Search: “jeremy-howard--x”

Fun fact - if you have a recent commit that mentions OpenClaw in a json blob, Claude Code will either refuse your request or bill you extra money. This is an empty repo, I'm just calling Claude Code d

I can’t believe I stopped using Claude Code max and entirely use DeepSeek and Hermes. It’s so fast, so so fast, 3x faster for the same task. So cheap. I spent $5 last week and never need worry about b

The Zig project's rationale for their blanket ban on AI-assisted contributions makes a lot of sense to me - for them, time spent reviewing PRs isn't about the code, it's about growing new contributors

DeepSeek V4 Pro is crazy good at bug fixing. Costs counted in cents not dollars/tens of dollars. It’s the next level quiet confidence not to get caught up by benchmarks & rankings, and just let us use

Ernie-5.1 from @ErnieforDevs lands at #13 in Text Arena — now the #1 highest-ranked model from a Chinese lab. Strongest categories: - #9 Math - #1 Legal & Government - #4 Business, Management & Financ

IBM Granite just released two multilingual embedding models with 97M and 311M parameters 🤏🏻 ModernBERT-based, 200+ languages, 32K context, and built for retrieval, search, similarity, and code. And...

The new DeepSeek-V4, like DeepSeek-V3, uses concepts from our 2024 paper on Self-Rewarding LMs -- see screenshots of their tech reports! (Congrats!) Classical :) Self-Rewarding LMs from Jan 2024: http

Xiaomi MiMo-V2.5-Pro achieves multiple breakthroughs in the latest Arena rankings (Apr 26, 2026) 🔥 🏆 Text Arena (Expert) — #6 globally | #1 open-source model Also #1 among Chinese models, with Xiaomi

However, older versions have a critical CVE, so you do need to upgrade! If you use uv (thanks to @charliermarsh) you can pop this in your pyproject to work around it: ``` [tool.uv] override-dependenci

I know the litellm team have a *lot* going on, & I have no desire to increase their workload even more… But if you're a litellm user, this is a critical issue to know about - it currently force downgr

I'm so confused… We're excited to partner with Google to offer Grounding With Exa inside of Gemini models! Using Exa's agent-first search, Gemini models can now access billions of websites, technical

I'm speechless at Google signing a deal to use our AI models for classified tasks. Frankly, it is shameful. For HR, I'm not speaking on behalf of Google but in my personal capacity, quoting public inf

This is great - @deepseek_ai V4 supports prefill! :D Most other providers have been dropping support for this critically important capability, so wonderful to see at least one company stepping up. htt

This post is a question about search provider preferences for use with various open-source tools and APIs (openclaw, pi, opencode, etc.), with examples of options like Brave, SerpAPI, and Gemini. The

It just takes a little time and care to engage with the work of new folks in the field -- but it can make a big difference :D On a more personal note, I'm grateful to @jeremyphoward for helping me bre

Xiaomi MiMo-V2.5 is now officially open-sourced！ MIT License, supporting commercial deployment, continued training, and fine-tuning - no additional authorization required. Two models, both supporting

🔥DeepSeek Input Cache Price Drop! Effective immediately, the price for input cache hits across the ENTIRE DeepSeek API series is reduced to just 1/10th of the original price! Build more efficiently fo

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'

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

THIS GUY LOST 200 IN ONE DAY BECAUSE THE STRING 'HERMES.md' WAS IN HIS GIT COMMITS HERMES.md is a real convention used in AI agent projects. it's a system prompt specification file. not some obscure e

Launching pyptx — a Python DSL for writing NVIDIA PTX kernels. One PTX instruction = one Python call. Write pure PTX in Python. Direct Hopper + Blackwell support: wgmma, TMA, tcgen05, mbarriers. JAX +

🚀 DeepSeek-V4 Preview is officially live & open-sourced! Welcome to the era of cost-effective 1M context length. 🔹 DeepSeek-V4-Pro: 1.6T total / 49B active params. Performance rivaling the world's top

