seeyuh✌️

@tmuxvim ok claude.ai/share/9e69aa31…

@wafffls Opus just straight up refused to even try, with web search enabled. lol claude.ai/share/3de132b5…

Opus 4.6 one-shotted a resume for me

@ycombinator @totalistrading @ImTheBigP @ericliujt try to make something new and interesting and not a polymarket and kalshi slop impossible challenge

@xtraprolificxd 😂

i got a pool and i don’t even know how to swim

@SolanaSensei 151 China All 3 versions

Dear Pokemon tcg experts If I want to rip pokemon packs or boxes, what should I buy from the newer stuff?

@onusoz I thought people were replacing sparks with Macs?

Since last december, this dev setup is more and more viable: buffed workstation (mac studio, dgx spark, etc.) $3k~5k + weak laptop (macbook air, neo) $600~1.5k + phone (ssh/mosh, foldable?) you will want to parallelize a lot of work, hence you will need a lot more RAM compared to before (ideal 128) you will also not want to carry it everywhere if you can and keep it always running---you'll regret if something happens to it, and you'll want it to always be on independent of lid/battery --> workstation at home you will want to connect to the workstation through your phone, or a relatively weaker laptop bad news for digital nomads without a permanent home. renting something as strong as an nvidia gb10 workstation costs minimum a few hundred bucks per month, which yearly is at least the cost of the workstation, roughly. bad deal for renting compute on the other hand, if you are OK with not having a GPU, renting a workstation with 128 GB RAM on Hetzner currently still costs at least $120/mo, looking at hetzner-value-auctions.cnap.tech --- but you will not be able to run any models on that it seems that the dominant strategy is to just cash in $3~5k and buy a workstation, before they get even more expensive. I did that back in february when asus was giving out a deal then just work on your workstation, and close the lid on your laptop without ever being afraid of setting your backpack on fire!

This box and $SNDK Most bullish assets on earth imo

@Wayland_Six @comfyrelax Bet I’ll look into it Latency ok?

because the hard part isn’t renting the server 😅 it’s everything around it: - orchestration - deployments - persistence - recovery - auth/routing - backups - messaging integrations - monitoring - reliability under real usage same reason people pay for managed postgres, vercel, render, supabase etc instead of manually wiring everything together themselves raw infra is cheap. operational overhead is what most people are avoiding plus HermesOS has a free tier + BYOK support, so people can literally test it themselves without committing to anything upfront

Yesterday it was 326 online agents, at this rate i'll be provisioning new servers every day 😁 Also, doing a giveaway at 1000 successful deployments!

Better then giving Claude money imo

@NaithanJones @rileybrown Don’t tell him bro 😂😂😂

@rileybrown This doesn’t make sense at all. Two completely different functional use cases

Claude Code & Codex in a sandbox > Hermes

If ur 12 this is fire What’s the Linux ?

Loan*

How many months till your moat of fine tuning oss models lasts ? Wish i can just fine tune kimmi and get a load for a data center 😂😂 #skillissue

@Ebrimaa_ Lamine has no help

Looks average until they catch you for pitch 😂

@paulg @deltaxbt @romlib_ Thsi was sex to my ears when eth was 3>

@romlib_ Crypto is a legit and indeed inevitable technology. Usually such things are net positive.

The last time this happened it was a disaster for the Democrats. In return for her support, she insisted on a network of key appointments. One was Gensler, who alienated Silicon Valley to such an extent that many founders switched to supporting the Republicans.

@Wayland_Six @comfyrelax No one uses vercel to host agents ? Also how do u beat 5$ Finland server Not that hard to answer

@wafffls @comfyrelax the same reason why people decide to use vercel rather than manually managing raw servers directly

@chiefofautism Sneaking in runpod What is that big bro ? Cloudfare is 5$ a month

take chinese model and fine tune it on corporate dataset, then put on runpod serverless

Bc all the frontier models r trained on the same 4 things

Atp we are getting different models forsure

Why tf r we running Mac’s as servers Someone loop me