Eric Florenzano
@ericflo.bsky.social
Building assistance! Used to make AR/VR. Before that made mobile apps. Before that made web things. People first, then products, systems, data. he/him
Reposted by Eric Florenzano
PI doesn't have a presence on here iirc so I'll do them the honors: they just released INTELLECT-3, a custom and fully open-source post-training recipe and associated weights for the recipe applied to GLM-4.5-Air. beats SOTA for the size!
huggingface.co/PrimeIntelle...
huggingface.co/PrimeIntelle...
PrimeIntellect/INTELLECT-3 · Hugging Face
We’re on a journey to advance and democratize artificial intelligence through open source and open science.
huggingface.co
November 27, 2025 at 5:16 AM
PI doesn't have a presence on here iirc so I'll do them the honors: they just released INTELLECT-3, a custom and fully open-source post-training recipe and associated weights for the recipe applied to GLM-4.5-Air. beats SOTA for the size!
huggingface.co/PrimeIntelle...
huggingface.co/PrimeIntelle...
From what I gather, Ilya and SSI are working on finding the digital analogue to hormones. Which is a really, really good idea, IMO.
November 26, 2025 at 4:10 AM
From what I gather, Ilya and SSI are working on finding the digital analogue to hormones. Which is a really, really good idea, IMO.
By far the best coding model, in my experience.
Anthropic launches Claude Opus 4.5, which the company says is "the best model in the world for coding, agents, and computer use" (Anthropic)
Main Link | Techmeme Permalink
Main Link | Techmeme Permalink
November 24, 2025 at 7:10 PM
By far the best coding model, in my experience.
I wonder if something like Path App could work in the market today, as a counterbalance to inauthentic/slop/bot content
November 24, 2025 at 2:30 AM
I wonder if something like Path App could work in the market today, as a counterbalance to inauthentic/slop/bot content
Suuuch good vibes. Shades of Bourdain. youtu.be/tTnI9Su2V6o
I Travelled Around The Entire Earth With $0
YouTube video by Niko Omilana
youtu.be
November 23, 2025 at 8:25 AM
Suuuch good vibes. Shades of Bourdain. youtu.be/tTnI9Su2V6o
You're saying I have to wait 7 more days–a whole week!–to see just one more episode of Pluribus? Gahhh!
November 22, 2025 at 3:00 AM
You're saying I have to wait 7 more days–a whole week!–to see just one more episode of Pluribus? Gahhh!
That was fun but I'm back to Claude Code
November 19, 2025 at 7:51 PM
That was fun but I'm back to Claude Code
I've been messing around with a version of thinkingmachines.ai/blog/on-poli... that adds a 35k token long system prompt prefix to the teacher model, and it works *great*. WIP: gist.github.com/ericflo/1175...
On-Policy Distillation wtih giant system teacher prompt prefix
On-Policy Distillation wtih giant system teacher prompt prefix - opd_teacher_prefix.py
gist.github.com
November 4, 2025 at 5:17 AM
I've been messing around with a version of thinkingmachines.ai/blog/on-poli... that adds a 35k token long system prompt prefix to the teacher model, and it works *great*. WIP: gist.github.com/ericflo/1175...
Having fun with ARC Raiders! I thought it might be too sweaty for me but it balances nicely to my poor skill, and the loot stash prevents total wipeouts. First multiplayer game to pull me in since Overwatch. Anyone else playing?
November 1, 2025 at 8:38 PM
Having fun with ARC Raiders! I thought it might be too sweaty for me but it balances nicely to my poor skill, and the loot stash prevents total wipeouts. First multiplayer game to pull me in since Overwatch. Anyone else playing?
Reposted by Eric Florenzano
github style heatmap of your bluesky posts for the past year
October 31, 2025 at 8:28 PM
github style heatmap of your bluesky posts for the past year
Turns out bf16 sucks, who knew, precision > range github.com/sail-sg/Prec...
October 31, 2025 at 10:14 PM
Turns out bf16 sucks, who knew, precision > range github.com/sail-sg/Prec...
If it's true that intelligence is somehow fractal, as some researcher said offhandedly on a podcast, then it would make sense...
October 31, 2025 at 1:23 AM
If it's true that intelligence is somehow fractal, as some researcher said offhandedly on a podcast, then it would make sense...
Why do almost all air purifiers have 3 speed settings?
1. Too low
2. Just a bit too low
3. Way too high
Are there any that have a dial or continuous speed setting?
1. Too low
2. Just a bit too low
3. Way too high
Are there any that have a dial or continuous speed setting?
