jsnode retweeted
if you're using claude to edit videos, you can give it a library of 5.2M+ audio files for $0
sound effects, ambience, music. openverse has a free api. no key needed.
give it api.openverse.org and ask:
“whenever you need sound effects search Openverse to find the best options and use them for tasteful sound design within my video”
no more using your browser to download random clips or trying to generate the audio itself
jsnode retweeted
Good plans are simple. I have one that should result in significantly more usage for everyone. Hope to get it done soon.
pssst!! aistandings.live is here!
just a public project, vote freely on AI like claude, chatgpt, gemini and so on, pretty basic :)
cant wait to watch standings changing!! and who is leading
ps: lmk what you think! i'd be so glad if you help to spread!
jsnode retweeted
if you hate reading long posts,
to sum it up:
AVOID - SOS: Shiny Object Syndrome,
if it works,
put your head down,
and increase your output.
What @icookbears said right here is tbh what I think a lot of people need to hear atm.
On X you can really get pulled in SO many directions at the same time.
Be it sleep channels, AI avatar or the next thing that might drop next week.
Meanwhile, you might actually have something going on that really works, but because you saw this new shiny thing on X, you think THIS is the thing that's gonna really hit.
And "the next thing" COULD perform really well for you...
BUT
I think for most people the better thing is to stay in the lane that has already proven to work for them and double down, triple down, and quadruple down as @icookbears said.
And the worst problem is, if you keep going in the directions you're pulled towards, the thing that initially worked well for you might stop working, simply because your attention is elsewhere.
I myself sometimes have fallen into this trap (multiple times might I add), but sometimes it's best to stop up and actually establish a strategy and stick to it, ruthlessly and consistently.
All of us have different competitive advantages and it's about finding those and really utilizing them.
jsnode retweeted
Replying to @theCTO
jsnode retweeted
15min @typesafe Jeveloper tutorial 🧠
My team at @treg_ai has been using Jev a lot in prod:
- Classify web traffic
- Smart onboarding
- Jev-reranked search
~10x cheaper, 18x faster, 30% more accurate in our tests compared with GPT6-luna
OpenSourced our Jev implementation 👇 github.com/superdesigndev/tr…
jsnode retweeted
Buyers now ask AI what to use.
Half of US consumers use AI search, but only 16% of big brands track what it says about them.
citeOS asks ChatGPT, Perplexity, Gemini, Claude and Google AI Mode the questions your buyers ask, and shows what they say about your brand.
Features:
- Visibility score for each AI engine
- Every answer, question by question
- Pages AI cites instead of yours
- Competitor comparison
- What to fix first
- Weekly alerts
Watch the demo.
jsnode retweeted
early SEO tricks from 2005 didn't survive once Google got smarter.
the same will happen with AI search as these engines get better.
“figuring it out early” isn't the advantage people think it is.
being early and being right are two different things.
the real advantage is having real people talking about you across the web.
because algorithms change.
jsnode retweeted
People are frustrated about paid AI coding plan limits.
I get it. A long agent run can consume a surprising amount of your allowance while you’re still debugging the first decision.
The providers are also serving expensive models under flat subscriptions. Limits are part of those economics.
I want clear pricing and honest constraints more than unlimited promises nobody can sustain.
VIDEO A/B TESTING IS COMING TO YOUTUBE
You can upload 3 versions of the SAME video
Different hooks, different pacing, whatever you wanna test
and YouTube tells you which one kept people hooked the longest so you can make it the main one
For Shorts and Long Form!
jsnode retweeted
Replying to @MaxHirsch13
Better to use this imo, much friendlier for your agent as well. asccli.sh/
jsnode retweeted
The secret to growing on X is making a lot of posts and being a reply guy 🤔
hmmm, 1 post, zero replies 🤣
The secret is simple, already be famous
jsnode retweeted
To celebrate the launch of GPT-5.6 Sol, we will reset the rate limits again (twice) across ChatGPT Work and Codex over the next 24 hours.
We want you to have the time to truly try ambitious tasks and get the hang of it. Happy exploring!
jsnode retweeted
I made a Hermes Agent slash command cheat sheet a while back.
@NousResearch has shipped a ton of new stuff since then, so I tonight, I rebuilt it from scratch.
Every official slash command as of 7.4.2026.
Bookmark it.
Study it.
Become a HERMES LEGEND. 🤘
jsnode retweeted
Ever lose a coding agent because you tabbed away?
Someone made a Claude Code menu bar light for exactly that.
It shows thinking, permission waits, and done states, so the frozen terminal stops hiding behind your Dock.
See the repo: github.com/m1ckc3s/claude-st…
jsnode retweeted
A study from @Stanford showed that 71.3% of chatgpt queries could be accurately answered by a local model. I suspect a major part of enterprise AI workloads could be run locally too for free (compared to the massive costs of frontier API cost).
Also, it reduces the risk of these workloads being taken away from you because you own the models instead of renting them - which sounds like a good idea these days haha.
That's why we're introducing the ability for everyone to filter AI models on @huggingface based on your local hardware.
For me, there are 800k+ public models that fit on my M5 24GB and that I can use easily thanks to llamacpp.
Let's go local AI!



























