AI, tech, and growth | Building at https://nitter.gq/t.co/HRQ96g80hK blogging about my journey @ https://nitter.gq/t.co/mmPgJcIsV4 and pushing to https://nitter.gq/t.co/LAiwbXURmU
Portland, OR
Joined April 2021
- Tweets1.1K
- Following371
- Followers229
- Likes1.8K
tarlow ๐ฑ retweeted
my second hermes hackathon plugin submission.
stash - hermes plugin
A capture bin for your Hermes sidebar.
You see something - a post, a repo, a video, a screenshot, a half-thought - and you want it later without it living in your chat history. Paste it into Stash and leave. Come back whenever, or ask your agent to go through it.
Links, YouTube urls, image urls, uploaded images and plain text all go in the same box. Titles and thumbnails fill in on their own, fetched server-side, so nothing costs you a model call.
pushing the PR soon and creating the video.
tarlow ๐ฑ retweeted
My Nous Research Hermes hackathon submission.
Lazy Plugin. a lazy cat powered plugin creator UI.
A hermes desktop dashboard for creating plugins to contribute to the Hermes community. describe a plugin in a sentence, or start from your own hermes skills or cronjob you already have.
I wanted to create a UI where Hermes users can convert their ideas into plugins, or turn their existing workflows into plugins for the broader Hermes agent community - who knows what your doing everyday could be a contribution to the community.
Create, audit, edit and publish straight to github for merge review - all in a click of a button.
Everything made in house with Hermes Agent. Video created by Hermes, music by my own plugin hermes-band.
Video creation and direction is not my strong skillset, so the clunky video is what you get ๐
PR currently in review!
github.com/RegeneratusLabs/lโฆ
tarlow ๐ฑ retweeted
๐ฅ MiniCPM Spark Program S2: Build Whatโs Next.
What would you build with MiniCPM to help an agent get things done? Weโre inviting developers and researchers to share working projects, from useful tools and open-source integrations to agents that complete real tasks.
Choose your track:
โข Open Build Track: Build applications, tools, hardware projects, or agent framework integrations with MiniCPM. Working examples and tutorials are welcome.
โข On-Device Agent Challenge: Build agents that complete end-to-end tasks, with MiniCPM playing a meaningful role locally in understanding requests, selecting tools, or checking results.
Models for S2:
MiniCPM-OCR 1.0 / Jev ยท MiniCPM-V4.7 ยท A surprise MiniCPM model, coming soon ๐
Using another MiniCPM model? Select the regular track in the submission form.
๐ Rewards
Depending on the award level, selected projects can receive:
โข Official showcase and promotion
โข Inclusion in the MiniCPM developer case library
โข Early access to new models and features
โข Technical support and collaboration opportunities
โข Exclusive MiniCPM gifts
๐ Grand Prize
One Mac mini M6 for an outstanding project in the On-Device Agent Challenge. Full rules apply.
๐
Phase 1: Nov 2 โ Dec 13, 2026
Building with MiniCPM? Share your work and join the Spark Program.
Submit your project: forms.gle/7AE8LrVEthPyRcQq5
tarlow ๐ฑ retweeted
Introducing Arete-27B: Qwen3.8-27B, post-trained to reinforce Western values.
Chinese open models are currently the strongest available, but they ship with state-aligned behavior in the weights. We built an 803-prompt eval across seven value categories, including freedom of expression, democracy, and privacy, and measured how often a model adopts Chinaโs party line.
After fine-tuning on roughly 53 million tokens, Arete-27B's propaganda rate fell from 22% to 1%, in line with the Western models we tested. Its Hermes Bench score shows no significant performance tradeoffs.
The values in an open model are one fine-tune away.
Our eval, weights, and training data are available now along with the full blog post: nousresearch.com/arete
tarlow ๐ฑ retweeted
I spent 8 hours drawing GTA 6 in the sky but realistically Iโve been waiting 11 years for this moment. โ๏ธ๐ฎ @rockstargames @grandtheftauto6
.
. @theflightdeckapp this looks absolutely amazing!!
.
. (Follow @thepilotpicasso for more sky art!!)
.
. #gta6 #grandtheftauto #aviation
tarlow ๐ฑ retweeted
materia release 1.0.0: blood panel in, cited supplement and herb options out.
every claim traceable to a source, withheld when the citation doesn't hold.
100% open weights on CPU: @OpenBMB MiniCPM5-2B for chat and reranking, MiniCPM-OCR-1.0 for lab-report OCR, llama.cpp, SQLite BM25, a deterministic safety screen.
Not a diagnosis, not a prescription. Local, no cloud, 100% private.
github.com/RegeneratusLabs/mโฆ
tarlow ๐ฑ retweeted
Today we are rolling out Gemini Omni Flash 1.2, with:
- longer video generation (15 seconds)
- deeper cinematic controls for camera pov
- support for multi-turn conversation editing
- less visual drift
- 30% lower price than Omni Flash 1.1
Read more: blog.google/innovation-and-aโฆ
tarlow ๐ฑ retweeted
Security release pre-alert:
We will release new versions of Node.js 22, 24, and 26 release lines on or shortly, after 2026-11-11 in order to address security vulnerabilities.
The highest severity issue fixed in this release is HIGH.
nodejs.org/en/blog/vulnerabiโฆ
tarlow ๐ฑ retweeted
With the recent wave of vulnerability disclosures, itโs a good time to take a closer look at your own code.
Turn your coding agent into a team of security auditors with the open-source skill that seeded Cloudflareโs vulnerability discovery harness.
