Search: “claude”

arXiv:2609.09203v1 Announce Type: new Abstract: Existing benchmarks for autonomous AI scientists evaluate only final outputs---generated code, hypotheses, or papers---yet discard the reasoning process

arXiv:2609.10883v1 Announce Type: cross Abstract: Language models are trained to implement a helpful AI Assistant character (e.g., Claude). We explore how finetuning on synthetic stories affects this

vulkan : add command-buffer debug labels for GPU profilers (#28101) vulkan : add command-buffer debug labels for GPU profilers Co-authored-by: gabby-zy z2262718160@gmail.com Assisted-by: Claude Code v

Same weights. 50 of harness search. 3x on Terminal-Bench. We optimized the OpenCode harness for GPT-OSS-20B (high reasoning) with a meta-harness: an agent that reads failures, patches the harness, and

The 256th episode of the LWiAI Podcast (recorded 09/03/2026) discusses major AI developments from the prior week: Anthropic’s Claude Fable 5.1 and Mythos 5.1, which feature lower pricing, stronger age

I’ve been using Qwen a lot recently and I’m honestly very impressed with it. For some of my tasks, Qwen seems to understand what I’m actually trying to achieve better than ChatGPT/GPT-5.6. I currently

This is a really neat benchmark. It's super interesting that Astra starts strong and holds the lead for up to 19 hours, but Fable 5.1 catches up in the final hours. Not entirely clear why. Different m

Catch up on July and August in Microsoft Foundry: stable Hosted Agent and Toolbox SDK paths, Claude tools on Azure-hosted deployments, Model Router updates, local inference improvements, and the SDK m

I'm the CTO of a mid-size nonprofit, and I run a local Qwen stack as a coding subagent for that work — partly on principle (a fair amount of what I handle shouldn't leave the building), partly because

This weekend I posted about the gap closing between frontier models and open source models. Well, now I'm coming with receipts. I've been running local + cloud models against real public github codeba

While we see for frontier models similar scores among famous coding benchmarks, across: DeepSWE, Terminal-Bench, LiveCodeBench, Code-Arena ELO. Here are in my opinion some next level benchmarks that r

correction: the switching costs weren't enough to stop my desire to try out gpt-6 astra i ported over all my skills and conversational context to codex this weekend. planning to use it as my daily dri

Hello everyone. I felt current LLM benchmark harnesses hand you headline numbers but offer no tooling to see how models actually answered each question (they dump everything to a JSONL or Parquet file

I ran a side-by-side ML text-processing and model-training workflow using Fable 5.1 vs. Astra (both on xhigh), and the results could not have been more different. Warning, long post. TL;DR -- Astra co

Checking that a major mathematical proof is correct can take years. Formalization—converting the mathematical reasoning into a form computer proof assistants like Lean can verify—can help. Last month,

Claude Code is absolutely horrendous at managing docx XML structures and it's obscene that the best these frontier companies can do are skills. Skills are prone to breaking, burn tokens (hello busines

GPT-6 Astra is coming to Devin. On FrontierCode 1.1, Astra performs within 0.4 points of Fable 5 at a 64% lower cost. It also sets a new SOTA on our internal testing benchmark, generating more compreh

GPT‑6 Astra GPT-6 Astra is 'rolling out today to a limited set of organizations and over the coming days will become available to all ChatGPT Plus, Pro, Business, and Enterprise users, as well as thro

vulkan: handle larger batch sizes (>4) efficiently for IQ3_S mat-vec (#27449) vulkan: handle larger batch sizes (>4) efficiently for IQ3_S mat-vec when NUM_COLS > 4. 5x perf at n=8 Assisted-by: Claude

arXiv:2609.00365v1 Announce Type: new Abstract: Command-line coding agents (e.g., Claude Code, Gemini CLI) can already read and write files and sustain long sessions, yet end-to-end research still fra

I've said this in another post, but again started with Claude Code, loved OpenCode, but I felt chained and tied to them both for the longest time (especially CC, just the worst). I felt less productiv

Meet the team behind the Replit MCP this Friday at 9AM PT. Join the Replit community team live with Amadeo Pellicce (@amapel) and Jean-Luc Thumm (@jeanlucthumm) for a deeper dive on the Replit MCP, no

day 1 of recreating iconic tech from my childhood :) I rebuilt Cher’s iconic closet as a full-stack app in @Replit 💛 the frontend uses React + TypeScript, with an Express backend. I used Replit’s Cler

kv-cache : optimize restoring non-contiguous cells (#27991) kv cache : batch state restore scatter reads per contiguous run When restoring state into non-contiguous destination cells (e.g. a prompt-ca

