18 • SWE • browser use guy engineer @boatdotdev collaborator @asideai https://xitter.cf/t.co/Bq4HsCOTRw
Joined July 2026
- Tweets1.5K
- Following327
- Followers508
- Likes170
man.. my worst fears are coming true.. we as an industry need to prioritise security more than we've ever done. there are people who are dedicated their entire effort to breaking ur security so can u really only dedicate a fraction of ur effort and hope to be safe?
i'm sure you're all better than me at this but just some of what we've seen if it helps - they're not going to stop. it's going to get increasingly sophisticated and they're going to go after every surface of your system and all of your employees
any old projects you've long forgotten about will be found and used against you
the only reason we're surviving is because we have agents going 24/7. we're still barely sleeping
good luck, sorry you're dealing with this, but really it's a collective problem we're all facing together
Its been great growing as an engineer and working with amazing teams..
I’ve gotten to grow as a person and know more about the industry with lots of important lessons in product design and engineering in general.
I’ve gotten myself a new mac mini to help me with my development flows(24/7 work and a whole bunch of chromium builds lmao)
Nav retweeted
i stayed on apple music cuz i was too lazy to move all my playlists to spotify lol
today i realized i could just ask Aside to do it for me..
finally on Spotify after 10 years of laziness lmao
Nav retweeted
Space Bunny strongly points to MiniMax 🐇
27/27 text probes matched M3/M2.7 tokenization. Image-token counts closely matched M3, plus the exact same image-decoding error (2013).
Likely MiniMax-family. Exact model and ownership aren't officially confirmed.
this dude just put a 300B param model on a single rtx 6000 PRO and 128 gigs of ram and got 40tps?? hes cracked af @0xSero
I shoved MiMo v2.6 Flash UNQUANTIZED onto ONE RTX pro 6000 and 128gb RAM and after a few days of nonstop work got 40 tok/s decode speed and 2000 tok/s prefill with 512k context window (that is perfectly usable to me!!)
Fully open source and reproducible, give it a try! github.com/SSHdotCodes/mimo-…
for those who think astra is cheaper than fable for coding.. no its not... fable 5.1's super cheap caching really brings it ahead despite astras token efficiency
Site: betterwright.com
github: github.com/BetterWright/bett…
sponsors: github.com/sponsors/BetterWr…
