Hacker News: fdsjgfklsfd

New comment by fdsjgfklsfd in "DeepSeek-V4-Flash Update"

fdsjgfklsfd — Fri, 31 Jul 2026 15:52:46 +0000

Was already released before your comment: https://huggingface.co/deepseek-ai/DeepSeek-V4-Flash-0731

New comment by fdsjgfklsfd in "DeepSeek-V4-Flash Update"

fdsjgfklsfd — Fri, 31 Jul 2026 15:50:50 +0000

I use DeepSeek V4 Flash (before this update) for most things:

- OpenCode for codebase editing: python scientific computing and LLM projects

- Open Interpreter Classic (python version) for Swiss army knife terminal replacement one-off task type stuff.

New comment by fdsjgfklsfd in "DeepSeek-V4-Flash Update"

fdsjgfklsfd — Fri, 31 Jul 2026 15:36:07 +0000

DeepSeek-V4-Flash-0731 scores higher than Fable 5 on Terminal-Bench, and Fable 5 is Mythos, correct?

New comment by fdsjgfklsfd in "DeepSeek-V4-Flash Update"

fdsjgfklsfd — Fri, 31 Jul 2026 15:30:37 +0000

Yes, they trained on my open source code and Wikipedia edits and Stack Overflow answers that I shared freely, so it's only fair that they release their models as open source and share back to the community that created them. I only allow my training data go to open source models.

New comment by fdsjgfklsfd in "DeepSeek Introduces Vision"

fdsjgfklsfd — Thu, 18 Jun 2026 13:52:46 +0000

Yeah the reasoning is formatted differently and the replies are often in Chinese.

New comment by fdsjgfklsfd in "DeepSeek Introduces Vision"

fdsjgfklsfd — Thu, 18 Jun 2026 13:50:56 +0000

Sometimes it's faster than swyping on a phone, but mostly I use it to learn about stuff and hash out ideas while driving.

New comment by fdsjgfklsfd in "Qwen3.6-Plus: Towards real world agents"

fdsjgfklsfd — Tue, 07 Apr 2026 19:58:57 +0000

The US government is vastly more likely to break down my door and arrest me for my speech than the Chinese government is. (Because I live in the US.)

New comment by fdsjgfklsfd in "Qwen3.6-Plus: Towards real world agents"

fdsjgfklsfd — Tue, 07 Apr 2026 19:55:14 +0000

Qwen3.5-plus is quite good, Qwen3.6-plus is not.

New comment by fdsjgfklsfd in "Qwen3.6-Plus: Towards real world agents"

fdsjgfklsfd — Tue, 07 Apr 2026 19:54:34 +0000

Qwen3.5-plus has been my go-to model for non-autonomous chatbot that runs arbitrary code and shell commands on my local machine for one-off tasks (unlike Claude Code). It has no problem calling tools to run code (that contains tools), and pretty smart, and cheap (though lack of token caching is making it much more expensive than it should be).

I tried Qwen3.6-plus and it was not as good.

New comment by fdsjgfklsfd in "Qwen3.6-Plus: Towards real world agents"

fdsjgfklsfd — Tue, 07 Apr 2026 19:49:43 +0000

> In particular, Qwen3.5-Plus is the hosted version corresponding to Qwen3.5-397B-A17B with more production features, e.g., 1M context length by default, official built-in tools, and adaptive tool use. For more information, please refer to the User Guide.

https://huggingface.co/Qwen/Qwen3.5-397B-A17B

So 3.5-plus has been released as open weights.

New comment by fdsjgfklsfd in "Tell HN: Litellm 1.82.7 and 1.82.8 on PyPI are compromised"

fdsjgfklsfd — Tue, 24 Mar 2026 20:23:21 +0000

Reporting spam on GitHub requires you to click a link, specify the type of ticket, write a description of the problem, solve multiple CAPTCHAs of spinning animals, and press Submit. It's absurd.

New comment by fdsjgfklsfd in "We Will Not Be Divided"

fdsjgfklsfd — Sat, 07 Mar 2026 20:28:17 +0000

https://www.thestack.technology/backlash-over-anthropic-ai-c...

https://www.anthropic.com/news/detecting-and-preventing-dist...

New comment by fdsjgfklsfd in "We Will Not Be Divided"

fdsjgfklsfd — Sat, 07 Mar 2026 20:13:02 +0000

The current biggest problem in the US is that the President is violating the Constitution with impunity

New comment by fdsjgfklsfd in "We Will Not Be Divided"

fdsjgfklsfd — Sat, 07 Mar 2026 20:12:18 +0000

The Constitution and Founding Fathers are pretty great compared to what we have now.

"At this point, Elbridge Gerry objected to Butler’s earlier-raised proposition that the clause be shifted to a presidential power. Gerry remarked that he never expected to hear in a republic a motion to empower the Executive alone to declare war."

"What is called a republic is not any particular form of government. It is wholly characteristical of the purport, matter or object for which government ought to be instituted, and on which it is to be employed … in this sense it is naturally opposed to the word monarchy, which … means arbitrary power in an individual person; in the exercise of which, himself, and not the res-publica, is the object."

New comment by fdsjgfklsfd in "We Will Not Be Divided"

fdsjgfklsfd — Sat, 07 Mar 2026 20:07:30 +0000

Aggregators:

https://fiftyplusone.news/polls/approval/president

https://www.natesilver.net/p/trump-approval-ratings-nate-sil...

New comment by fdsjgfklsfd in "We Will Not Be Divided"

fdsjgfklsfd — Sat, 07 Mar 2026 20:01:09 +0000

"Overplayed"? Did you see the actual footage of the event? The event in which people attacked Capitol Police and broke into the Capitol and tried to take power by force?

New comment by fdsjgfklsfd in "Keep Android Open"

fdsjgfklsfd — Sat, 21 Feb 2026 17:32:47 +0000

They aren't actually trying to solve any real problem.

New comment by fdsjgfklsfd in "GPT-5"

fdsjgfklsfd — Thu, 14 Aug 2025 19:42:49 +0000

Do you mean "all variants of the same stacked transformer architecture converge in performance"? Or do you know of tests against some other architecture? The diffusion-based LLMs?

New comment by fdsjgfklsfd in "GPT-5"

fdsjgfklsfd — Fri, 08 Aug 2025 14:08:44 +0000

What's openai/gpt-5 vs openai/gpt-5-chat?

New comment by fdsjgfklsfd in "GPT-5"

fdsjgfklsfd — Thu, 07 Aug 2025 18:44:32 +0000

I think they're just reaching the limits of this architecture and when a new type is invented it will be a much bigger step.