(not written by Claude, all errors and crappy text are result of too little coffee on a Sunday morning ;) Our home server is a 2018 Thinkstation P520, bought for about 600eur in 2023. It's been upgrad

specs hardware: M4 Max 128GB Studio inference engine: llama.cpp (qwen4exp branch) judge: claude-opus-4-6 AtomicChat/Qwen3.8-Flash-Next-GGUF Qwen3.8-Flash-Next is a great model I benched in my previous

GLM 5.3 and GLM 5.3 Flash (previously Ox Alpha) are fully rolled out on Ollama's cloud. Private. Fast. US and Europe hosted. Zero data retention. GLM 5.3: ollama launch claude --model glm-5.3:cloud GL

arXiv:2608.26130v1 Announce Type: new Abstract: Coding agents built on large language models (LLMs), such as Claude Code, Cursor, OpenAI Codex, GitHub Copilot, and Aider, receive tool responses that r

Just a rumour of a bug is enough to find a security exploit these days Anil Madhavapeddy is a professor of computer science at Cambridge and a core maintainer of the OCaml compiler. In this somewhat a

Post rédigé avec l'aide de GLM5.3 flash Contexte : formateur professionnel d'adultes en France, j'utilise des agents LLM au quotidien et le français qu'ils produisent est mon critère n°1, avant les be

I've been building a small tool opensource project that sits between applications and local LLM servers (starting with Ollama) to diagnose silent inference failures instead of just showing logs. Thing

A high-performance 125B model now running locally on just 75GB RAM! Thank you @UnslothAI for the day-0 support.🥳 Qwen3.8-Flash can now be run locally! 🔥 The 125B MoE model outperforms Claude-Opus-4.6

grammar : parse - in char classes as literal hyphen (#27591) grammar : accept '-' escape in character classes gbnf_escape_char_class() escapes '-' as '-' but parse_char() rejected that escape, so gene

arXiv:2608.22817v1 Announce Type: new Abstract: Industrial technical reports contain high-value knowledge for maintenance, troubleshooting, and product engineering, but their heterogeneous structure (

Hi, since ollama provide multiple cloud models i was wondering is there an app that could be used for chat like claude already has but you can switch models? Or if that is complicated to build at leas

Hi, I’m having fun using “huihui_ai/Qwen3.6-abliterated:35b-Claude-4.7” for pen testing. It’s uncensored so it does whatever I want. I’m on M4 Pro 14 core 64GB. Just wondering if there are some models

What do I want in AI? Here are just a few things. I want voice-enabled everything. I want things to be more proactive. I want to manage AI’s escalations (versus delegation). I want those escalations t

I ran the Aider benchmark on Qwen 3.8 27B FP8 with FP8 KV cache 256K context vLLM. The score: 72.9 This matches Gemini 2.5 Pro from 2025-04-12 which also scored 72.9. Beats Claude Opus 4 from 2025-05-

I've tried a few Gemma 4 models, for example 'gemma4:26b-mlx'. It says 'I cannot process images.'. On their website it mentions images, audio etc. https://ollama.com/library/gemma4/tags I’m using Olla

i got it last week and im really impressed. its maybe like a sonnet from last year or 6 months ago. i had built some automation for myself and a dashboard cobbled together over the years from bits of

I've been trying to figure out what the best configuration for my local stack would be and have been primarily determining this through trial and error. I wanted to get some outside opinions and stack

Where did THESE things go for ChatGPT? Claude has them. I can access older versions of my conversations easily. But with ChatGPT, they just DISAPPEARED. I can no longer regenerate answers or following

I recently bought a 32GB V100 off eBay and thought I was all set with rudimentary tests showing zero issues. But then I started seeing weird VRAM-related errors in llama.cpp. I sic'ed Claude on it, to

i have another saas to kill (will share results of Kill My SaaS 1 next week!!) btw if you havent set your {codex | claude | gemini | devin} automations to autoresearch how to improve your seo/aeo ever

In 1948, a 32-year-old at Bell Labs published a paper nobody fully understood. Engineers found it too mathematical. Mathematicians found it too engineering-focused. One prominent mathematician reviewe

Inkling and Inkling Small are now served directly by @thinkymachines on OpenRouter, free to use inside agentic harnesses only. Plug them into Claude Code, Codex, Hermes Agent and more to unlock the fr