@chandlerwilcox · X

@AmblingLife · X

@BansalSamy87003 · X

I am 14 year old

@bhavin_Confuse · X

BEHAVR ( @Behavr_AI ) — chat with any video instead of scrubbing through it. Ask "where does he fix the CORS bug?" → get the answer with the exact timestamp.

TimeGuessr — 给你一张图片，让你猜测图片发生的时间和地点。我们把 Timeguessr 的玩法原封不动地搬了过来，只是把图库换成了另一批“假照片”——全部由 AI 生成的过去 50 年里可能发生的瞬间

@VanillaSkyAI · X

is like Lovable for video. Paste a URL, get a launch video, chat to edit, post 🎬 Here's one I made in minutes 👇

@builldsystems · X

- uptime monitoring built for indie hackers juggling multiple side projects.

@KsaAZaks · X

- Traffic Orchestration Platform

@johncalvo · X

Built an entire YouTube research platform with @AnthropicAI Claude Code. a YouTube research tool that treats entire channels as a searchable transcript database rather than individual videos. Any YouTube channel. Every word. Fully searchable. Track how topics trend, peak, and evolve across hundreds of videos. Researching what someone said on YouTube means watching hours of footage and hoping you find it. ChannelScout extracts full transcripts from any channel, makes every word instantly searchable, and tracks how topics trend over time, without watching a single video manually. Paste a YouTube channel or playlist URL and it transcribes and indexes every transcript. Follow multiple channels and they all land in one private library. New videos on followed channels are auto-transcribed and added to your library the day they publish. Beyond YouTube it accepts any yt-dlp-supported URL including Vimeo, TED, and SoundCloud, and you can upload local files directly

@danielberigoi · X

Type plain text, get a clean deck in 30 seconds, broadcast it live to every phone in the room

@versuchai · X

pw · HN

Hiya! So I've been playing around with having Claude make videos for a bit now even had some success posting the results to TikTok (and setup a whole pipeline so Claude can generate and post autonomously). With the release of Nano Banana 2 Lite, I was curious show fast I could make the generation, so last night I gave it a whirl and got down to around 30s for short-form video. It uses GLM-5.2 fast via Fireworks to generate the scripts and image prompts and, like I said, Nano Banana 2 Lite for the images, gpt-4o-mini-tts for the narration, and ffmpeg to string it all together and add the Ken Burns zoom effect (which still has a shake I haven't been able to get rid of). The video compilation proved to be the blocker once the rest was in place, but I was able to speed that up by putting it on a 64 vCPU EC2. The cost might be the most interesting aspect as the short form videos tend to be about 25 cents. Almost 90% of that is the images, which are 3.336 cents a piece. Of course, running