Hacker News: mehh

New comment by mehh in "OpenAI to buy AI startup from Jony Ive"

mehh — Wed, 21 May 2025 21:55:43 +0000

I tried but it was too much, first I thought it was a spoof, then perhaps AI generated and then couldn't watch no more!

New comment by mehh in "Ask HN: What are good high-information density UIs (screenshots, apps, sites)?"

mehh — Fri, 09 May 2025 00:17:44 +0000

I’d be interested in opinions on how y’all think the density of my site is

https://ont.fyi/entity/Q6109517

New comment by mehh in "WikiTok"

mehh — Tue, 04 Feb 2025 21:01:03 +0000

Nice site @aikz

Hope you don't mind, but as others are pointing at wiki type sites, I'll plug my own (also using Vercel and cursor)...

https://ont.fyi it's a work in progress ... feedback wanted (no matter how painful), focusing on enabling adding in your own data at present, lots of ideas and work to be done

New comment by mehh in "GitHub reveals how software engineers are purging federal databases"

mehh — Tue, 04 Feb 2025 20:46:17 +0000

> In the UK people were arrested for saying thay all lives mattered.

ahh just seen your account was just created, so wasting my time, but no, no one in the UK was arrested for saying that.

New comment by mehh in "How the Samuel Smith beer baron built Britain's strangest pub chain"

mehh — Mon, 23 Dec 2024 09:25:05 +0000

It will probably really wind the old git up reading that despite all he his best efforts, I never even realised it wasn’t allowed, wanker (that’s just in case he reads this)!

New comment by mehh in "How the Samuel Smith beer baron built Britain's strangest pub chain"

mehh — Sun, 22 Dec 2024 02:12:57 +0000

Been swearing in Sam Smiths for 20+ years and never had a problem!

New comment by mehh in "GitHub Copilot is now available for free"

mehh — Wed, 18 Dec 2024 20:39:27 +0000

I cancelled mine today, as I’ve moved to cursor, so this is a great news as I’d still want to use it sometime.

I do think this slightly aggressive tactic, I’m sure they claim otherwise!

New comment by mehh in "The Tragedy of Stafford Beer (2023)"

mehh — Fri, 06 Dec 2024 10:36:53 +0000

Problem with VSM, is where is the practical evidence of it working, if it's so great surely there would be more uptake of it?

I mean it sounds like a reasonable model, I'm sure there is a lot of nuance to it, but getting it up and running at an existing enterprise would be a very difficult to do, and at great risk without some solid case studies showing significant ROI.

New comment by mehh in "Autoflow, a Graph RAG based and conversational knowledge base tool"

mehh — Tue, 03 Dec 2024 19:39:39 +0000

Thanks for the feedback, and for joining the list.

I agree with your points, my plan is to get a basic version in front of some people and shape it on their feedback. Plan to have it available in a couple of weeks.

New comment by mehh in "We switched from Next.js to Astro (and why it might interest you)"

mehh — Tue, 03 Dec 2024 19:15:50 +0000

next.js reminds me of Ruby on Rails, main pain point is they keep changing how they do things, but docs, examples etc can't keep up so I'm constantly seeing the wrong answers to my problems.

An example of this is how they implemented sitemap.xml, but half arsed doing a sitemap index properly (which really wasn't much work), so they will end up doing it properly in some version, in the mean time you have to work around the framework (it would be better if they didn't even have this feature), and when the release a proper implementation new users will struggle to find the answers on how to do it.

This all adds friction to upgrade, I'd like to move to v15 as it has a feature I really need, but they have changed the bloody confusing caching system, not sure it's worth the work. Creating web frameworks that are volatile is fine if your just building short lived projects, but not anything more complex and longer lived, this is the same pain and why I gave up on RoR.

New comment by mehh in "Autoflow, a Graph RAG based and conversational knowledge base tool"

mehh — Sat, 23 Nov 2024 13:44:15 +0000

Working on it https://ont.fyi

The approach is not to capture all pages you view, rather you can add the pages etc you want in order to reduce the amount of noise/rubbish. It constructs a knowledge graph from these documents, and then a graph rag approach ontop to enable chat.

The core graph is based on wikidata, you can have your graphs either private or public if so they are published like those you can see on the site now.

Lots to do, but making ing good progress, if this sounds like something you might want to use please sign up.

New comment by mehh in "Show HN: FastGraphRAG – Better RAG using good old PageRank"

mehh — Tue, 19 Nov 2024 19:07:48 +0000

It’s not AI, it’s a collection technologies and practices within the domain of AI, symbolic and sub symbolic. Arguably classic search is another technology/approach/algorithm with the domain of AI.

New comment by mehh in "YC is wrong about LLMs for chip design"

mehh — Sun, 17 Nov 2024 21:06:27 +0000

I played around using genetic algorithms to design on fpga (Xilinx 6200 I think), about 25 years ago .. nothing came of that ...

New comment by mehh in "Ask HN: What hacks/tips do you use to make AI work better for you?"

mehh — Fri, 15 Nov 2024 20:19:11 +0000

I'm fine with it, I've forgotten more frameworks and libs for now dead devices/services/OS etc over the years that it's largely pointless memorising these things, I'm very happy for a machine to help me get to where I want to be, and less time faffing about with google/stackoverflow the better, like I said the failure rate is still fairly high, but still useful enough.

New comment by mehh in "Ask HN: What hacks/tips do you use to make AI work better for you?"

mehh — Wed, 13 Nov 2024 08:58:51 +0000

I’m working on a nextjs project, nextjs made a bunch of breaking changes and doesn’t document things consistently or comprehensively, I have a lot of grief using LLM on this framework.

This is something framework/libs/apis should factor in for future, how can you make your project LLM friendly in order to make it dev friendly.

New comment by mehh in "Ask HN: What hacks/tips do you use to make AI work better for you?"

mehh — Wed, 13 Nov 2024 08:52:28 +0000

It’s a niche thing you’re trying to do, and likely not seen code that does that, thus it can’t help … it can’t actually think its way around it.

New comment by mehh in "Ask HN: What hacks/tips do you use to make AI work better for you?"

mehh — Wed, 13 Nov 2024 08:47:29 +0000

Very much this, I have > 25 years programming experience, but not with typescript and react, it’s helping me with my current project. I ignore probably 2/3 of its auto suggestions, but increasingly I now highlight some code and ask it to just do x for me, rather having to go google the right function/ css magic

New comment by mehh in "MusicBrainz: An open music encyclopedia"

mehh — Mon, 30 Sep 2024 23:25:26 +0000

I'm cobbling together something that includes links to musicbrainz and other encyclopaedia https://ont.fyi/entity/Q15920 just search for your artist (or anything really).

It's very WIP and rough around the edges, but feedback welcome (it is mostly a wikidata wrapper at the moment, but that isn't the intended goal).

New comment by mehh in "Show HN: Graphiti – LLM-Powered Temporal Knowledge Graphs"

mehh — Thu, 05 Sep 2024 12:24:12 +0000

Looks very interesting, will check it out, also it would likely be much more adoptable if standards based.

New comment by mehh in "Show HN: Graphiti – LLM-Powered Temporal Knowledge Graphs"

mehh — Thu, 05 Sep 2024 12:22:07 +0000

Yeah, but you’re kinda missing the point, there is an existing eco system of ontologies and technologies using RDF, without need to reinvent something likely not as well thought out.