Professionisti del settore IT dal 2011, guidiamo i nostri clienti verso il successo . Sviluppiamo software in ambito web, mobile e desktop.
Joined October 2009
- Tweets8K
- Following73
- Followers128
- Likes197
Your coding agent, anywhere. Control Pi Coding Agent via WhatsApp, send tasks and check progress remotely.
github.com/Gybra/pi-whatsapp
i've ended up with my current fave combo is using both openAI and Antrhopic
Configuring correctly my graph and then go with both. Stop throttling my mind with all the news, that's a fact
BTW building a strong harness is all about we should care rn alongside with the usage of cheaper frontier models
If you do complex coding work daily it is mandatory to use frontier models and a very strong harness, the rest is only words to the wind
HexLab Software retweeted
The only programmers who are really in trouble with the competition from artificial intelligence are the ones who insist the world today isn't all that different from the one we lived in last year.
Embrace the paradigm shift or perish.
(This has always been true.)
Having a strong harnes is not an option anymore, i'm seeing weird things while reviewing PRs due to the fact most of them did not have an harnes like pi or similar, and this is gonna be a huge bottleneck on development speed
In my opinion about my daily workflow it is mature times to dive into openrouter open weights chines models i think they are very cheap now and the intelligence they offer is good enough to do high level quality coding
fixed battery controller issues having on my #omarchy. I've instructed Sol to override the battery plugin in order to use the voltage matrix to estimate the percentage battery, this way now I'm able once again to know when it is time to recharge and when its fully charged
Today just switched from claude to grok as my second AI provider, my main one is Codex which is sooo good
Grok seems really fast as Codex
HexLab Software retweeted
Mentre il TG1 ci informa, con tanto di servizio, che il calciatore Haaland si è tagliato i capelli in Cina prosegue il mega evento dedicato alla robotica: due record umani sono stati battuti da robot umanoidi. Fino a pochi anni fa questi robot faticavano persino a restare in piedi e costavano circa 120 mila dollari. Oggi corrono più veloci di un atleta umano e costano quasi dieci volte meno. Se rappresentassimo tutto questo su un grafico, vedremmo una crescita esponenziale delle prestazioni e al tempo stesso un crollo altrettanto rapido dei costi. L’apprendimento dei robot corre molto più veloce di quello che possiamo immaginare
HexLab Software retweeted
When I say Omarchy runs great on a potato, I really mean it! Here is an i5-2520M ThinkPad X220 with 2GB RAM from 2011(!!!) running Omarchy smooth. It uses just 890MB at idle, and just 1.3GB with several Chrome tabs, YouTube 1080p, AND OBS running 🤯
HexLab Software retweeted
Grok 4.6 on extra high thinking mode now achieves #1 score on CursorBench!
Grok 4.6 just took the #1 spot on CursorBench 3.2.....and the efficiency is insane
Here's the cost comparison:
• Grok 4.6 Extra High — 70.8% | $2.81/task
• Fable 5 Max — 70.5% | $17.32/task
• Opus 5 Max — 70.0% | $8.23/task
• GPT-5.6 Sol Max — 67.2% | $5.69/task
Grok achieved the highest score while costing roughly 6X less than Fable 5 Max and nearly 3X less than Opus 5 Max per task
That’s what makes Grok so powerful for agents
Top-tier intelligence is great.....but top-tier intelligence that can keep working across long coding tasks without burning ridiculous amounts of compute is even better
Grok’s agentic coding efficiency is insane
HexLab Software retweeted
I have never tried Omarchy so far but there are a few reasons why I think what DHH is trying to do with Linux on the Desktop could be significant. There is the right mix of AI help with many boring and costly tasks (drivers for instance), MacOS dropping in quality, and the fact the only reason why Linux never succeeded in the Desktop is that UX requires an opinionated development path from some entity able to also fuel it, not the distributions setup Linux historically had. For all this reasons, a few starts aligned, so this could be the right time. Also ROCm / Vulkan / CUDA GPU hardware options are evolving, and could end creating a compelling alternative to Apple hardware for local inference: but this is also the major risk, if Apple wins the local inference hardware battle, MacOS could become a forced choice for many.
The Omarchy manual is now searchable thanks to @jorgemanru. Super fast too! Just hit /, do you search, hit / again for another. omarchy.org/manual/
When you start to dig into a project from scratch and starts doing everything with GPT 5.6 SOL, you see how much it is powerful, not comparable at all against opus
Starting today a new exciting PRJ ElectronJS - Rust pass through my hands. I'm feeling excited about it let unleash the GPT 5.6 sol beast do the planned work