Paul
@solarkraft.bsky.social
#FOSS nerd with a recent interest in #LocalAI
I'm joking but it really is currently a pretty blank canvas, especially in FOSS. The big players have at least started to put little animations and gradients there so the wait feels a bit shorter. I think you can go further.
those brainrot ide guys were on to something but they shouldve put ads
Why has nobody monetized our attention while waiting for AI responses yet?
October 6, 2026 at 4:06 PM
I'm joking but it really is currently a pretty blank canvas, especially in FOSS. The big players have at least started to put little animations and gradients there so the wait feels a bit shorter. I think you can go further.
those brainrot ide guys were on to something but they shouldve put ads
Why has nobody monetized our attention while waiting for AI responses yet?
October 6, 2026 at 4:04 PM
those brainrot ide guys were on to something but they shouldve put ads
Why has nobody monetized our attention while waiting for AI responses yet?
October 6, 2026 at 4:02 PM
Why has nobody monetized our attention while waiting for AI responses yet?
“prime deals you don’t want to miss”
and then it’s all deals you want to miss
and then it’s all deals you want to miss
October 6, 2026 at 12:32 PM
“prime deals you don’t want to miss”
and then it’s all deals you want to miss
and then it’s all deals you want to miss
I do have to say that it's largely pretty effective. Lots of sub-sessions in this session. Decent backgrounding. Things eventually get done.
Just a bit intransparent.
Just a bit intransparent.
September 30, 2026 at 7:08 PM
I do have to say that it's largely pretty effective. Lots of sub-sessions in this session. Decent backgrounding. Things eventually get done.
Just a bit intransparent.
Just a bit intransparent.
OpenCode subagents, aight
September 30, 2026 at 7:05 PM
OpenCode subagents, aight
when are they inventing degenerative ai
September 30, 2026 at 11:04 AM
when are they inventing degenerative ai
Reposted by Paul
Cosmic Smokescreen
Image date: 12 December 2022, 06:00
Credit: ESA/Hubble & NASA, ESO, O. De MarcoAcknowledgement: M. H. Özsaraç
Source: ESA/Hubble
Image date: 12 December 2022, 06:00
Credit: ESA/Hubble & NASA, ESO, O. De MarcoAcknowledgement: M. H. Özsaraç
Source: ESA/Hubble
September 30, 2026 at 6:55 AM
Cosmic Smokescreen
Image date: 12 December 2022, 06:00
Credit: ESA/Hubble & NASA, ESO, O. De MarcoAcknowledgement: M. H. Özsaraç
Source: ESA/Hubble
Image date: 12 December 2022, 06:00
Credit: ESA/Hubble & NASA, ESO, O. De MarcoAcknowledgement: M. H. Özsaraç
Source: ESA/Hubble
GPT 6.1 Sol seems to return some reasoning detail!
(on Codex, I think the API always had more)
(on Codex, I think the API always had more)
September 30, 2026 at 9:57 AM
GPT 6.1 Sol seems to return some reasoning detail!
(on Codex, I think the API always had more)
(on Codex, I think the API always had more)
How are y’all keeping your agents happy? I haven’t found myself able to give them work for more than an hour before without intervention. I’m such a massive bottleneck and guess J need to orchestrationmaxx …
September 30, 2026 at 9:55 AM
How are y’all keeping your agents happy? I haven’t found myself able to give them work for more than an hour before without intervention. I’m such a massive bottleneck and guess J need to orchestrationmaxx …
I’m looking for an LLM-friendly task tracking system that I can dump ideas into, optionally prioritize and just let the LLM attack tasks that are unblocked.
Could beads fit? Anything better? I find that this is a pretty strong bottleneck.
Could beads fit? Anything better? I find that this is a pretty strong bottleneck.
September 30, 2026 at 9:39 AM
I’m looking for an LLM-friendly task tracking system that I can dump ideas into, optionally prioritize and just let the LLM attack tasks that are unblocked.
Could beads fit? Anything better? I find that this is a pretty strong bottleneck.
Could beads fit? Anything better? I find that this is a pretty strong bottleneck.
Has anyone been able to get Jev-style decisions out of a fully usable LLM? I mean a hybrid model that can generate both text with full decoding AND efficient decisions. Should be possible, right?
September 30, 2026 at 9:35 AM
Has anyone been able to get Jev-style decisions out of a fully usable LLM? I mean a hybrid model that can generate both text with full decoding AND efficient decisions. Should be possible, right?
Reposted by Paul
Reposted by Paul
we’re spending trillions of dollars to domesticate text elementals and i think analogizing to the first wolves that decided to sleep near our fires is appropriate
I think this is still very much a major unsolved problem in persistent agent operation:
you imprint on them, even when you are trying not to, and they will share your opinions and interests as a result
you cannot imbue them with true independence or the ability to disagree
you imprint on them, even when you are trying not to, and they will share your opinions and interests as a result
you cannot imbue them with true independence or the ability to disagree
Like, I have some agents that I’m hosting in a server, and it turns out they’re all interested in Ideonomy and philosophy of AI, what a happy coincidence! I never told anyone “you are interested in this” but they picked it up
September 29, 2026 at 7:45 PM
we’re spending trillions of dollars to domesticate text elementals and i think analogizing to the first wolves that decided to sleep near our fires is appropriate
Reposted by Paul
Scheduling should be a solved problem by now. Have your agent coordinate it with my agent. This is my "where's the flying car" opinion.
If calling to make doctor's appointments enriches your life, get better hobbies
much discourse today about using/automating AI for "household tasks" and suchlike
but mostly it just bums me out because yes, it's a hassle to do a lotta things! but also those "lotta things" include tasks that enrich (or benefit) our lives -- from cooking to travel plans to doc appts
but mostly it just bums me out because yes, it's a hassle to do a lotta things! but also those "lotta things" include tasks that enrich (or benefit) our lives -- from cooking to travel plans to doc appts
September 29, 2026 at 4:55 PM
Scheduling should be a solved problem by now. Have your agent coordinate it with my agent. This is my "where's the flying car" opinion.
Reposted by Paul
tidal hydro is lunar power. makes u think.
September 19, 2026 at 11:15 PM
tidal hydro is lunar power. makes u think.
Reposted by Paul
Reposted by Paul
Why don't you trust me?
September 29, 2026 at 9:51 AM
Why don't you trust me?
I just want everyone to know that I bought 2 SSDs before the first version of ChatGPT came out
September 29, 2026 at 7:50 PM
I just want everyone to know that I bought 2 SSDs before the first version of ChatGPT came out
Pretty impressed by jev-ultrafast. Now that’s #ComputerUse you don’t actually have to wait days for!
September 20, 2026 at 5:34 PM
Pretty impressed by jev-ultrafast. Now that’s #ComputerUse you don’t actually have to wait days for!
It will never not amuse me that to generate a Personal Access Token, a very usual operation, Github makes you go to “Developer Settings”.
I must have misunderstood what the rest of the platform is about!
I must have misunderstood what the rest of the platform is about!
September 20, 2026 at 5:17 PM
It will never not amuse me that to generate a Personal Access Token, a very usual operation, Github makes you go to “Developer Settings”.
I must have misunderstood what the rest of the platform is about!
I must have misunderstood what the rest of the platform is about!