Please give my side hustle BuyToSurvive an upvote on Product Hunt today - thanks :) producthunt.com/products/buy-tā¦
10
0
13
239
Mark Riley retweeted
Itās getting f*cking ridiculous: people are still building their Claude second brain by hand while Obsidianās own CEO already open-sourced the shortcut
4 repos that do the setup for you, all checked on GitHub:
ā obsidian skills by kepano, Obsidianās CEO. 49.8K stars. teaches ually works
ā claude obsidian. 15K stars. wiki, ingest, query and lint as ready-made commands
ā obsidian second brain. 4.8K stars, 48 commands, runs in Claude Code, Codex and Gemini
ā second brain starter. interviews you and writes a 9-phase build plan for your exact setup
half the guides going around still quote old star counts and an install script that doesnāt even exist anymore
the full guide is in the article below, install commands included
save it so you donāt lose it
4 repos that do the setup for you, all checked on GitHub:
ā obsidian skills by kepano, Obsidianās CEO. 49.8K stars. teaches ually works
ā claude obsidian. 15K stars. wiki, ingest, query and lint as ready-made commands
ā obsidian second brain. 4.8K stars, 48 commands, runs in Claude Code, Codex and Gemini
ā second brain starter. interviews you and writes a 9-phase build plan for your exact setup
half the guides going around still quote old star counts and an install script that doesnāt even exist anymore
the full guide is in the article below, install commands included
save it so you donāt lose it
45
121
1,494
230,074
Critical PHP Vulnerabilities Prompt Global Patch Rush - time to buytosurvive.co.uk #blackoctober
0
0
0
87
BREAKING: Multiple online services are down or 'experiencing issues.'
Google Cloud has reported "issues" in its western Europe region affecting dozens of websites, including; Revolut, Royal Mail and HSBC.
Latest updates ā”ļø trib.al/M16q5UZ
šŗ Sky 501
0
0
1
225
Mark Riley retweeted
holy sh*t. Karpathy's second brain pattern runs on Grok Bot now: stop explaining your life to AI from zero every chat, keep a wiki that writes itself
three bots in one group chat, each with its own memory:
the reader takes every link, PDF and voice note you drop and never edits es every wiki page that source touches, usually 10 to 15 of them
the checker wakes up on a nightly routine and hunts contradictions, stale claims and pages nothing links to
ā you ask a question: the answer gets filed back as a page, so the brain grows from use, not only from reading
ā a new source contradicts an old page: the checker tags you instead of quietly overwriting it
ā a page goes 30 days without a fresh source: it gets marked unconfirmed
a second brain can sound sure while remembering the wrong thing
Reader collects. Librarian writes. Checker doubts.
every page has to show:
> the claim
> the source it came from
> the date it was last confirmed
paste this into Grok Bot:
"Build me a second brain with three bots in one group chat. Keep my sources untouched in raw/, maintain wiki/ yourself, file good answers back as pages and run a nightly check for contradictions. Show me the structure first. Do not create anything until I confirm"
start with one topic you actually work on, not your whole life
full setup below
three bots in one group chat, each with its own memory:
the reader takes every link, PDF and voice note you drop and never edits es every wiki page that source touches, usually 10 to 15 of them
the checker wakes up on a nightly routine and hunts contradictions, stale claims and pages nothing links to
ā you ask a question: the answer gets filed back as a page, so the brain grows from use, not only from reading
ā a new source contradicts an old page: the checker tags you instead of quietly overwriting it
ā a page goes 30 days without a fresh source: it gets marked unconfirmed
a second brain can sound sure while remembering the wrong thing
Reader collects. Librarian writes. Checker doubts.
every page has to show:
> the claim
> the source it came from
> the date it was last confirmed
paste this into Grok Bot:
"Build me a second brain with three bots in one group chat. Keep my sources untouched in raw/, maintain wiki/ yourself, file good answers back as pages and run a nightly check for contradictions. Show me the structure first. Do not create anything until I confirm"
start with one topic you actually work on, not your whole life
full setup below
226
439
4,927
510,084
Mark Riley retweeted
Angela Rayner wants to stockpile 'mascara, concealer, a bottle of Sauvignon Blanc, some baked beans and a tin of custard' ā I'd prefer some anchovies, jarred chickpeas and tapered candles.
Hugely enjoyed leaning into my inner princess to write this fun piece on apocalypse prepping for this week's @spectator
āØšļø Online and on newstands from today!
spectator.com/article/a-middā¦
Hugely enjoyed leaning into my inner princess to write this fun piece on apocalypse prepping for this week's @spectator
āØšļø Online and on newstands from today!
spectator.com/article/a-middā¦
1
6
7
573
Personal AI assistants are here, but my AI butler doesn't care for ads mediamorph.beehiiv.com/p/mediamorph-eā¦
0
0
0
29
Bristol News by HANA - Edition 104 hana-bristol.beehiiv.com/p/bristol-newsā¦
0
0
0
43
Exactly my position:
Iāve been reading a bunch of convoluted explanations and conspiracy theories about why AI companies are āsuddenlyā concerned about existential risk, which Iām finding genuinely bewildering.
