ShogenTheOne

Proudly CEO and Founder of @E_bokio

[ShogenTheOne @ShogenTheOne]

this is a good feature i like it

[ClaudeDevs @ClaudeDevs]

New in Claude Code: your sessions can now message each other.

Instead of having to re-explain yourself in another session, you can now tell Claude to do it. It sends a summary (not your history or files), and the other session picks it up mid-task.

[ShogenTheOne @ShogenTheOne]

I was impressed at the first when Anthropic released Opus 5 but after a feel like its dumber and make a lot of mistakes lazy can't even do a task without drifting lot of regressions,its bad Opus 5 it's worst even if the benchmarks put it a head with fable 5 but its not even close

[Sulfur @sulfurscales]

i built a way to generate full ai vlogs for youtube using seedance 2.5, without ever picking up a camera

this was supposed to stay internal but f*ck it, i'm leaking the whole thing

you give it a script or even just a topic and it comes back with a finished vlog, voiceover, b-roll, captions, ready to upload

here's how it works: a custom claude skill breaks your script into scenes and writes timestamped storyboard prompts for each one, matched to pacing so nothing feels random. those prompts get fed into seedance 2.5, using its 30 second continuous generation and reference asset support to keep the visuals consistent across scenes instead of looking like ten unrelated clips stitched together. then it pulls in an ai voiceover that matches the tone of the script, stitches every scene together, and burns in captions automatically

you're not filming, not voicing, not editing, not exporting from three different apps

the whole thing runs start to finish and outputs a finished 16:9 vlog ready to post, and it costs a fraction of what an editor or camera setup would run you

i'm sharing the full breakdown, which includes:

the claude skill that handles scene breakdown and storyboard prompts the seedance 2.5 setup that keeps visuals consistent scene to scene the voiceover setup that keeps it from sounding robotic the exact workflow from script to finished vlog

RT + reply "PROMPTS" and i'll send it over (must follow so i can dm)

[ShogenTheOne @ShogenTheOne]

What happen to Anthropic 🤨

[Theo - t3.gg @theo]

Crazy that we never got a reset for this 🙃

[ShogenTheOne @ShogenTheOne]

its here guys

[BytePlus @BytePlusGlobal]

5... 4... 3... 2.5

It's almost here.

[ShogenTheOne @ShogenTheOne]

claude code still down, we need reset after this

[CodeRabbit @coderabbitai]

We put Claude Opus 5 through our code review bench.

It wrote the most precise actionable comments we've ever measured:
> 39.3% against our baseline's 35.2%.

It also caught fewer known bugs:
> 55.2% vs 61.1%, and produced four times the nitpicks.

Our verdict:
> A precision specialist, which pairs well with a recall model.

Full write up in the comments.

[ShogenTheOne @ShogenTheOne]

Opus 5 is a good model, cheap, only weakness i found is slow as fuck, 4 hours for just mid phase that not hard.

[ShogenTheOne @ShogenTheOne]

i need reset

[ShogenTheOne @ShogenTheOne]

same

[Theo - t3.gg @theo]

I got so used to the limits with Fable that Opus feels practically unlimited

[ShogenTheOne @ShogenTheOne]

no reset that weird?

[Claude @claudeai]

Introducing Claude Opus 5.

It's a thoughtful and proactive model that comes close to the frontier intelligence of Fable 5 at half the price.

[ShogenTheOne @ShogenTheOne]

@theo Very good, impressive in frontend, its follow the exact instructions, low hallucination, in general its good model not good as quite as sol or fable but its cool

[ShogenTheOne @ShogenTheOne]

finally

[Claude @claudeai]

Introducing Claude Opus 5.

It's a thoughtful and proactive model that comes close to the frontier intelligence of Fable 5 at half the price.

[ShogenTheOne @ShogenTheOne]

@thsottiaux that a weird error, this appear when i click in a running session?

[ShogenTheOne @ShogenTheOne]

Exceted to test it

[Qwen @Alibaba_Qwen]

🎨 Meet Qwen-Image-3.0 — the third generation of our foundational image generation model.

If 1.0 was about "Precision," and 2.0 added "Variety, Completeness, Beauty & Authenticity," then 3.0 comes down to a single word: Real (实).

Three dimensions of "Real":
📰 Rich Content — prompts up to 4.5k tokens. One-pass generation of complex layouts: newspapers, storyboards, exam papers — even a 3×3 infographic grid or picture-in-picture-in-picture UIs.
🔬 Authentic Details — text legible down to 10px, full LaTeX paper pages, pores, hair strands & near-photographic skin texture.
🌏 Deep Knowledge — native rendering in 12 languages, 100+ art styles, realistic UIs (web / games / livestreams), plus world knowledge & live web retrieval.

Not just "good-looking" — genuinely useful. Image generation as a real productivity tool for design, content, education & e-commerce.

Go create 🏃🎨

💬Qwen Chat: https://t.co/941HmITJ2W
📝Blog: https://t.co/5mnS4uI9Ar

[NIK @ns123abc]

>be openai
>release gpt 5.6 sol
>max thinking budgets, full psycho
>benchmark results take few days to roll in
>“best model ever”
>reviews locked in
>4 days later
>silently nerf it
>nobody re-tests lol
>users still paying full price
>not realizing the model they benchmarked isn’t the model you’re paying for

Lmao, it’s over

[celeste @vmfunc]

great model guys

[ShogenTheOne @ShogenTheOne]

unlucky i burned all the usage i was little bit excitedfor fable 5

[ShogenTheOne @ShogenTheOne]

Its back baby

[Claude @claudeai]

Fable 5 is back.