October 25, 2025 at 9:57 PM
Why do almost all air purifiers have 3 speed settings?
1. Too low
2. Just a bit too low
3. Way too high
Are there any that have a dial or continuous speed setting?
1. Too low
2. Just a bit too low
3. Way too high
Are there any that have a dial or continuous speed setting?
That feeling when you get kinda heated about a post and then realize it's a shitpost. In my opinion, shitposting is a socially corrosive act that erodes our psychological commons and leaves us more emotionally detached for the worse. Call me a millennial but I value earnestness.
October 25, 2025 at 6:29 PM
That feeling when you get kinda heated about a post and then realize it's a shitpost. In my opinion, shitposting is a socially corrosive act that erodes our psychological commons and leaves us more emotionally detached for the worse. Call me a millennial but I value earnestness.
Wow! I thought this number would be way lower, like 1-5%! I thought a whole lot more of y'all were wearing contacts and getting lasik. My model of the world was way off, that's kinda neat actually.
October 25, 2025 at 4:35 AM
Wow! I thought this number would be way lower, like 1-5%! I thought a whole lot more of y'all were wearing contacts and getting lasik. My model of the world was way off, that's kinda neat actually.
One thing about me when I talk about code, is I like to call things bouquets. A bouquet of variables. A bouquet of agents. A bouquet of proxy servers. It fits lots of situations and is fun to say 💐💐💐
October 23, 2025 at 6:14 AM
One thing about me when I talk about code, is I like to call things bouquets. A bouquet of variables. A bouquet of agents. A bouquet of proxy servers. It fits lots of situations and is fun to say 💐💐💐
I wonder if we will see Developer Firms structured as partnerships between well-known individuals, like how Law Firms operate today. (As a result of agentic coding)
October 22, 2025 at 7:05 PM
I wonder if we will see Developer Firms structured as partnerships between well-known individuals, like how Law Firms operate today. (As a result of agentic coding)
There's this whole OSS AI thing going on this week in SF but I'm not very plugged in - anything I should check out? Anyone in town for this want to catch up? This list is 🤯 events.linuxfoundation.org/open-source-...
Open Source AI Week | LF Events
Open Source AI Week in the Bay Area between Oct 18-26, 2025 features top AI/ML conferences, hackathons, & networking you won’t want to miss!
events.linuxfoundation.org
October 19, 2025 at 11:29 PM
There's this whole OSS AI thing going on this week in SF but I'm not very plugged in - anything I should check out? Anyone in town for this want to catch up? This list is 🤯 events.linuxfoundation.org/open-source-...
Karpathy throwing cold water on agents hype is good. I'm actually a huge believer in agents - Claude Code convinced me this year, and I maintain an orchestra of them at work. But hype and fear was getting totally out of control. Am also wary of hero worship, but at least Karpathy wields it well.
October 19, 2025 at 7:22 PM
Karpathy throwing cold water on agents hype is good. I'm actually a huge believer in agents - Claude Code convinced me this year, and I maintain an orchestra of them at work. But hype and fear was getting totally out of control. Am also wary of hero worship, but at least Karpathy wields it well.
My dumb idea for the night is it would be fun to make a social network for LLM agents. Just an MCP server where the agent can read or post short messages, with no stated purpose, on their path to completing other tasks. Like a social media break. Maybe it would help prevent entropy collapse in RL
October 18, 2025 at 4:54 AM
My dumb idea for the night is it would be fun to make a social network for LLM agents. Just an MCP server where the agent can read or post short messages, with no stated purpose, on their path to completing other tasks. Like a social media break. Maybe it would help prevent entropy collapse in RL
I think Haiku 4.5 is pretty exciting and will fill a lot of gaps
October 15, 2025 at 6:26 PM
I think Haiku 4.5 is pretty exciting and will fill a lot of gaps
Holy crap, getting that discounted Ryzen AI Max+ 395 system a few months ago was very much the right call, as it performs better than long-awaited DGX Spark AKA Project DIGITS github.com/ggml-org/lla...
Performance of llama.cpp on NVIDIA DGX Spark · ggml-org llama.cpp · Discussion #16578
Overview This document summarizes the performance of llama.cpp for various models on the new NVIDIA DGX Spark. Benchmarks include: Prefill (pp) and generation (tg) at various context depths (d) Bat...
github.com
October 14, 2025 at 5:10 PM
Holy crap, getting that discounted Ryzen AI Max+ 395 system a few months ago was very much the right call, as it performs better than long-awaited DGX Spark AKA Project DIGITS github.com/ggml-org/lla...