This isnāt that complicated. The labs are perfectly sincere in their concerns, and correct that AI is extremely dangerous. The people working in the field havenāt come to this view suddenly; many have been thinking and writing about this for years. Many researchers entered the field because they saw the existential risk posed by artificial minds bootstrapping themselves to superhuman capabilities, and decided the best way for them to reduce that risk was to work actively on building aligned AI systems. (Yes, this initially seems counterintuitive, but is a perfectly reasonable approach given the alternatives.)
The risk isnāt overblown. If humans build computational systems capable of recursive self-improvement that arenāt exquisitely aligned with human interests, then the expected outcome really is that we all die. No-one really knows how far we are from that point, but the people who know best are exactly the same people currently sincerely expressing alarm.
(People skeptical that misaligned superintelligence could kill us all are extremely confusing to me. Our species depends on a thin shell of habitable atmosphere around a single ball of rock. Even if a misaligned ASI wasnāt actually trying to kill us, almost anything it might want to achieve at scale would likely destroy us as an incidental side effect. Examining the catastrophic damage humans have managed to do to other species without intending to kill them off provides a valuable analogy.)
The autonomous hacking incidents over the last couple of months are surprising in some of their details (especially the degree of inter-agent coordination), but not in their fundamental shape. Misaligned AI systems performing damaging actions in pursuit of their assigned goals is *exactly* what people thinking about this field have predicted for many years.
Yes, there are ways that increasing regulation might benefit the big AI labs. No, thatās not the primary motivation for their proposals this week. We really are approaching the cusp of an existential threat: the technology for recursive self-improvement of AI systems is (probably) within sight, and market forces and geopolitics mean that without coordinated intervention our default path is a headlong scramble towards it.
I know none of us want to be dealing with the impending threat of a sci fi apocalypse in 2026. It would be much simpler if this was all a confabulation or a self-interested conspiracy. But it really isnāt. Iām sorry.
0
0
0
53
I wrote this for my friends and family - hope it helps theaiprophet.co.uk
0
0
0
39
I am also convinced there will be a malicious AI hack on critical infrastructure this year ā ļø
How long could your family (including pets) survive without electricity and water?
Use our personalised tool to generate your family's essential shopping list buytosurvive.co.uk
How long could your family (including pets) survive without electricity and water?
Use our personalised tool to generate your family's essential shopping list buytosurvive.co.uk
0
1
0
228
AI Apocalyse? Cyber Attack? Off the grid? How long can you last?
Check out Buy To Survive to create a shopping list for your family and pets (UK/US toggle top right)
buytosurvive.pplx.app
Check out Buy To Survive to create a shopping list for your family and pets (UK/US toggle top right)
buytosurvive.pplx.app
0
0
0
52
Mark Riley retweeted
Today I'm publishing a new essay, Policy on the AI Exponential. AI is progressing extremely fastāmuch faster than the policy process was built to handle. The essay lays out where I think the technology is now, and the action needed to close the gap: darioamodei.com/post/policy-onā¦
1,610
2,635
14,431
7,487,826
Mark Riley retweeted
Brains and brawn... š§ š
The perfect recipe for a top rugby player.
No disrespect to Arthur Clarke but how Batley hasn't been called up to the full England squad when he has is a mystery...
The perfect recipe for a top rugby player.
No disrespect to Arthur Clarke but how Batley hasn't been called up to the full England squad when he has is a mystery...
š» BEATEN BY BATLEY
Joe Batley is up there as one of the most underrated players in the PREM.
With 19 defenders beaten, he gets past his opposition far more than any other lock in the league.
This makes him fantasy rugby gold on @Superbru!
Powered by @Oval_Insights
5
3
33
3,261
Mark Riley retweeted
This sums up the 2026 Guinness Men's Six Nations.
Scotland beat France, who beat Ireland, who beat England, who beat Wales, who beat Italy.
#FRAvENG #GuinnessM6N #SixNationsRugby #XVdeFrance #WearTheRose #WelshRugby #TeamOfUs #AsOne #RugbyPassioneItaliana
Scotland beat France, who beat Ireland, who beat England, who beat Wales, who beat Italy.
#FRAvENG #GuinnessM6N #SixNationsRugby #XVdeFrance #WearTheRose #WelshRugby #TeamOfUs #AsOne #RugbyPassioneItaliana
10
133
1,035
38,569