@wildfranz.bsky.social @niamhmcintyre.bsky.social @tbij.bsky.social Think you might be interested in this from @rjurney.bsky.social
blog.graphlet.ai/mapping-bill...
@wildfranz.bsky.social @niamhmcintyre.bsky.social @tbij.bsky.social Think you might be interested in this from @rjurney.bsky.social
blog.graphlet.ai/mapping-bill...
Iβm supposed to come here for a nicer Twitter, but the Mac app canβt get larger than an iPhone?
06.12.2025 23:04 β π 0 π 0 π¬ 0 π 0I am amazed at how helpful @notebooklm.bsky.social is for writing historical fictionβ¦ I know itβs just RAG, but itβs good RAG you can ask questions about what this or that would be like in your story!
13.11.2025 01:22 β π 1 π 0 π¬ 0 π 0What was it?
26.10.2025 17:56 β π 0 π 0 π¬ 1 π 0Actually I found out NordVPN is keeping MeshNet due to outcry from their users :)
01.10.2025 15:59 β π 2 π 0 π¬ 0 π 0
I am gonna try to hit yβall with ancient history on a daily basis.
Know that ancient aliens shit? Humans own those off-world fucks. Djoserβs Stepped Pyramid used hydraulics to shit 80 ton blocks out the top like a volcano 4,650 years agoβ¦ hydraulics still exists.
journals.plos.org/plosone/arti...
Does anyone know of an alternative to @nordvpn.bsky.social Meshnet? I *love* this product and must find someone else by November 1st... five minute VPN ftw!
cc @decius.bsky.social you knows the security, right?
Transform traditional study materials into interactive games with NotebookLM and CrosswordLabs. Parul Pandey's new article dives into how to engage students using technology to make lessons more enjoyable and memorable.
16.09.2025 21:19 β π 1 π 1 π¬ 0 π 0
The Rise of Semantic Entity Resolution is on Towards Data Science this morningβ¦!
> semantic entity resolution for knowledge graphs uses language models to automate the most painful part of building knowledge graphs from text: deduplicating records.
towardsdatascience.com/the-rise-of-...
This is really funny⦠arbitrary bitcoin KYC is far worse than fiat banking. Make one questionable purchase ever in your life⦠account DENIED. No appeal. Regulation of finance does not suck. Censorship for LIFE.
25.07.2025 15:53 β π 0 π 0 π¬ 0 π 0from gremllm import Gremllm # Be sure to tell your gremllm what sort of thing it is counter = Gremllm('counter') counter.value = 5 counter.increment() print(counter.value) # 6? print(counter.to_roman_numerals()) # VI?
The is diabolical... a Python object that hallucinates method implementations on demand any time you call them, using my LLM Python library github.com/awwaiid/grem...
04.07.2025 17:49 β π 175 π 27 π¬ 9 π 8In that same period Google and Hadoop birthed big data, which formed the basis for the current AI trend. There were huge developments like MaReduce.
04.06.2025 08:00 β π 1 π 0 π¬ 0 π 0Well, LLMs are better at teaching math and code than any other methodβ¦ if you donβt get it, just ask a lot of questions to an LLM with grounding so you can verify on the source.
04.06.2025 07:58 β π 1 π 0 π¬ 0 π 0Real utility fromβ¦ NFTs?
04.06.2025 07:55 β π 2 π 0 π¬ 0 π 0Okay, domains is a reasonable use case. It is the first one with real utility I have seen. I donβt think removing fungibility from media is a good thing.
03.06.2025 21:25 β π 1 π 0 π¬ 0 π 0Maybe I missed itβ¦ what purpose do NFTs serve?
03.06.2025 19:02 β π 0 π 0 π¬ 1 π 0LLMs are generative AI, in the field of artificial intelligence, in the field of computer science. They are rapidly transforming our world. NFTs did what for society? So far only cryptocurrency has impactful utility.
03.06.2025 17:21 β π 0 π 0 π¬ 1 π 0
Check out what productive settings for a Claude Code Python project looks like⦠CLAUDE.md, commands and allowed-tools. This setup makes me 5-10x as productive as before AI.
Feedback appreciated!
gist.github.com/rjurney/4d6c...
It upsets me honestly, because I know theyβre getting laid off while early adopters of AI coding will get ahead. It is a _skill_ to get Claude Code to work for you on your project. AI still needs a human, albeit at a higher level.
Hereβs what I meanβ¦ this took time:
gist.github.com/rjurney/4d6c...
For my next trick, Iβll short TSLA for the sixth time in a few months. Made a bunch on four, lost a little on the fifth :)
03.06.2025 02:34 β π 3 π 0 π¬ 1 π 0I will admit that I do all features first as CLI features as a PM strategy enabled by agent coding andβ¦ it never gets my CLI instructions wrong, so I just glance at them. It has never made a mistake or done something unexpected in fifty commands.
03.06.2025 02:33 β π 0 π 0 π¬ 0 π 0Itβs a definite risk, and an emergent property already if you donβt refactor, so some productivity must be lost on making it readable.
03.06.2025 02:31 β π 1 π 0 π¬ 0 π 0Yes we do, youβre still responsible for the code. Read and understand every line. Interrupt the agent. Give it feedback. Constantly.
03.06.2025 01:45 β π 1 π 0 π¬ 1 π 0This is what bad AI generated code is like, actually, and itβs shit I reject from PRs. You have to tell it to get that shit out of here, build a simpler interface and update your project config to adjust the behavior. Itβs all a software engineering skill.
03.06.2025 01:45 β π 0 π 0 π¬ 1 π 0Okay, good. Because now itβs 30% at Microsoft.
03.06.2025 01:42 β π 0 π 0 π¬ 0 π 0Itβs amazing. I want to help you, but you think the thing putting you out of work is an NFT.
03.06.2025 01:30 β π 0 π 0 π¬ 1 π 0More than 30% at google. And rapidly growing. Both those are top software orgs. AI needs you to operate it, if you donβt learn how youβre a lamplighter.
03.06.2025 01:25 β π 0 π 0 π¬ 0 π 0How much code do you think LLMs are writing at this point, percentage wise? 20% at Microsoft, and thatβs LOW. But itβs like NFTs? Iβm talking to someone getting laid off in 2026, maybe even 2025, for your attitude re: LLMs.
03.06.2025 01:22 β π 0 π 0 π¬ 1 π 0No, this has happened. Textbook rental companies died. Now stack overflow is dead.
03.06.2025 01:15 β π 1 π 0 π¬ 1 π 0Wait, what? Youβre just as responsible for what you commit with agents soβ¦ how is there little incentive to ask? Precise definitions are in fact now the entire field of software engineering.
03.06.2025 01:11 β π 1 π 0 π¬ 1 π 0