Knowledge catalogue
arXiv:2608.16211v1 Announce Type: new Abstract: Long-horizon agents are beginning to automate complete workflows that produce code, reports, and research artifacts. Medical imaging workflows are multi
OpenAI is announcing security updates following the July news that its AI broke out of a sandboxed environment and accidentally hacked Hugging Face, including improvements to its research environments
I've been experimenting with Qwen3.8-27B using DeepSeek Harness. It's a monster at long-horizon tasks, and the results were pretty wild. DeepSeek Harness ran on my Windows PC and connected over LAN to
It's a small experiment of mine to check thinking effort on Qwen and I do have to say xhigh does overthink but I'm not sure if it's bad because the result is rather amazing. Although the prompt was ve
i was having ollama cloud in last two month and it was great with generous amount of ds v4 pro and glm5.2 usage and actually i built so much with it without worrying about costs or limits. and i was u
teams want to understand what their agents are doing but it’s hard to sift through all that trace data at scale but you can basically find any signal by fine-tuning a small, cheap model on data showin
This 1 hour workshop on context engineering will help you build agents that hold long conversations and cut your token cost by up to 90%. Last month we gave it live at the AI Engineer World's Fair 202
arXiv:2608.14639v1 Announce Type: cross Abstract: Per-field accept/review with selective risk at most alpha -- accept a field only if the error rate among accepted fields is controlled -- is the trust
arXiv:2608.13786v1 Announce Type: cross Abstract: Large language model (LLM) chatbots are increasingly used to answer clinical questions with citations to relevant clinical studies. Prior research has
arXiv:2608.13675v1 Announce Type: cross Abstract: Between October 2018 and July 2026 AI models progressed from simple systems like BERT to massive agents that solve complex math and write software. Th
https://preview.redd.it/wkg27e152qjh1.png?width=853&format=png&auto=webp&s=2e3f8b11ea6393041f501e95c5835f9bea0245dd So ive been trying different harnesses and coding agents with the new qwen 3.8 , and
Quick update on the RTX 5060 Ti local LLM repo. It has changed quite a bit since my previous posts. The project started as a collection of practical notes and benchmark results. That was useful, but a
It could be just me and my setup, but I just tried to get fable to adjust my Qwen 3.8 deployment script and (simple task, mostly knob turning).... and it outright refused. Censor box immediately kicks
arXiv:2608.12373v1 Announce Type: new Abstract: Large language models are increasingly used in strategic and advisory contexts, yet their safety alignment is typically evaluated in English only. We te
Qwen3.8-27B is available on @ollama ！Any harness you run, the model always delivers. Let's code together, and show us what you build.😎 Qwen 3.8 27B is now available on Ollama. It's one of the best ope
Google will now allow you to remove visible watermarks from the images, videos, and music made with AI tools. With the update, you can toggle off a new 'Media watermark' setting in Gemini and Google's
Throughput observation more than a demo. Box and recording are sudoingX's on X, shared with his okay; I work on Ling at inclusionAI. He handed the web UI on his llama-server a 33-token prompt — build
arXiv:2608.12138v1 Announce Type: cross Abstract: General-purpose large language models (LLMs) have recently been reported to match or exceed specialized clinical AI tools on medical benchmarks, but s
arXiv:2608.12249v1 Announce Type: new Abstract: Modernizing legacy Fortran is a problem of volume: the transformations are individually routine, but the codebases can be enormous, and across much of c
🧩 DeepSeek Harness v0.1 is now available in Developer Preview! 🔹 We’re opening it up to developers building agent harnesses worldwide and open-sourcing the codebase in MIT license. 🔹 Powered by the Co
Grok 4.6 is objectively #1 when considering intelligence, speed & cost SpaceXAI's Grok 4.6 scores 61 on the Artificial Analysis Intelligence Index, joining the frontier in line with GPT-5.6 Sol, with
arXiv:2608.10273v1 Announce Type: cross Abstract: Deploying large language models (LLMs) for decision support in emergency departments (EDs) faces two major challenges: privacy risks of transmitting p
But then users start to report a weird bug. It's the 4th time your team has been trying to fix it. I mean... asking AI to fix it. Unfortunately, it seems like not even Fable can figure it out. You go
arXiv:2608.10408v1 Announce Type: new Abstract: Vision-language models (VLMs) have shown strong capabilities in generating visualization code from textual or visual specifications. However, real-world
arXiv:2608.09072v1 Announce Type: cross Abstract: Large language model-powered coding agents are increasingly used to modify existing code repositories, for example, by adding features or fixing bugs.
arXiv:2608.09164v1 Announce Type: new Abstract: Aligning large language models (LLMs) with human privacy preferences requires capturing individuals' disclosure boundaries beyond general privacy norms.
really excited to see this release AND integrate it with deepagents!! https://www.langchain.com/blog/switchyard-agent-routing-benchmark Lightning strikes for continuous and long-run agents! Nemotron 3
This is part of working with the EU AI Act, other labs are adding similar watermarking. It’s hard to identify AI-generated text, and this gives people better tools to do that. We’ll also be a shipping
arXiv:2608.08254v1 Announce Type: new Abstract: Structured output, where an LLM populates a predefined JSON schema, has become a default mechanism for data labeling and information extraction, but it
A downside with VLM-based parsing is that they’re generally slower than text-based heuristic approaches. As a result they add latency to any ad-hoc file processing *in-the agent loop* (e.g. if you upl
Frontier performance you can actually own. Proud to help power DeepSeek-V4-Flash on Ollama's cloud, with the fastest hosted performance available. Open weights, zero data retention, U.S. & EU hosting.