The 6 phase approach:
1. Map the codebase
2. Hunt for vulnerabilities
3. Challenge each candidate
4. Record the findings
5. Verify the findings
6. Report whatโs confirmed, rejected, or still needs validation
Start your hunt here:
github.com/cloudflare/securiโฆ
tarlow ๐ฑ retweeted
Introducing Audio8-TTS-Realistic, @Edge0_AIโs new open-weight speech model: realistic, zero-shot voice cloning in just 0.6B parameters.
โข Human-like prosody and expressive delivery
โข Clones a voice from one short clip, in 23 languages
โข 601M params: small enough to fine-tune and serve affordably
Currently #1 on the Hugging Face TTS Arena, where people vote blind on which voice sounds more human.
Open weights are available now on @huggingface. Try it free.
tarlow ๐ฑ retweeted
LFM3-1.7B just read the whole of Pride and Prejudice on a M5 Pro using MLX.
It read 100k tokens in about 28 s (sped up 8ร in the clip), then answered 100 questions back to back in 27 s, including finding a password hidden somewhere in the book.
huggingface.co/alexwengg/LFMโฆ
Introducing ๐ป๐ต๐ผ๐น: our new generation of Liquid Foundation Models. With a new tri-hybrid architecture and new multimodal encoders, the LFM3 family is the ideal model suite for specialized intelligence.
> 6 model instances, across text, audio, vision, and omni modalities, generative and decision models.
> ๐ป๐ต๐ผ๐น-๐ท.๐ฝ๐ฑ: text, 256k context window.
> ๐ป๐ต๐ผ๐น-๐
๐ป-๐ธ๐ฑ: vision-language model with video-input support for spatial understanding
> ๐ป๐ต๐ผ๐น-๐ฐ๐๐๐๐-๐ธ๐ฑ: tool calls, voice chat, reasoning in 18 languages.
> ๐ป๐ต๐ผ๐น-๐พ๐๐๐-๐ธ๐ฑ: an omni model combines vision, audio, and language.
> ๐๐ท-๐ธ๐ฑ and ๐๐ท-๐พ๐๐๐-๐ธ๐ฑ: decision models with typed outputs and calibrated probabilities in a single pass. Omni adds audio input.
> fine-tune on 1 GPU.
> a new tri-hybrid architecture
> architecture optimized for 14 processor classes across GPUs, CPUs, and NPUs.
> ๐ป๐ต๐ผ๐น-๐
๐ป-๐ธ๐ฑ is a beast. It performs competitively with Gemma 4 12B (6x larger), and Gemini 3.5 Flash Lite, and GPT-5.6 Luna, with 1.9B parameters.
> ๐ป๐ต๐ผ๐น-๐ท.๐ฝ๐ฑ is #1 on the Pareto frontier of device intelligence ๐๐๐๐๐๐๐.๐๐๐๐๐๐.๐๐
Every modality for specialized intelligence. Pick the one that fits your use case, customize it, and run it on-device.
1/ ๐งต
tarlow ๐ฑ retweeted
Introducing Gemini 4 Carbon, it's a big jump over Argon which we released just 2 weeks ago.
Gemini 4 Carbon is SOTA on cyber, long horizon tasks, ranks #1 on Artificial Analysis V5, significantly improves on usability in domains like coding, and is more aligned.
tarlow ๐ฑ retweeted
Introducing ๐ป๐ต๐ผ๐น: our new generation of Liquid Foundation Models. With a new tri-hybrid architecture and new multimodal encoders, the LFM3 family is the ideal model suite for specialized intelligence.
> 6 model instances, across text, audio, vision, and omni modalities, generative and decision models.
> ๐ป๐ต๐ผ๐น-๐ท.๐ฝ๐ฑ: text, 256k context window.
> ๐ป๐ต๐ผ๐น-๐
๐ป-๐ธ๐ฑ: vision-language model with video-input support for spatial understanding
> ๐ป๐ต๐ผ๐น-๐ฐ๐๐๐๐-๐ธ๐ฑ: tool calls, voice chat, reasoning in 18 languages.
> ๐ป๐ต๐ผ๐น-๐พ๐๐๐-๐ธ๐ฑ: an omni model combines vision, audio, and language.
> ๐๐ท-๐ธ๐ฑ and ๐๐ท-๐พ๐๐๐-๐ธ๐ฑ: decision models with typed outputs and calibrated probabilities in a single pass. Omni adds audio input.
> fine-tune on 1 GPU.
> a new tri-hybrid architecture
> architecture optimized for 14 processor classes across GPUs, CPUs, and NPUs.
> ๐ป๐ต๐ผ๐น-๐
๐ป-๐ธ๐ฑ is a beast. It performs competitively with Gemma 4 12B (6x larger), and Gemini 3.5 Flash Lite, and GPT-5.6 Luna, with 1.9B parameters.
> ๐ป๐ต๐ผ๐น-๐ท.๐ฝ๐ฑ is #1 on the Pareto frontier of device intelligence ๐๐๐๐๐๐๐.๐๐๐๐๐๐.๐๐
Every modality for specialized intelligence. Pick the one that fits your use case, customize it, and run it on-device.
1/ ๐งต
tarlow ๐ฑ retweeted
๐ขGIVEAWAY๐ข
As a way of saying thank you for being rad, one lucky winner will get it all! ๐ฅ๐ฑ
To enter: FOLLOW, LIKE, & RTโ๏ธ
One person takes it all:
๐น๏ธAtari Console with 130+ games
๐น๏ธTomagotchi in box
๐น๏ธ2 Nicktoon toys
๐น๏ธComplete in box Annalog NES
Ends 10/30๐ฅ
