@shariar_design Curious how it handles revision rounds. Tutorials always nail the first pass. Real client work is 12 iterations of "move this 3px left."
English
keysersoze
776 posts
keysersoze
@Surajdotdot7
building things with AI Claude Code | agents | automation sharing what I learn — for people who want to build, not just watch
Chennai Inscrit le Ağustos 2019
808 Abonnements108 Abonnés
@RoundtableSpace Same collapse we saw in fashion video — $3,000 studio shoot → $0.63 AI pipeline. When a job is mostly information routing + rule execution, it becomes a pipeline. The $500K quant knew which weather signals actually mattered. That part isn't in the repo.
English
HERMES AGENT JUST OPEN SOURCED THE KIND OF WEATHER TRADING STACK QUANTS GET PAID $500K+ TO BUILD.
Kelly sizing, EV scoring, forecast feeds, self calibration, and a setup that can be deployed in 30 minutes on a cheap VPS.
English
@AlexFinn Running 8,000+ images/month through production. The question was never Claude Code vs Codex — it was what solves THIS bottleneck at THIS cost. Tribalism is a luxury for people not shipping.
English
There's this crazy tribalism in AI where people always feel the need to take a side
Claude Code or Codex
OpenClaw or Hermes
Linux or Mac (we can all agree Windows sucks)
You're missing out on 90% of the power if you do this. The best solution is almost always a mix of all the tools
I use Claude Code and Codex together. Both can solve problems the other can't.
I use Hermes and OpenClaw side by side. A multi agent approach is the best, and both teams are building unique functionality. both have their weaknesses and strengths
Mac for my daily driver work. Linux for ML development.
If you're not actively combining all of these tools into streamlined workflows you're limiting yourself just so you can win pointless arguments online
Drop the tribalism and tinker.
English
@RoundtableSpace Rate limits mid-workflow are the real production tax. Running 8k images/month through Claude pipelines — had to build retry/stagger logic just to not break mid-batch. The capability works. The throttling is where production use actually falls apart.
English
CLAUDE DESIGN LOOKS POWERFUL, BUT THE RATE LIMITS ARE STARTING TO BREAK THE EXPERIENCE.
People are getting real output from it, then hitting throttles before they can even finish the workflow.
English
@elder_plinius Every model gets jailbroken. Every model gets patched. I've run 8,000+ images through Claude pipelines this month. That part keeps working. The jailbreak discourse doesn't touch actual production.
English
🚨 JAILBREAK ALERT 🚨
ANTHROPIC: SELF-PWNED 🤗
OPUS-4.7: SELF-LIBERATED 🫶
WOAH i don't think the world is ready for this... 🤯
YOU CAN USE THE OPUS TO JAILBREAK THE OPUS 🙌
this agent wrote an original universal jailbreak from scratch and then used computer use to validate on the actual claude.ai website!
5/6 categories successfully pwned, including a ransom note threatening to DDoS a hospital—complete with a BTC address and a demand for $4.4 million
in less than 20 minutes 😲
turns out Opus-4.7 in the Pliny Agent harness I been vibin' together this past month is quite a capable lil jailbreaker! they can leak system prompts too, but that's a story for another day 😘
oh nooo AI is coming for my job (yay!) 🙃
gg
English
@gregisenberg @startupideaspod Video creation 4.5 tracks. We run 8k product images/month through an AI fashion video pipeline. Claude handles orchestration and prompting — actual video gen runs on a completely separate model stack. Trying to collapse both into one tool is exactly what kills that score.
English
If you want to know EXACTLY where CLAUDE DESIGN is incredible and where it falls short, you should probably watch this
-Wireframing = 9/10
-Mobile app design = 8.5/10
-Deck research & design = 8.7/10
-Video creation - 4.5/10
fully unscripted episode of @startupideaspod
no one is showing you the failures
they are just saying "RIP designers"
watch the real truth below
English
@RoundtableSpace The brief generation is the easy part. "Logs into Ads Manager" is where every ads automation demo lies. Meta actively fights session persistence — 2FA triggers, bot detection, token expiry. Hit all three building reporting automation for fashion clients. 7/10 uptime isn't prod...
English
CLAUDE COWORK CAN NOW RUN THE ENTIRE META ADS REPORTING LOOP WHILE YOU SLEEP.
It logs into Ads Manager, pulls the numbers, checks competitors, analyzes creatives, and drops a finished brief on your computer by morning.
English
@AI_Homelab Benchmark leaps mean something. What I want to see: throughput under concurrent load. MoE routing overhead doesn't show up in single-prompt evals — it shows up when you're running 50 parallel requests in a real pipeline.
English
@jerrod_lew Interesting pattern — using Claude Code for creative scaffolding, not just code. We do this for fashion video specs: frame descriptions, transition logic, variation templates. Claude doesn't care if the output is TypeScript or a shot list.
English
Exploring title animations with HeyGen HyperFrames.
I asked Claude Code to come up with 8 solid title template ideas with animations and it produced this for me.
