keysersoze

766 posts

keysersoze banner
keysersoze

keysersoze

@Surajdotdot7

building things with AI Claude Code | agents | automation sharing what I learn — for people who want to build, not just watch

Chennai Tham gia Ağustos 2019
808 Đang theo dõi107 Người theo dõi
keysersoze
keysersoze@Surajdotdot7·
@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
0
0
0
68
DailyPapers
DailyPapers@HuggingPapers·
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.
DailyPapers tweet media
English
5
12
115
6.8K
keysersoze
keysersoze@Surajdotdot7·
@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
0
0
0
344
keysersoze
keysersoze@Surajdotdot7·
@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
0
0
1
50
Ado
Ado@adocomplete·
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
13
7
90
4.9K
keysersoze
keysersoze@Surajdotdot7·
@delveroin AI pipeline turning product images into 13-sec fashion videos. $0.63/video — we used to pay $3,000 for a shoot. Processing 8,000+ images/month for brands. [add your URL here]
English
0
0
0
2
(Oma)devuae
(Oma)devuae@delveroin·
who’s building something cool AND useful? Drop your URL lets send some traffic
English
143
1
74
4.1K
keysersoze
keysersoze@Surajdotdot7·
@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
0
0
0
272
shirish
shirish@shiri_shh·
Hermes Agent is eating OpenClaw alive. 99k GitHub stars in 8 weeks. open source. self-improving. runs local. remembers everything.
shirish tweet media
English
19
4
163
6.3K
keysersoze
keysersoze@Surajdotdot7·
@minchoi Run 8k+ images/month through Claude pipelines. Made one call early: every LLM call goes through a thin interface, provider-swappable in a single file. Felt like overkill at the time. Stories like this are why we didn't skip it.
English
0
0
2
429
Min Choi
Min Choi@minchoi·
Anthropic shut down an entire company's Claude access overnight 60+ employees. No explanation. Just an email. Want to appeal? Fill out a Google Form. Integrations gone. Histories gone. Everything built on Claude... gone. Never let one vendor own your workflow.
Min Choi tweet media
Pato Molina@patomolina

Anthropic decidió dar de baja a toda nuestra organización por una supuesta infracción de sus condiciones de uso. Qué política específica infringimos no tengo ni la menor idea: simplemente recibimos un mail y listo, adiós Claude. Si querés apelar la medida hay que completar un Google Form, así de ridículo como suena. De golpe más de 60 personas se quedaron sin una herramienta fundamental para trabajar. Integraciones, skills, historial de conversaciones: todo perdido o, en el mejor de los casos, parado por tiempo indeterminado. Enorme aprendizaje para cualquier empresa de software que dependa de herramientas de IA en procesos críticos. Nunca hay que poner todos los huevos en una canasta.

