All entries

Fieri Iussit https://x.com/emollick/status/1969993499157446943?s=20 My modest proposal for how to acknowledge AI work is to use the Latin phase 'Fieri Iussit,' which means 'commanded to be made,' a co

FSD v14.3.2 has been driving me all over LA tonight. This build is f-ing incredible, smooth as butter and it’s fascinating how well it can handle complex traffic scenarios, road closures and tight roa

FYI Claude Code is mostly a vibe-coded product (as they say, 100% written by Claude) It's the worst harness for Opus 4.6 among ANY harness on Terminal-Bench 2 I feel sorry for Claude Code I know they'

Gary Marcus reported receiving a high volume of phishing emails through X (formerly Twitter) direct messages, suggesting either widespread account compromises or a potential security vulnerability all

🚨GUYS QWEN3.6 27B/35B @unslothai MLX QUANTS @Brooooook_lyn cooked 🔥 Apple Silicon users, the exact models y’all have been asking for LANDED. Unsloth mixed-precision quants in native MLX format. >Fast.

HealthBench Professional, our new evaluation of clinician chat tasks, is now available on HuggingFace for easy access. Each example was written, reviewed, and adjudicated by three or more physicians.

Here is a very common problem when building complex agents. Long-horizon agents (in particular) fail in two ways: the decision-maker can't decompose well, or the skill library goes stale. This new res

Hermes Agent tip of the day: There are 4 ways to deal with the model while its running, - Message it, by default, it will interrupt the agent loop, stopping it and making it respond to your new messag

Sebastian Raschka has updated his LLM architecture gallery with higher resolution figures and improved summaries, including coverage of the DeepSeek V4 model architecture. This resource provides visua

How do you think the left redistributes wealth? Violence How do you think the left seizes the means of production? Violence How do you think they censor and surveil opponents? Violence What do you thi

Clem Delangue, co-founder of Hugging Face, shared a positive comment about the machine learning internship experience at Hugging Face, suggesting the internship program is engaging and enjoyable for p

I actually switched my personal Claude subscription to this (currently using Mimo v2) Nous Portal offers everything you need to build with Hermes Agent in one easy subscription: → 300+ models from eve

I am increasingly bullish on open source harnesses (like OpenCode) not because they will be better than SOTA closed harnesses, but because they will never pull shady stuff like what Claude Code and ot

I don’t think there will be any coding models 3-4 years from now. completely disagree. buying Cursor is a genius move by Elon. wouldn't be surprised if xAI had the best coding model 12-18 months from

Dylan Patel announced his availability to meet in person at Dark Matter Coffee in New York City on a specific date between 11:00 AM and 12:30 PM. The post included a Google Maps link to the coffee sho

If using a cloud based browser backend in Hermes Agent, it will now auto-detect if you want it to look at or use a locally hosted website and switch to local browser so it can access it. Hopefully thi

If you want to build proactive agents on real hardware, come build with us today. We’re co-hosting the Proactive Agent Build Day at @agihouse_org Ambient agents. persistent memory. accessibility. @Eve

François Chollet criticizes anonymous AI influencer accounts on social media, warning that following their content can lead to diminished critical thinking and poor judgment. The post cautions against

I cannot verify this specific quote or its authenticity without access to the actual content at the provided URL. The statement appears to be attributed to a U.S. President calling for peaceful resolu

In other words, you need the world models that LeCun, Schmidhuber, Fei Fei Li, and I have been advocating for all along. Sam Altman says today's models are still dumb because they barely understand yo

I can't verify the specific content of this post without accessing the URL, and the title appears to be commentary rather than a factual claim. Based on the framing, this likely discusses the relation

Indeed it will This is the federal income tax play all over again. It started in 1913 as a “class tax” on the rich, hitting less than 1% of the population with a 1% rate above $3,000. It expanded duri

Heather Knight / New York Times: Inside Andon Market, billed as the first retail boutique run by an AI agent; the Andon Labs experiment uses a Claude Sonnet 4.6-based agent to run the boutique — Andon

