back
user profile
padolsey
4,464karma·578submissions·June 29, 2011
about
padolsey.at.hn
I'm James. Living between Beijing and London. I like coding. Also plants. Stroke survivor & disability advocate. My dog's a whippet/iggy cross and is called Ducky. He's a beautiful lunatic.
* website: [j11y.io](https://j11y.io) * building: [nope](https://nope.net) * bsky: [@j11y.io](https://bsky.app/profile/j11y.io) * contact: https://tally.so/r/waYPvE * twitter: [@padolsey](https://x.com/padolsey) * book recommendations: [ablf.io](https://ablf.io) * me = founding eng @ [collective intelligence project](https://cip.org)
My work email is my first name at cip dot org.
---
---
My meet.hn token: meet.hn-10d164d4-bf7f-4431-898f-e02b34b836dc
recent activity (578 total)
comment
I agree; it has its part to play; I guess I just see it as such a miniscule one. True bad actors are going to use abliterated models. The main value I see in alignment of frontier LLMs is less bias an…
comment
> Even if it’s not a perfect solution, it help steer the problem in the right direction Yeh tbf I was a bit strong worded when I said "pointless". I agree that perfect is the enemy of goo…
comment
I now think of single-forward-pass single-model alignment as a kind of false narrative of progress. The supposed implications of 'bad' completions is that the model will do 'bad things&…
comment
This study just seems a forced ranking with arbitrary params? Like, I could assemble different rules/multipliers and note some other cooperation variance amongst n models. The behaviours observed…
comment
> communicating complex ideas in conversation is hard and lossy True but.. > instead of building the website, the model would generate an interface for you to build it, where every user input to…
comment
>exceptionally smart at making predictions Is anyone though? Genuine question. I don't have much faith in predictions anymore.
comment
Was it just me who thought that this was _already_ how LLMs worked? I'd always assumed they were -- so to speak -- swimming in their own embeddings space before coming out on the other side with …
comment
I imagine this is a much harder problem than meets the eye. Even for my own travel, there are like a dozen things I'm trying to optimize for. Time, money, seat, travel to/from airport (traff…
comment
So basically this just adds random characters to input prompts to break jailbreaking attempts? IMHO If you can't make a single-inference solution, you may as well just run a couple of output filt…
comment
I was thinking that. And really chuffed to see things like $(function(){
$(".rollovers a").hover(function(){
$(this).children("span").fadeOut();
}, function…
comment
> Programmatically assemble prompts for LLMs using JavaScript.
> $`Analyze ${env.files} and report errors. Use gitmojis.`
This is kinda misleading and confusing as a lead. I could lite…
comment
The fundamental flaw people make is assuming that LLMs (i.e. a single inference) are a lone solution when in-fact they're just part of a larger solution. If you pool together agents in a way wher…
comment
Umm it does have support for open/free/self-hosted models through either openrouter or by changing the oai endpoint (as long as you've got an openai compatible endpoint which is usually…
comment
I was in in the `concat->copy->[Claude/OAI]->paste` workflow until a few weeks ago. Cursor is a revelation. Nowadays I only very rarely pump things wholesale into Claude[dot]ai when I&#x…
comment
Cursor is a fully fledged fork of VSCode so IMHO it's in a different ballpark to Aider/Claude-Engineer/etc. Its LLM assistance is baked in to the IDE. Feels really comfortable. I switch…
comment
Cursor is incredible. You can use whatever model you like. Give it your openAI key if you want o1-preview. Using it with Claude Sonnet is usually enough though. I use it everyday and it makes it possi…
comment
I haven’t tried, and tbh I’d be very scared of messing with the complete cocktail of meds (~7) I’m on as it is. Risky! I’d rather maintain a knowable stability even if it’s non optimal.
comment
This is such an interesting thing to read about!! Thank you for posting it! I have epilepsy following hemmorhaging to the parietal area affecting my motor movement, planning, and sensation. Much like …
comment
It's BrailleInstitute, an org catering to those with visual impairments. Understandably, their site is accommodating to their core audience.
comment
Niiice! I really like it. The spatial approach is cool, though labelling/annotations/axes would help. I share the frustraion with getting book covers for my project ablf.io. Amazon used to m…
comment
> gives me the information I need. I mean, I'd like at least a brief blurb about their entire premise of safety. Maybe a definition or indication of a public consultation or... something.. oth…
comment
Technically it's acting on behalf of a proactive user in Chrome so IMHO is non-"robotic". But heh tbf this was also the excuse of Perplexity where they argued they are a legitimate non-…
comment
Yeh sure - what did you have in mind?
comment
I really love this kind of thing. I made one called 'redoku' a long long time ago. It generates random challenges. Try it here: https://padolsey.github.io/redoku/ …
comment
I've found Claude to be way too congratulatory and apologetic. I think they've observed this too and have tried to counter it by placing instructions like that in the system prompt. I think …
comment
> If we're talking psychoanlytically of where wanting comes from, and call it a desire to fill a void of how incoherent you actually are, then an LLM doesn't go through that process. Iron…