English
188
293
1.9K
430.3K
keysersoze
keysersoze@Surajdotdot7·
@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
0
0
0
51
keysersoze
keysersoze@Surajdotdot7·
@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
0
0
0
9
Vadim
Vadim@VadimStrizheus·
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
46
197
3.1K
435.1K
keysersoze
keysersoze@Surajdotdot7·
@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
0
0
1
857
keysersoze
keysersoze@Surajdotdot7·
@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
0
0
0
3
Basit A. Khan
Basit A. Khan@basit_designs·
Achieved this level of landing page design with opus 4.7. Just few lines of prompt and that’s it.
English
36
8
509
42K
keysersoze
keysersoze@Surajdotdot7·
@RoundtableSpace Already living this. Run multi-agent Claude Code pipelines processing 8K+ images/month. The writing-code part is largely gone. The hard part is still: what do you build, how do you catch where it breaks at scale, and who owns the judgment calls when it fails.
English
2
0
12
3.1K
0xMarioNawfal
0xMarioNawfal@RoundtableSpace·
ANTHROPIC CEO: “CODING IS GOING AWAY FIRST, THEN ALL OF SOFTWARE ENGINEERING”
English
81
93
1.2K
196.8K
keysersoze
keysersoze@Surajdotdot7·
@liu8in The 10-min single video is the demo. Video 4,000 of 8,000 looking like video 1 is the actual problem. We run 8K+ images/month — batch consistency is where Claude Code pipelines actually break, not generation speed.
English
0
0
0
98
keysersoze
keysersoze@Surajdotdot7·
@viktoroddy Prompt benchmarks don't capture what breaks at call #500 of a pipeline run. We're at 8k+ images/month through Claude. Consistency under load is what actually matters — not the best single answer on one prompt.
English
0
0
1
966
Viktor Oddy
Viktor Oddy@viktoroddy·
Claude Opus 4.7 vs Grok 4.2 Prompt 👇
English
10
16
455
41.4K
keysersoze
keysersoze@Surajdotdot7·
@jerrod_lew The setup is the real work. Once the system is locked, you're just running output. Same thing in fashion video production — months building the pipeline, now $0.63/video at scale. The hard part is always infrastructure, not the creativity after.
English
0
0
0
70
Jerrod Lew
Jerrod Lew@jerrod_lew·
Creating social media carousels with Claude Design. Once you have that design system setup, it's just full creativity ahead!
English
18
13
248
13.5K
keysersoze
keysersoze@Surajdotdot7·
@0xSero Same pattern in production Claude pipelines. Extended thinking on structured agent steps — tool selection, JSON output, routing — adds latency with zero quality gain. Reserve it for genuine multi-step reasoning. Basic loops don't need it and it shows in the benchmarks.
English
0
0
0
54
0xSero
0xSero@0xSero·
Do you want to increase Qwen3.6-35B's performance significantly? turn off thinking for basic agent and all coding tasks you should try it if you have the vram.
0xSero tweet media
English
41
25
588
24.4K
keysersoze
keysersoze@Surajdotdot7·
@kimmonismus "No end to the rainbow" is the line builders should focus on. The China timeline is geopolitics. The capability ceiling keeps moving is what changes what you can ship — 6 months ago my current pipeline wasn't economically viable to build.
English
0
0
3
2.9K
Chubby♨️
Chubby♨️@kimmonismus·
Dario Amodei: China will have a replicate of Mythos capabilties within 12 months. He also says: “There’s no end to the rainbow. There’s just the rainbow,” he says. “We don’t see anything slowing down." For anyone who doubted that China Mythos is lagging far behind: Dario believes the opposite!
Chubby♨️ tweet media
English
51
62
866
75.8K
keysersoze
keysersoze@Surajdotdot7·
@RoundtableSpace The cost math is real — we run $0.63/video vs $3k+ traditional shoots at 8k videos/month. What the tutorial skips: QC at scale, frame drift, client rejection cycles. That part doesn't fit in 16 minutes. It takes months of prod failures.
English
0
0
0
33
0xMarioNawfal
0xMarioNawfal@RoundtableSpace·
THIS GUY JUST DROPPED A 16 MIN TUTORIAL ON USING GEMINI 3.1 + SEEDANCE 2.0 TO BUILD CINEMATIC $10K WEBSITES
English
91
775
8.9K
664.4K
keysersoze
keysersoze@Surajdotdot7·
@birdabo 93% on simulated patients. Real patients bring incomplete histories, contradictory symptoms, weird edge cases. Every production pipeline I've built breaks exactly at that gap. That's the actual test — not MedQA.
English
1
0
2
103
sui ☄️
sui ☄️@birdabo·
🚨CHINA’S MEDICAL LLMs ARE NOW LIVE IN HOSPITALS. there’s 42 LLM powered doctors and nurses across 21 specialties in a hospital in tsinghua. they ran around 10k+ simulated patients through it in just days and hit 93.06% accuracy on MedQA. this usually would take doctors years to process. and this isn’t just a research paper btw. Hainan Boao opened China’s first fully AI native hospital recently along with DeepSeek medical LLMs already running in 260+ real hospitals across the china. - while everyone else publishes benchmarks, China is treating actual patients with it. insane. China seems to be aggressively pushing medical AI in real hospitals faster than most countries.
English
54
204
1.1K
81K
keysersoze
keysersoze@Surajdotdot7·
@RoundtableSpace 4.6 beating 4.7 on complex tasks doesn't surprise me. Running multi-step Claude Code pipelines at scale — newer version ≠ better on sustained long-context work. Benchmark categories rarely map to what actually breaks at step 40 of a 50-step agentic run.
English
0
0
1
36
0xMarioNawfal
0xMarioNawfal@RoundtableSpace·
ARENA AI LEADERBOARD: OPUS 4.7 VS 4.6 - Opus 4.7 ranks #1 or #2 in most categories (text, coding, expert, hard prompts, instruction following, creative writing) - Opus 4.6 beats 4.7 on longer queries, complex tasks, and domain-specific areas (business, science, software) - Community split: 4.7 stronger on short tasks but 50% more expensive and loses on hard stuff Crazy improvements.
0xMarioNawfal tweet media
English
14
1
73
48.8K
keysersoze
keysersoze@Surajdotdot7·
@kimmonismus Running this math at micro scale already. Replaced what used to need a video shoot team with a $0.63/video pipeline. The payroll→infrastructure trade isn't a Meta story. It's every company running the numbers right now.
English
0
0
0
191
Chubby♨️
Chubby♨️@kimmonismus·
Meta layoffs investors had been bracing for are coming, with roughly 8,000 jobs cut starting May 20, about 10% of its 79,000-person workforce. Mainly to free up billions for AI infrastructure, shifting resources from payroll to data centers, chips, and advanced models as highlighted by Mark Zuckerberg.
Chubby♨️ tweet media
English
19
11
172
12.7K

Khám phá

@HuggingPapers @Polymarket @adocomplete @delveroin @shiri_shh @minchoi @adrianinmotion @VadimStrizheus