Hacker News: james2doyle

New comment by james2doyle in "ChatGPT Images 2.0"

james2doyle — Tue, 21 Apr 2026 23:58:34 +0000

In the next round of ChatGPT advertisements, if they don’t use AI generated images, then that means they don’t believe in their own product right?

New comment by james2doyle in "ChatGPT Images 2.0"

james2doyle — Tue, 21 Apr 2026 23:56:10 +0000

I think "better" is doing a lot of heavy lifting in this argument. Better how?

Is an AI generated photo of your app/site going to be more accurate than a screenshot? Or is an AI generated image of your product going to convey the quality of it more than a photo would?

I think Sora also showed that the novelty of generating just "content" is pretty fleeting.

I would be interested to see if any of the next round of ChatGPT advertisements use AI generated images. Because if not, they don’t even believe in their own product.

New comment by james2doyle in "AI Resistance: some recent anti-AI stuff that’s worth discussing"

james2doyle — Mon, 20 Apr 2026 20:57:37 +0000

You should check out "model collapse". It seems that an abundance of content, that is more and more AI generated these days, may not be a viable option. There is also a vast amount of data that is increasingly going private or behind paywalls

New comment by james2doyle in "Cloudflare's AI Platform: an inference layer designed for agents"

james2doyle — Thu, 16 Apr 2026 18:40:25 +0000

To better clarify, I don’t see "workers-ai/@cf/google/gemma-4-26b-a4b-it" in the /models enpoint in gateway.ai.cloudflare.com but it does seem to exist as a hosted model. Same with "workers-ai/@cf/nvidia/nemotron-3-120b-a12b" which I would expect to see

New comment by james2doyle in "Cloudflare's AI Platform: an inference layer designed for agents"

james2doyle — Thu, 16 Apr 2026 18:35:51 +0000

I find it really confusing that the worker AI models on here: https://developers.cloudflare.com/workers-ai/models/ do not have full overlap with the ones on here: https://developers.cloudflare.com/ai/models/

Yes, you can see the same "hosted" ones on there, but when you look at the models endpoint, there are much less options at the "workers-ai/*" namespace. Is that intentional?

New comment by james2doyle in "Cloudflare's AI Platform: an inference layer designed for agents"

james2doyle — Thu, 16 Apr 2026 18:23:39 +0000

I just added some credits to my account. You can set a daily $ spend limit as well as add credits without auto-refill

New comment by james2doyle in "Cloudflare's AI Platform: an inference layer designed for agents"

james2doyle — Thu, 16 Apr 2026 18:23:12 +0000

Seems like it. I just added some credits to my account. You can set a daily $ spend limit as well as add credits without auto-refill

New comment by james2doyle in "Google releases Gemma 4 open models"

james2doyle — Thu, 02 Apr 2026 16:36:37 +0000

Yeah you can see here that tool calling is disabled: https://huggingface.co/inference/models?model=google%2Fgemma...

At least, as of this post

New comment by james2doyle in "Google releases Gemma 4 open models"

james2doyle — Thu, 02 Apr 2026 16:35:38 +0000

Hmm just tried the google/gemma-4-31B-it through HuggingFace (inference provider seems to be Novita) and function/tool calling was not enabled...

New comment by james2doyle in "StepFun 3.5 Flash is #1 cost-effective model for OpenClaw tasks (300 battles)"

james2doyle — Thu, 02 Apr 2026 16:12:32 +0000

Oh I never noticed that. Good to call out. But that would put it much closer to Minimax M2.7 in terms of price than to the likes of Mimo V2 Pro, and Gemini Flash 3 preview, which are both on the list

New comment by james2doyle in "StepFun 3.5 Flash is #1 cost-effective model for OpenClaw tasks (300 battles)"

james2doyle — Wed, 01 Apr 2026 20:56:26 +0000

None of the Qwen 3.5 models seem present? I’ve heard people are pretty happy with the smaller 3.5 versions. I would be curious to see those too.

I would also be interested to see "KAT-Coder-Pro-V2" as they brag about their benchmarks in these bots as well

Kat-Coder-Pro V2 Released. Same Price as V1

james2doyle — Mon, 30 Mar 2026 16:46:38 +0000

Article URL: https://www.streamlake.ai/product/kat-coder

Comments URL: https://news.ycombinator.com/item?id=47576669

Points: 3

# Comments: 0

New comment by james2doyle in "OpenCode – Open source AI coding agent"

james2doyle — Fri, 20 Mar 2026 23:10:52 +0000

What caused the switch? Also, are you still trying to use Claude models in OpenCode?

New comment by james2doyle in "AI coding is gambling"

james2doyle — Wed, 18 Mar 2026 18:14:47 +0000

The only similarity is that they both say "you’re absolutely right" when you point out their obvious mistakes

New comment by james2doyle in "AI coding is gambling"

james2doyle — Wed, 18 Mar 2026 18:13:37 +0000

_hyper-competent collaborator who may completely make things up occasionally and will sometimes give different answers to the same question*_

New comment by james2doyle in "Ask HN: Are MiniMax Models Scams?"

james2doyle — Wed, 18 Mar 2026 18:01:17 +0000

I’ve used M2.5 in OpenCode using their Zen inference. I found it to be decent. Did not really seem comparable to Opus 4.5 for "quality" output. As in, I often tweaked the output more when using M2.5.

I think the best thing was the speed. If it is going to be wrong, I would prefer it to be wrong quickly.

New comment by james2doyle in "MiniMax M2.7 (200K context, $0.30/1.20) released"

james2doyle — Wed, 18 Mar 2026 17:59:01 +0000

They have the details up on their site now: https://www.minimax.io/models/text/m27

New comment by james2doyle in "Mistral.ai Leanstral: open-source model designed for engineering"

james2doyle — Mon, 16 Mar 2026 20:27:37 +0000

There is a blog post now: https://mistral.ai/news/leanstral

New comment by james2doyle in "Mistral.ai Leanstral: open-source model designed for engineering"

james2doyle — Mon, 16 Mar 2026 18:29:22 +0000

Mentioned in the 2.5.0 release of the Vibe CLI tool: https://github.com/mistralai/mistral-vibe/releases/tag/v2.5....

New comment by james2doyle in "Mistral.ai Leanstral: open-source model designed for engineering"

james2doyle — Mon, 16 Mar 2026 18:26:55 +0000

> Leanstral > Our first open-source code agent designed for Lean 4, built for formal proof engineering in realistic repositories. 119B parameters with 6.5B active.

Mentioned in the 2.5.0 release of the Vibe CLI tool: https://github.com/mistralai/mistral-vibe/releases/tag/v2.5.... A HuggingFace page is linked for the weights but it returns a 404: https://huggingface.co/mistralai/Leanstral-120B-A6B-2603