CSMastermind in "I'm Tired of Talking to AI"

CSMastermind — Wed, 27 May 2026 11:41:45 +0000

AI customer service bots are awful. Their only redeeming feature is how bad most customer service processes already are.

New comment by CSMastermind in "Dropbox CEO Drew Houston to step down"

CSMastermind — Tue, 26 May 2026 22:10:43 +0000

Wow cool to see.

New comment by CSMastermind in "Incident with Actions and Pages"

CSMastermind — Tue, 26 May 2026 14:30:04 +0000

Will more copilot usage fix this? We should try more copilot.

New comment by CSMastermind in "Scammers are abusing an internal Microsoft account to send spam links"

CSMastermind — Sun, 24 May 2026 17:47:17 +0000

This happens all the time, it's a classic phishing tactic.

New comment by CSMastermind in "Chess invariants"

CSMastermind — Fri, 22 May 2026 20:42:51 +0000

> The player’s choice is not restricted to pieces that have been captured previously

I grew up playing chess but my grandfather always insisted that pawns could only be promoted to captured pieces so when I played him we had to play a that variant.

I suspect this came from players not having extra pieces with their chess sets.

New comment by CSMastermind in "The IBM-ification of Google?"

CSMastermind — Fri, 22 May 2026 01:52:41 +0000

If anything I think Microsoft is IBM

New comment by CSMastermind in "Waymo pauses Atlanta service as its robotaxis keep driving into floods"

CSMastermind — Thu, 21 May 2026 17:53:07 +0000

I got downvoted for saying this last time the topic came up but constraints focus a project. It’s best to start work with as few variables as possible, and only add new ones when absolutely necessary.

I'm working on a similar problem in computer vision and we're quickly approaching the point where our pure vision work is better than our Lidar supported track because we've had to deal with the constraints instead of having a crutch to lean on.

New comment by CSMastermind in "Anthropic is expanding to Colossus2. Will use GB200"

CSMastermind — Thu, 21 May 2026 05:54:31 +0000

More people should try Grok. I don't use it for coding but it's replaced a lot of my ChatGPT usage. Definitely more perferred model for quick questions or easy answers.

New comment by CSMastermind in "Map of Metal"

CSMastermind — Thu, 21 May 2026 00:30:31 +0000

I'm blown away by the things people think to create.