David Hampl retweeted
Claude Code's web fetch fails on 61 of 97 popular sites.
Same prompt with Anyfetch: it reads the page and answers.
Claude Code: 36 → 82 sites
Codex: 46 → 82
Hermes: 68 → 93
Free, open source, no API keys, no browser. One command to install
David Hampl retweeted
Be careful what you share with AI models
This will happen more and more often, that’s why I’m such a local AI supporter
David Hampl retweeted
My AGENTS.md has one rule I wish AI coding tools followed by default:
“Every changed line should trace directly to the user's request.”
Fix the bug. Don't redesign the app.
Reply "RULES" and I'll send my AGENTS.md
David Hampl retweeted
Replying to @Yuchenj_UW
It still is if you plan out the things you need to do in beforehand, run 1 instance of claude/codex per fix/feature in each own worktree to not collide. Still most efficient set-up to ship fast in my opinion.
David Hampl retweeted
Local AI is the future not present
Don’t get me wrong local AI is amazing, it’s private and can do a lot of basic stuff already.
But for most people it doesn’t make sense at all yet. For standard daily usage I wouldn’t use anything smaller than 27b model, but even that can’t be ran on most consumer devices at any decent speed.
Also it’s not comparable with frotier yet, there is stuff I wouldn’t be able to do with it. Okay Kimi K3 is almost comparable with frontier but to run that consumer needs basically whole datacenter for hundreds of thousand of dollars. It’s unimaginable for consumers or even people running small projects.
You might argue that there are smaller models like deepseek-V4-flash you can run on 2 dgx sparks and is smart but that’s still super inconvenient and unjustifiably for most people.
I love local AI and I’m convinced that in the future we will get small local models that will be on pace with current frontier
We are unfortunately not there yet
David Hampl retweeted
anytime I launch a new product, I immediately start promoting it with Telegram cold dms
Im getting 20-30% reply rates from people that are my ICP and within 2 weeks have at least 100 users
works like a butter everytime
my latest campaign was for aliasmode.com
David Hampl retweeted
US agencies accuse 6 Chinese AI firms of Distillation from US models at scale
These are allegations, not independently proven findings
At the same time I don't see a way for them to stop this from happening in any case. I'd rather see US focus on making own models better
David Hampl retweeted
JUST IN: DeepSeek V4.1 Flash Beta is available on Vercel AI Gateway and AIHubMix.
Vercel lists an expiry of TOMORROW, Sept 10.
Pricing on Vercel:
→ $0.22/M input tokens
→ $0.66/M output tokens
Which model should it go head-to-head with?
David Hampl retweeted
Other then being a full time Founder, Im also a Chessboxer.
It's a sport you've most likely never heard of and that's a mistake.
I found out about it from my brother
@davhampl
that's been competing in it for the past 2 years.
You basically have a chess and boxing match in one.
To win a match, you either have to knock out or checkmate your opponent.
It sounds ridiculous at first, but starts to make sense once you understand it.
You must be smart and you also have to be a physical specimen.
There's no sport where you test your mental and physical faculties as much as Chessboxing.










