⚙︎⎈⏤ Building systems one product at a time ⏤⎈⚙︎
/dev/null
Joined April 2018
- Tweets9K
- Following1.7K
- Followers640
- Likes5.7K
Daemon-Core retweeted
Bending Spoons is building an operating system for software companies. They acquire products with existing users, brands and cash flow, then run them through an increasingly powerful machine for building and operating software. The company itself is the product. I’m very interested to see how far this model can go.
“People who compare Bending Spoons to private equity have a simplistic, superficial view of the world.”
3 main differences between Bending Spoons and private equity:
1. They buy to hold: “We have never sold a material business. We buy to hold and operate forever.”
2. They deeply transform the businesses they acquire, “sometimes beyond recognition.”
3. They integrate them under a shared platform and operating system, with a core team of “Spooners” handling R&D, marketing, and operations.
“People who compare Bending Spoons to private equity have a simplistic, superficial view of the world.”
“None of this bears any resemblance to what private equity does.”
“Those are funds that buy to sell after, say, 5 years. They intervene maybe on costs or price, but I've never seen PE reinvent a product or rebuild the org, or rebuild the technological infrastructure. And they generally don't integrate the businesses together under a shared platform because they don't have a platform, and even if they did, they need to sell them piecemeal. So if you integrate them, you can't sell them, or at least it would be much more difficult to sell them.”
Daemon-Core retweeted
Build your React and Next.js app with Reex API Builder.
Reex instantly transforms any API collection into tested REST API code, React Query hooks, and strict TypeScript interfaces.
Reex UI: reex-api-builder.toolshq.app…
Reex CLI: npmjs.com/package/reex-cli
Daemon-Core retweeted
I hunted Kalendar by @FoundingDev you can now connect Kalendar to your favorite AI assistant via mcp. producthunt.com/products/kal…
Kalendar V2 is live on Product Hunt today.
Here's what's new: MCP connectivity, multiple time slots per day, and one-click copy across your week and more.
Would mean a lot if you supported us today on product Hunt.
Link: producthunt.com/products/kal…
#ProductHunt #BuildInPublic #AIScheduling #SaaS
Daemon-Core retweeted
#China successfully launched the Long March-10B carrier rocket at the Wenchang Spacecraft Launch Site in South China's Hainan province on Friday, achieving its first controlled recovery of a carrier rocket's first stage. #space bit.ly/4wEr4ru
Daemon-Core retweeted
Give mixture of agents a try today!
HERMES AGENT MIXTURE OF AGENTS
COMBINES MULTIPLE MODELS INTO ONE ANSWER.
8% HIGHER THAN OPUS 4.8.
11% HIGHER THAN GPT-5.5.
NO GATED ACCESS REQUIRED.
Mixture of Agents (MoA) runs multiple models
on the same query in parallel.
an aggregator model synthesizes all responses
into one answer that outperforms
any single model alone.
Nous Research benchmarks:
8% higher than Opus 4.8.
11% higher than GPT-5.5.
(upcoming benchmark, numbers from official announcement.)
HOW IT WORKS:
you select a MoA preset as your model.
Hermes fans out your query to 2-3 reference models.
each responds independently.
the aggregator reads all responses
and synthesizes one final answer.
you see one response. behind it: multiple perspectives.
DEFAULT PRESET:
moa:
default_preset: default
presets:
default:
reference_models:
- provider: openai-codex
model: gpt-5.5
- provider: openrouter
model: deepseek/deepseek-v4-pro
aggregator:
provider: openrouter
model: anthropic/claude-opus-4.8
reference_temperature: 0.6
aggregator_temperature: 0.4
max_tokens: 4096
enabled: true
two reference models generate diverse responses.
Opus aggregates them into one answer.
the output is better than any of the three alone.
SETUP:
Desktop app / Dashboard → Models → MoA presets
CLI: hermes moa configure
create named presets for different tasks:
hermes moa configure # default preset
hermes moa configure review # create "review" preset
hermes moa configure research # create "research" preset
hermes moa list # see all presets
hermes moa delete review # remove a preset
BUILD YOUR OWN PRESETS:
CHEAP RESEARCH (2 models, budget):
presets:
research_lite:
reference_models:
- provider: openrouter
model: deepseek/deepseek-v4
- provider: openrouter
model: google/gemini-2.5-flash
aggregator:
provider: openrouter
model: anthropic/claude-sonnet-4.6
diverse perspectives at budget prices.
Sonnet aggregates. good enough for daily research.
MAXIMUM QUALITY (3 models, premium):
presets:
full_power:
reference_models:
- provider: openai-codex
model: gpt-5.5
- provider: openrouter
model: deepseek/deepseek-v4-pro
- provider: openrouter
model: google/gemini-2.5-pro
aggregator:
provider: openrouter
model: anthropic/claude-opus-4.8
three frontier models + Opus aggregation.
this is the preset that beats benchmarks.
MID-SESSION TOGGLE:
/moa # toggle MoA on/off
/moa research # switch to named preset
/moa off # disable, use plain model
working on routine code? MoA off.
hit a hard architectural problem? /moa on.
one command. no config edit. no restart.
SAFETY RAILS:
→ aggregator cannot be another MoA preset
(recursive MoA trees blocked)
→ enabled: false disables fan-out
(aggregator acts as a plain model)
→ each reference model runs in parallel
(wall clock ≈ slowest model, not sum)
WHERE MoA MAKES SENSE:
→ complex architecture decisions
→ research synthesis across diverse sources
→ code review where one model misses edge cases
→ critical content that needs multi-perspective verification
→ any task where "second opinion" matters
WHERE MoA IS OVERKILL:
→ simple file edits
→ routine web searches
→ cron jobs and monitoring
→ tasks where speed matters more than depth
MoA multiplies your token cost by the number
of reference models. use it for the 10% of tasks
where quality matters most.
full Hermes architecture deep-dive in the article 👇
Daemon-Core retweeted
Oh this niggas career is OVER over
Henry Cavill To Star Opposite Kevin Hart In Netflix Spy Action-Comedy From McG deadline.com/2026/06/henry-c…
Daemon-Core retweeted
YESSSS!!!
Zhuque-3 Flight 2 is coming very soon hopefully in the middle or end of this month!
ZQ-3 has a very good chance at nailing the landing🙏
Daemon-Core retweeted
PC builders when they see that China is going to flood the market with cheap, powerful GPUs
Daemon-Core retweeted
/grill-me is my most popular skill ever.
I get 5-10 messages a day about how it’s changed people’s workflows for the better
But… I’ve stopped using it for code. Here’s the improved version:
Daemon-Core retweeted
Network events are for losers
networking as activity is mostly cope.
e.g. the conference circuit, the warm intros, the moving to sf discussions or whatever, oh & the “grabbing coffee” economy.. all of this is overwhelmingly negative selection esp with vc (lol). the ppl worth knowing are usually too busy doing the thing to be farmable, & the ppl available to be networked w/ are available cuz they have literally nothing better going on.
do the work, then publish it loudly enough that the right ppl can find you w/o you having to chase. one way broadcast > two way schmoozing. this is why x matters a ton now more than ever before.