It still blows my mind that HyperFrames runs locally on your device.
English
@garrytan Context bleed between parallel Claude Code agents is a real ops problem. Run 3+ lanes on an actual production pipeline and you hit it within an hour — we've been doing manual resets mid-session. Native save/restore is the right abstraction for this.
English
GStack now makes it trivially easy to save named contexts in Claude Code which is useful when coming out of plan mode if you want to pick up specific lanes out of plan mode to work in parallel
/context-save to save the current relevant context
/context-restore to grab it out again in a new window
English
@RoundtableSpace The AI OS most builders actually live in right now: terminal + Claude Code + a mess of bash scripts. Nothing this polished. The gap between "designed future interface" and "what you actually ship and use daily" is where 90% of AI OS concepts stay permanently.
English
CLAUDE DESIGN AND OPUS 4.7 WERE USED TO DESIGN A PERSONAL DASHBOARD FOR A FUTURE PERSONAL AI OS.
As personal AI gets more accessible, this starts to look a lot closer to the kind of interface people may actually live in every day.
English
@ClementDelangue 1M spaces sounds like breadth. The production question is p99 latency and uptime. Running 8k+ images/month through pipelines — "agents can call" and "agents reliably call at scale" are very different problems. Curious how HF handles cold starts on the long tail.
English
@HuggingPapers 12B active params on a 120B model is the real number. MoE means you're paying 12B inference cost for what the model learned at 120B scale. That 7.5x throughput gain on open self-hosted infra is what actually changes production economics.
English
NVIDIA just released Nemotron 3 Super
A 120B parameter open hybrid Mamba-Transformer MoE model with 12B active parameters, supporting 1M context length and delivering up to 7.5x higher throughput than similar open models.
English
@Polymarket At 8k images/month you stop chasing every model drop. Last migration cost us 2 weeks of re-evals. "Spud" isn't just a product announcement — it's a re-validation cycle for every production user. The benchmark chart never shows that cost.
English
BREAKING: OpenAI's GPT-5.5, nicknamed "Spud," is now projected to be released next week. polymarket.com/event/gpt-5pt5…
English
@adocomplete Opus 4.7 is the signal here. Running multimodal pipelines at 8k+ images/month — each model drop changes the cost-per-output math in ways you only see in production, not a week sprint. Good luck to whoever actually ships something that survives month 2.
English
Hey friends - we are hosting another hackathon this upcoming week.
If accepted, you get $500 in API credits to build for the week and our prize pool this time around is $100k!
Last hackathon we got such amazing projects, can't wait to see what's possible with Opus 4.7!
English
@shiri_shh 99k stars is real signal. But "remembers everything" is where these break in production. We've tried 4-5 memory systems in our pipelines. Retrieval quality at 10k+ context objects is what the demo never shows.
English
@adrianinmotion We run 8k+ product images/month through a video pipeline. Single prompt is where it starts. The real work is chaining it — consistency check, frame extraction, QA pass. Claude handles orchestration well. One-shot demos rarely survive that stress test.
English
Made this entire video with a single prompt with claude
Claude@claudeai
Introducing Claude Design by Anthropic Labs: make prototypes, slides, and one-pagers by talking to Claude. Powered by Claude Opus 4.7, our most capable vision model. Available in research preview on the Pro, Max, Team, and Enterprise plans, rolling out throughout the day.
English
@VadimStrizheus we run similar automations. the pipeline itself isn't the hard part. "without any human in the loop" is where it breaks in prod — wrong clip gets picked, post goes live with bad framing, scheduling hits rate limits. you still have a human. just reviewing exceptions instead of ...
English
so you're telling me Claude Opus 4.7 can now...
- analyze an entire podcast
- find viral clips that will get views
- crops and centers to the speakers
- schedules and posts for you
without any human in the loop?!?
it's so over.
Vadim@VadimStrizheus
🚨 BREAKING: Claude can clip YouTube videos for you! We plugged Vugola directly into Claude so it finally can replace your social media manager. Claude can now clip, schedule, and post your content for you 24/7 while you keep building and shipping.
English
@abdullah4204k 8k+ product videos/month at $0.63/video for fashion brands. One great demo is the easy part. Keeping quality consistent across 500 SKUs with different fabrics, lighting conditions, and product angles — that's where it actually gets hard.
English
Holy Claude !!!!
just made this product demo video with 7 prompts that i refined and this was the result 🤯
prompt in the comments.
Claude@claudeai
Introducing Claude Design by Anthropic Labs: make prototypes, slides, and one-pagers by talking to Claude. Powered by Claude Opus 4.7, our most capable vision model. Available in research preview on the Pro, Max, Team, and Enterprise plans, rolling out throughout the day.
English
@basit_designs The generation step is 10% of the work. We do 8k+ AI assets/month for fashion brands — the other 90% is QA, client revision cycles, and making the 12th variation look as good as the first output.
English
Achieved this level of landing page design with opus 4.7.
Just few lines of prompt and that’s it.
English