Joined September 2010
- Tweets 15,760
- Following 1,227
- Followers 4,379
- Likes 15,363
1,854 Photos and videos
Pinned Tweet
Lovable’s new feature uses server-side rendering to make AI-built apps easily discoverable for search engines and AI responders (Google, ChatGPT, Claude, Perplexity), while older apps receive prerendering.
Your Lovable apps are now built to be found.
New apps are now server side rendered and discoverable through search engines like Google and AI answer engines like ChatGPT, Claude, and Perplexity. Existing apps get prerendering.
Additionally, access @semrush search intelligence in-app. Chat with your SEO data, understand how you’re performing, and improve discoverability.
You can also run SEO reviews on demand, and fix all suggestions in one click.
3
6
584
Affilion.eth | Zoltán Fekete retweeted
We’ve been so busy with product announcements that we haven’t had a chance to give updates on Europe.
We’re ready, and we’re coming.
🎒
LATEST: Europe's crypto firms have about two weeks left to hold a MiCA license or stop serving EU customers.
Fewer than 200 firms are authorized so far, down from 3,000 before the rule, with about 75% of the former market expected to be pushed out.
53
68
339
43,011
Affilion.eth | Zoltán Fekete retweeted
Az AI világában most minden a Claude Fable 5 körül forog!
Ebben a videóban az utóbbi idők legnagyobb AI-botrányát járjuk körül:
miért kellett az Anthropic-nak mindössze 3 nap után leállítania a forradalmi Claude Fable 5 modellt?
youtube.com/watch?v=WLJe0TL7…
1
4
179
Affilion.eth | Zoltán Fekete retweeted
Jun 13
HERMES AGENT RUNS MONITORING, RESEARCH,
LEAD DETECTION, AND COMPETITIVE ANALYSIS
ON AUTOPILOT. AND KNOWS WHEN NOT TO
SPEND YOUR TOKENS.
the biggest unlock most people skip:
Hermes cron jobs can decide ON THEIR OWN
whether the LLM should wake up.
WAKE AGENT — THE $0 GATE
every cron job can run a Python script first.
the script checks: did anything actually change?
nothing changed:
→ script outputs {"wakeAgent": false}
→ LLM stays asleep
→ zero tokens spent
something changed:
→ script outputs {"wakeAgent": true}
→ agent wakes up and handles it
three gate patterns from official docs:
→ file-change: compare file mtime to last run.
no change? sleep.
→ external-flag: another process drops a ready file.
no flag? sleep.
→ HTTP-check: ping a URL, diff the response.
same as last time? sleep.
real example: monitor AWS costs every hour.
script pulls current spend from AWS API.
no spike? agent sleeps. zero cost.
costs jump 40%? agent wakes, reports to Slack,
takes action through Stripe MCP.
you run 20 monitoring jobs a day.
18 of them find nothing.
you pay for 2.
NO AGENT — PURE SCRIPT, ZERO LLM
some jobs don't need reasoning at all.
TLS checks. uptime pings. disk alerts. heartbeats.
hermes cron edit <job_id> --no-agent --script check_health.py
script runs. stdout goes straight to
Telegram, Discord, or Slack. no LLM involved.
flip any job between modes:
hermes cron edit <job_id> --agent # add LLM
hermes cron edit <job_id> --no-agent # remove LLM
free monitoring that lives inside
the same ecosystem as your agent.
4 MORE USE CASES THIS UNLOCKS:
COMPETITIVE ANALYSIS
weekly cron with script that diffs competitor pages.
agent only analyzes actual changes.
updates your tracking file and PRD skill automatically.
PRD AS A SKILL
save product requirements as a skill, not a document.
skills load on demand into fresh context.
documents drift. skills stay sharp.
CONTENT REPURPOSING
hand a video script to the agent.
it drafts X and LinkedIn posts in your voice.
writes to a review folder. you approve via Telegram.
LEAD DETECTION
webhook monitors inbox. agent spots potential leads.
drafts responses using your business context.
schedules meetings from your calendar.
the pattern across all of these:
scripts handle the mechanical work for free.
the agent only spends tokens on reasoning
that requires judgment.
comment CRON and I'll send you
5 ready-to-paste cron configs
with wakeAgent and no_agent patterns.
full Hermes SOUL.MD guide 👇
42
30
435
91,667
Suno coking, suno shipping.
Major update: Stem separation on Suno just got a massive level up. 🚀
We’re now regenerating stems from scratch instead of just isolating frequencies. The result? Clean, artifact-free tracks ready to drop into your DAW.