Sapiens2 is the highest quality ViT backbone that now exists in the public domain. It was pretrained on the equivalent of 1/2 of all human images on Flickr. First public release by a large lab that is

this is probably the most important piece of software of the decade next to vllm and sglang. i'm not joking. llama.cpp at 100k stars now that 90% of the code worldwide is being written by AI agents, I

Today I re-iterate: I hate MoEs and we are wasting time on them.... Let's unite and call a global ban on MoEs please. Please 1M+ salary researchers: do better... credits to @IlysMoutawwakil for the gr

AFAIK this is the first time it's been made official from an OpenAI staffer - the `/backend-api/codex/responses` endpoint that Pi and Opencode (IIUC) uses is officially supported! :D This is really gr

... and Anthropic reverted this change. Claude Code is now part of Pro, as per the Pricing page. Important note on the growth hack: Anthropic advertises safety and integrity as their values. A 'fake d

Jeremy Howard shares positive impressions of working with Kimi Moonshot's K2.6 model for two hours, noting it performed well despite being used somewhat unexpectedly. The post suggests K2.6 demonstrat

This post appears to reference regulatory or policy 'clampdowns' on AI, with the author expressing anticipation that OpenAI will face similar restrictions. Without access to the full context or surrou

For the 'small test' they've modified their docs to remove mention of Claude Code in Claude Pro: https://support.claude.com/en/articles/11145838-using-claude-code-with-your-max-plan It's been a shock

🚀 Meet Qwen3.6-27B, our latest dense, open-source model, packing flagship-level coding power! Yes, 27B, and Qwen3.6-27B punches way above its weight. 👇 What's new: 🧠 Outstanding agentic coding — surpa

Anyone know whether OpenAI officially supports the use of the `/backend-api/codex/responses` endpoint that Pi and Opencode (IIUC) uses? It doesn't seem to be documented, and was reverse engineered by

@nbaschez what test, when it seems to be a full-on update to the pricing page? I could not get it to not show this update, no matter how many different devices I checked in (not connected to my accoun

Since this is blowing up on hacker news. Boris said that CLI usage is allowed. Thus we added support for it, only to find out that we are still blocked there. It is trival to work around with a few re

This is so confusing. Did Anthropic really just drop Claude Code from their 20/month plan? Why would they do that through a pricing page update without making a proper announcement? Plus, 20/month sti

This is what I’ve been cooking in the past 4 months . GPT Image 2 is over a massive 240 elo jump over the second place model, marking the biggest jump bigger than the rest of the leaderboard combined

I upgraded my Claude token counter tool to compare different models and Opus 4.7 does appear to use 1.46x times the tokens for text and up to 3x the tokens for images - it's priced the same as Opus 4.

A user reports that Opus 4.7 performs better in Claude Code when executed with a minimal system prompt (using just a period) rather than the full default system prompt, suggesting that reducing system

Philosophy (among other things) grad here. I could write a whole essay about this video, and mostly the reactions to it. People are dunking on her because of what she symbolises more than what she say

in 1982 Titanic survivor Ruth Becker was giving an interview where she stated the ship broke in two. The treasurer of the Titanic Historical Society actually took the microphone away from her and said

I cannot provide a reliable summary of this specific post without access to its content, as the URL appears incomplete or potentially inaccurate. To create an accurate knowledge base entry, please pro

This post likely discusses why narratives or thought experiments set in zero-dimensional space—where there is no length, width, height, or any spatial extension—fail to generate compelling storytellin

Amanda Askell is likely a researcher or professional involved in AI safety or alignment work, and Jeremy Howard is publicly crediting or thanking her for a contribution or achievement on social media.

Roy Rogers demonstrates his preferred style of playing the hurdy-gurdy, showcasing traditional or characteristic technique in this post shared by Jeremy Howard on X. The post reflects appreciation for

So cool to see that open-source, with open experimentation (and with the help of someone posting blog posts about their personal research), can yield a very robust method for MoE balancing. This metho

The one nag I have to add to the system prompt still: 'PLEASE remember and follow this CRITICAL guidance with great care: Do NOT end responses with follow-up offers like 'Want me to...', 'Let me know