Matching posts

Matching terms are highlighted

David Lingenfelter's writing & photography site

David Lingenfelter's personal site gathering his writing, books, photography and curiosity about science.

个人网站@dlingenfelter　Filed in No.005

1 day agoCopy original

POST

Claude for writing, Codex for code details, but account bans are the real worry

A user picks Claude for writing and Codex for code details, but says the real pain point is keeping accounts from being banned.

claude@vfxliubin　Filed in No.011

1 day agoCopy original

POST

Gemini 4 Argon distills 7,000 tweets into a personal writing workflow

兄弟们，再给大家分享一个我个人的 X 写作运营的压箱底绝活。 前提只有一个：你得自己真刀真枪发过大量推文的（非AI大量写作）。 很多人用 …

gemini-4@GeekCatX　Filed in No.008

22 hours agoCopy original

Teaching Auto Router taste preferences with Jev

The author says Jev lets you teach Auto Router preferences like preferring GPT 6.1 Sol for copywriting over Opus 5.5, in a few clicks.

jev@NadavAHollander　Filed in No.006

20 hours agoCopy original

ToneBench: DeepSeek V4.1 Flash 1017 writes better than GPT-6.1 Terra at $0.014 per script

Towards AI's ToneBench ranks GPT-6.1 Terra 23rd of 84 and concludes that for pure cheapness, GLM-5.3 Flash ($0.022) and DeepSeek V4.1 Flash 1017 ($0.014) write better for less, though they use 7-15x more tokens per script and run slower.

deepseek-v4.1@Whats_AI　Filed in No.020

1 day agoCopy original

POST

Report-writing benchmark: Gemini 4 Argon tops 20-task eval

Across 20 expert-written report tasks, scores ranged 54.3%–64.1% with Gemini 4 Argon highest; most lost points came from deciding what to include and explaining what facts mean.

gemini-4@aliansarinik　Filed in No.008

1 day agoCopy original

Camellia Yang's bilingual writing site

Bilingual writer/translator/podcaster Camellia Yang's personal site, with optimized layout and performance.

个人网站@Camelliayang　Filed in No.005

2 days agoCopy original

POST

Gemini 4 Argon praised for its prose writing

A user says Gemini 4 Argon writes excellent prose and jokes that humans trained on Chinese essay formats are outmatched by the model's parameters and TPM.

gemini-4@Stv_Lynn　Filed in No.008

3 days agoCopy original

POST

Gemini 4 Argon: strong writing, but hallucinations and repeat mistakes

The author says Gemini 4 Argon is unmatched at copy, literary writing and translation, yet hallucinates and repeats mistakes from two years ago, making it too inconsistent to rely on.

gemini-4@Da7_Tech　Filed in No.008

2 days agoCopy original

POST

LLM landscape roundup: Gemini 4 Argon shipped, strongest at writing

A Japanese user's roundup of the current model landscape says Gemini 4 Argon has shipped, leads on writing and video/audio input, but is rarely used for coding.

gemini-4@ynishi2015　Filed in No.008

3 days agoCopy original

Showing10of60posts

10 per batch

Keep scrolling to reveal posts 11–20

Showing the first 60 matches. Narrow the query with a model name or tag to find more specific results.