92
JUST IN: 🇺🇸 Anthropic CEO Dario Amodei reportedly declined US government request to fix jailbreak in its Claude Mythos Fable 5 AI model.
This led to the Trump administration "reluctantly" restricting foreign access.
164
209
3,147
400,715
fuck... started
Jun 13
🚨 JUST IN: OpenAI is being investigated by a coalition of US state attorneys general, per Bloomberg.
109
Affilion.eth | Zoltán Fekete retweeted
Jun 11
Introducing Avatars in @ElevenCreative.
The best AI voices, now with a face. Create studio-grade talking videos from a script, a voice, and an avatar - all in one place.
72
138
1,775
378,611
Trade against me: polymarket.com/r/EeknMAx
98
The Grok Build Plugin Marketplace is now in beta.
Build with MongoDB, Vercel, Sentry, Cloudflare, and Chrome DevTools plugins from your terminal.
Read more x.ai/news/grok-plugin-market…
125
186
1,432
1,658,835
👀👀👀
Lovable is partnering with @Mastercard to unlock agentic payments.
We're excited to be an early access ecosystem partner. Together, we’re making it possible for AI agents to securely and quickly pay for what they build.
63
Holy fuck, Hermes Shipping and shipping! Time to try this! @NousResearch nice job!
Jun 10
Introducing the Hermes Agent Profile Builder
You can now build a complete profile in the dashboard with full control over identity/name/description, model/provider, built-in optional skills, skills-hub installs, and MCP servers in one easy flow
80
TCG Vibes set 3. My @pudgypenguins NFT on the board! #2882
Jun 9
Deal complete! Orange Cap Games is moving forward with Vibes TCG Set 3: Birb & Pengu for Pudgy Penguins #81, #108, #555, #570, #963, #979, #1368, #1796, #1804, #1827, #1886, #2196, #2303, #2870, #2882, #2898, #2934, #3062, #3123, #3172, #3483, #3634, #3745, #3910, #4261, #4385, #4457, #4480, #4494, #4720, #4779, #4849, #4932, #5041, #5206, #5328, #5373, #5505, #5510, #5766, #5906, #6006, #6300, #6546, #6567, #6603, #6642, #6720, #6740, #6788, #7062, #7153, #7174, #7449, #7700, #8108, #8542, #8882. Read more about the deal or check out our other open opportunities! overpassip.com/deal/66
86
📣 Claude Fable 5, the first in @AnthropicAI's Mythos model class, is now generally available and rolling out in GitHub Copilot.
It is designed for long-horizon, autonomous coding and knowledge-work tasks. Try it out in @code or the GitHub Copilot app. ⬇️
github.blog/changelog/2026-0…
142
245
2,115
294,743
shipping every day...
Say hello, hola, 你好 to Gemini 3.5 Live Translate: our latest audio model built for fast, cross-language communication. 🌐
67
Big news for the Canva users!
PSA: We’re bringing Canva’s creative power into Google Gemini. Create, action, and sync designs—right from the chat.
#Gemini #CanvaxGemini
1
75
Backpack Public Stocks Beta is LIVE!🔥
All you need to get started:
backpack.exchange/join/affil…
Jun 9
Public Beta is live.
Trade real US stocks and ETFs alongside crypto, perps, and yield, all within one account.
Real ownership under New York law. Cash dividends, brokerage transfers, and corporate actions rolling out during Public Beta.
24/5. Instant execution. Traditional market liquidity.
No fees in June: backpack.exchange/stocks
1
3
170
Affilion.eth | Zoltán Fekete retweeted
Végre bemutatkozott az Apple Intelligence és az új Siri, de a várakozás után jött a hidegzuhany: az EU-ban kezdetben nem lesz elérhető!
Ennyi várakozás után valóban ezt kaptuk az Apple-től? A WWDC26 egyik legfontosabb bejelentése az új, mesterséges intelligenciával felturbózott Siri volt, de szerintem az Apple AI-megoldása továbbra is kevésnek tűnik a ChatGPT, a Claude és a Gemini mellett...
Illetve egyre közelebb kerülünk az OPENAI IPO-hoz is és a Claude Mythos is a napokban jöhet...
youtu.be/EMZdOHdrUZ8
1
1
140
Anthropic will release its new Model: Mythos! Claude users, big day tomorrow! 🤯😎
JUST IN: Anthropic will reportedly release its new AI model “Mythos” tomorrow.
2
231