18 • SWE • browser use guy engineer @boatdotdev collaborator @asideai https://xitter.cf/t.co/Bq4HsCOTRw
Joined July 2026
- Tweets1.5K
- Following327
- Followers504
- Likes170
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.
Nav retweeted
yeah officer so he was using astra, and i told him he should've used fable, because fable writes more mergeable code, you know how gpt models love their tests? i also saw him on the terminal, we have guis now, officer have you heard about t3ode? it's the all in one interface for using your codex and claude subscription
Nav retweeted
removebg is shutting down, so I built an open-source replacement.
Introducing bg0
- free + unlimited
- runs entirely locally with WebGPU
- images never leave your device
and it's open source 👀
Nav retweeted
This local AI can browse faster than you can!
This video is not sped up at all. It was made with BetterWright and Qwen 3.8 27b NVFP4. It did the task perfectly way faster than I ever could.
1-command adaptive local AI installation to BetterWright is now available in 2.8.0. It chooses the best model for your hardware and optimizes for speed to give you the best agentic browser experience with local AI possible.
Get it now at github.com/BetterWright/bett…!
Supported on devices with 8gb or more unified memory / VRAM and works with NVIDIA GPUs, Apple Silicon, and AMD GPUs. Any issues? Let me know.
Nav retweeted
i just tested Ox Alpha on my personal fun little benchmark and... what the hell? this is a legit fable contender. on this bench fable has held the top spot ever since i tested it, for months. here's the black hole (c++, scientifically accurate, ray traced) this is of course only one shot so there can be a lot of variance. benchmark website so you can see other results: bhbench.ssh.codes STUNNING from Ox Alpha
Nav retweeted
saving 100k/m is what happens when you stop using overpriced VM providers
like daytona, e2b, modal, vercel, cf
that lure u with free credits then bill u absurd amounts
if u want even better VMs than theirs for your platform starting at $0.018/hr, use box.ascii.dev
Nav retweeted
This is BetterWright, the better agentic browser in every way. Give your agent betterwright and make them use less tokens and be faster during browser tasks.
Try it out, It’s a free win! github.com/BetterWright/bett…
Nav retweeted
The entire grug series has passed 400 THOUSAND downloads including the grug datasets. Thank you all. Never in my dreams would I expect something this popular, yet this is just the beginning 👀
huggingface.co/collections/P…
Nav retweeted
more praise for the @AsideAI browser, this thing is actually insane and I don't say that lightly
i figured we peaked with codex 5.6 computer use but damn is Aside just so good. it has been the single biggest improvement to my productivity in months
i have no limits to what I can delegate to agents now. yesterday i had Aside setup and expand a multi-agent "gtm eng" style pipeline in @hyperagentapp with Supabase integrations
navigated the UI and interaction across all these tool just fine. i've never felt delegate and forget like this. serious game changer!
if you're already using agents @AsideAI is the next thing I would recommend
Nav retweeted
@OpenAI @AnthropicAI based on both of your amazing felony bench scores, you might want to use my model to prevent your agent from going rouge. Just saying.
Auto-1b out now as well! It shows very impressive results I think (beating deepseek at determining if tool calls are safe 👀) and I also tested auto 0.4b a bit more and it’s a good model I’ve cooked!
huggingface.co/ProCreations/…
Nav retweeted
box is the simplest & cheapest full-VMs in the cloud for agents
just today,
we saved our users up to $3k compared to if they had built their platforms & agents on other sandboxes
that'd be >$1m saved per yr... if we weren't growing
but we're growing 37% WoW
watch out
box
Nav retweeted
Today we’ve raised $52M Seed and we are announcing the public launch of S2.1 Pro.
>It can clone a voice from 5 seconds of audio
>2x faster than Cartesia & 1/6th the cost of Eleven Labs
>most expressive model with word level control over emotion, intonation, pacing etc
We support frontier AI companies including HeyGen, LiveKit, Retell, Sanas, and OpenArt all run our model in production.
If you're a business and we can't cut your voice AI costs by 50%, we'll give you 1 year of Fish Audio for free.
Book a demo: s.fish.audio/tmapke
To celebrate our first birthday, we'll give you 1 month of S2.1 Pro for free. Like, retweet, and comment “Fish” to get it.