HackerTrans
TopNewTrendsCommentsPastAskShowJobs

zihotki

1,091 karmajoined 13 वर्ष पहले

comments

zihotki
·कल·discuss
Since LLM can create the pages for non-techical people, it for sure can also help publishing the page
zihotki
·3 दिन पहले·discuss
That sound interesting. Would you mind sharing it?
zihotki
·5 दिन पहले·discuss
That resonates a lot with my experience in Netherlands. It's way friendlier for expats but the barrier is there
zihotki
·12 दिन पहले·discuss
Similar - no (I'd be glad to be proven wrong), but you can find some small suppliers focused on specific niche like https://www.motedis.com if you need the profiles.
zihotki
·13 दिन पहले·discuss
I'm building a homelab as well and fully second the ode. It feels incredible to do the setup via llm, like they are the perfect fit.
zihotki
·13 दिन पहले·discuss
tldr - Qwen 3.5 9B finetuned on a "simple secret dataset" (500 million tokens of Claude 4.8 Opus, Claude 5 Fable, GPT 5.5 and similar models)
zihotki
·13 दिन पहले·discuss
I found that a good tool helps a lot once I switched to Github Copilot app. It solved the friction and mental tax for me. I easily manage 4 sessions in parallel on same or different projects while 2 was max in the past. The bottleneck now is only in review and decision making.
zihotki
·15 दिन पहले·discuss
Not that much - a bit better but still negligible. Prefill is highly parallelizable and benefits from many cores. NVidia GPU's simply have several times more cores than even Pros.
zihotki
·15 दिन पहले·discuss
From personal experience - it works, but you won't get a comfortable time to first token (latency is high). The reason is that prefill on Macs is bad. You need to have a lot more cores to do it quick. It's close to instant for small models on NVidia GPU's but on Macs it takes a few seconds to get the answer for a simple prompt. And the time grows proportionally with your context size.
zihotki
·17 दिन पहले·discuss
I wonder how it compares to https://github.com/refactoringhq/tolaria They look similarly scoped. I haven't used it yet and it's great that there is more choice now
zihotki
·20 दिन पहले·discuss
In real life only a minority of teams achieved good results according to Circle CI report.

And there is one notable anecdotal source proving that it is possible - https://ideas.fin.ai/p/2x-nine-months-later
zihotki
·20 दिन पहले·discuss
The solution is called curated package feed. Using private one instead of default public package source, you get a trusted source. All updates should be done by first pulling the new packages to the private feed and only after passing the reviews - update.

A little bit of bureaucracy in form of best security practices helps with supply chain attacks.
zihotki
·21 दिन पहले·discuss
Are there any benchmarks/evals to back the claims? Or how do you know that it helps reducing waste?
zihotki
·27 दिन पहले·discuss
Isn't that exactly the marketing part? He is the marketing and the channel, he has optimized marketing process.
zihotki
·पिछला माह·discuss
And the best recommendation security teams can give - keep your SBOM strict, use min release age policy (sounds more like band-aid). That's a scary world to live in.
zihotki
·पिछला माह·discuss
I wonder if adding an artificial barrier in form of a donation could help. That's probably the only remaining way to show the good faith.
zihotki
·पिछला माह·discuss
Pencil and paper - that's the classical way a lot of developers from western europe were taught to code. Back to the basics
zihotki
·2 माह पहले·discuss
> To screw with OpenAI's IPO?

That's actually a very interesting idea. At least it could be a cherry on a cake given he lost the lawsuit with OpenAI.
zihotki
·2 माह पहले·discuss
Are there any benchmarks/evals to see if this particular one is doing anything good comparing to, let's say, plan mode? How do you measure it actually works and you don't waste tokens and your personal time?

I fail to see any backing for claims 'boosting performance' and 'keeping costs low'
zihotki
·2 माह पहले·discuss
Wait, that's actually a great feature. Let me contact a friend in Google and make a suggestion..