A discussion evaluating the value proposition of a Beelink Mini S compact computer with Intel N95 processor and 8GB RAM at a €95-105 price point for running a budget 24/7 home server, likely including

Swyx shared a video of himself singing 'Sign of the Times' by Harry Styles while wearing a Base Ten shirt, which he found entertaining enough to watch repeatedly. The post expresses enthusiasm about t

'Left wing violence is the problem in America. Charlie Kirk was murde*ed by a left wing radical. President was almost kil*ed. We have a real crisis where there are far too many left wing people who do

Automated lint: 44 errors, 10 warnings, 3 info

“Loves tearing down overhyped AI claims, but his critiques always hit the nail on the head”. They get it, in China. 全球AI圈最有影响力的15个人，你一个都不认识就别说自己懂AI了 说真的，AI这个行业吧，信息差就是钱差。 你每天刷那些二手资讯、等媒体翻译，黄花菜都凉了。真正的消息，

Mocking armchair critics who have probably never touched a gun, let alone faced a crazed demon, asking “Why not tase him / shoot him in the leg / talk to him?” or some similar nonsense. FACT: He was t

A quantized version of DeepSeek-V4-Flash has been released on Hugging Face by the MLX community in 2-bit format with dynamic quantization, making the model more efficient for inference on resource-con

AURA is a local-first image management application designed specifically for AI enthusiasts and users who collect large numbers of AI-generated images. It features integration with Civitai, automated

Sam Altman commented on a discussion about AI efficiency, noting that a particular capability compresses work that previously took approximately two weeks into a single day, indicating significant pro

Never let critical thinking get in the way of extremist fantasy stories. If you're on either side of this slider, congratulations, you may be a child in an adult costume body! Black and white thinking

NEW paper from Alibaba. A 30B MoE with only 3B active params matches Qwen3-235B on real tool-use workloads. AgenticQwen-30B-A3B: 50.2 average on TAU-2 + BFCL-V4 Multi-Turn. AgenticQwen-8B: 47.4. Both

Next up: Hermes Agents on Tuesday in Lisbon 🇵🇹 as we work to make our office the go-to space for AI builders in Portugal, then we have another major one this week. we will this time be joined by the t

No more updating needed for new model releases via Nous Portal and OpenRouter! Hermes will no longer have to be updated to receive model list curation updates for several providers, including Nous Por

No, the top score if you didn't account for action efficiency would be 100%, achievable with 20 lines of Python. All you need is to brute-force the state space. Please stop spreading complete disinfor

Gary Marcus argues that software engineers will remain in high demand for years into the future, countering claims that artificial intelligence or other technological developments will eliminate the n

Nous Portal offers everything you need to build with Hermes Agent in one easy subscription: → 300+ models from every frontier lab → Free models and discounts exclusive to the Portal → Bundled tools: w

Allie K. Miller discusses optimizing a lighting setup while experimenting with integrating ChatGPT's image generation, search, and shopping features into a unified workflow. The post appears to recomm

OpenAI released a new dataset on Hugging Face Hub designed to improve ChatGPT's performance in clinical settings, addressing the specific needs and workflows of healthcare professionals. The dataset s

Opened a llama.cpp discussion about whether custom GBNF grammars can compose with tool calls in llama-server. Right now tools work alone, grammar works alone, but tools+grammar doesn't. If you use lla

OpenAI's core principles outline the company's commitment to developing artificial intelligence safely and beneficially, emphasizing responsible AI development and deployment. These principles likely

OpenAI's core principles emphasize democratizing access to AI technology, empowering individuals and organizations through AI tools, promoting universal prosperity across society, building resilient A

Makena Kelly / Ars Technica: Palantir Slack logs and staff interviews reveal internal debates over the company's ICE and DOD contracts during Trump's second term, its manifesto, and more — It took jus

pay attention anon. this is what local ai actually feels like in 2026. qwen 3.6 27b dense just knocked down the second test in my single file agentic benchmark series. on 1x 3090. mandelbrot fractal e