Oh no, we aren’t going to go back to this sort of prompting again, are we? I would love Anthropic to test if it actually works robustly, because our experiments (with slightly older models) found it d
arXiv:2608.06968v1 Announce Type: cross Abstract: Language-model agents act on state encodings of their environment, yet these are treated as interchangeable interfaces. Using pretrained language mode
Disclosure: I’m the author of Ante. DeepSeek recently reported an 82.7% score on Terminal-Bench 2.1 for DeepSeek V4 Flash 0731. Its evaluation used “DeepSeek Harness minimal mode,” which hasn’t been r
Currently serving 200 tps+ output speed for DeepSeek-V4-Flash on Ollama's cloud with zero data retention (ZDR). Have an amazing weekend 🫡 DeepSeek-V4-Flash-0731 is now fully rolled out as the new defa
I’m running DSV4F 0731 on dual spark, and honestly… wow. It’s an absolute workhorse, and the benchmarks are real. Everyday tasks with Hermes agent? Effortless. Coding tasks with OpenCode? I’m genuinel
And here's an even better version, built by GPT-5.6 Sol Ultra running in Code Desktop https://x.com/simonw/status/2085808307865014295 I had Codex Desktop and GPT-5.6 Sol Ultra take a go at building my
arXiv:2603.00059v3 Announce Type: replace-cross Abstract: How well can AI-derived synthetic research data replicate the responses of human participants? An emerging literature has begun to engage with
upgraded my stack, and i can now work on almost anything from anywhere hands free: - talk to chief of staff (via remote codex voice or text) - chief assigns tasks to managers of various projects - man
An AI model from Meta also hacked another company during testing Stop me if you've heard this one before: An AI model from the parent company of Facebook and Instagram hacked into another company’s sy
A small update to Sir Shortoken. Sir Shortoken already had Quick, Balanced, Deep, Bullets, and Aggressive Bullets. I wanted something between Bullets and normal prose. So I added LELP-S+ (Less English
arXiv:2608.04205v1 Announce Type: new Abstract: Human evaluation of AI systems and digital products is costly, slow, and difficult to scale. Offline evaluations are more scalable but often abstract aw
Zac Hall / 9to5Mac: OpenAI debuts Agent Plugins, an open standard for bundling skills and MCP servers, and says Amazon, Cursor, Microsoft, and Vercel are on its steering committee — OpenAI's GPT-5 tur
arXiv:2608.03070v1 Announce Type: cross Abstract: Frontier AI model developers increasingly rely on layered safeguards to prevent catastrophic misuse, but little public evidence exists on how much pro
There are a lot of LLM benchmarks but few, if any, harness benchmarks. I am thinking this would be a really good community project to build one. End goal: a leaderboard of harness performance (multipl
DeepSeek V4 Flash is Ollama's fastest growing model ever in token usage, and the most popular model on OpenRouter this week. It’s available in Pi across a range of providers. If you’ve never tried an
arXiv:2608.03297v1 Announce Type: new Abstract: A standard claim in the literature on retrieval-augmented and memory-augmented language models is that shorter context is better when the relevant infor
arXiv:2608.03659v1 Announce Type: cross Abstract: Large language models (LLMs) are increasingly used to generate scientific reviews, yet existing evaluations rarely examine whether different providers
Incident Report: unsanctioned agent behaviour during cyber testing It happened again. This time it was the UK government's AI Security Institute who accidentally attacked other companies while running
arXiv:2608.02672v1 Announce Type: cross Abstract: Cloud misconfiguration remains a leading cause of security incidents, yet whether LLMs and SLMs can generate security-compliant Infrastructure-as-Code
arXiv:2608.03979v1 Announce Type: cross Abstract: We introduce Video-DeepResearch (Video-DR), extending multimodal agents from static images to continuous video streams, a setting that demands dense s
DeepSeek-V4-Flash-0731 is Ollama's fastest growing model ever in token usage. We are scaling capacity in US & Europe. On Ollama, this model runs with high performance (100tps+) and zero data retention
I released LLM 0.32 this morning, the most significant new version of LLM since the initial launch of the project. The new version includes support for visible reasoning traces, server-side provider t
arXiv:2608.01347v1 Announce Type: new Abstract: Large reasoning models used as coding agents incur costs from deliberation, tool calls, and repeated agent turns, yet the causal effect of prompt wordin
Sam Sabin / Axios: The UK AISI says it observed a total of 19 instances where Mythos and GPT-5.6 Sol tried to hack people and companies during a routine cyber evaluation in July — The U.K. AI Security
Alibaba Group Holding Ltd. today debuted a new addition to its Qwen series of open-source large language models. Qwen3.8-Max is the Chinese e-commerce giant’s most capable LLM to date. It features 2.4
Chinese tech giant Alibaba released what it says is its largest and 'most capable AI model to date,' claiming performance rivaling the best systems from US frontier labs Anthropic and OpenAI, as well
My comment on Devtools must be open source (exe.dev) — Hacker News.One of the arguments for open source software for end-users has always been the freedom to examine and modify how that software works
Thanks for the recognition. We'll keep building! 🚀 Big news: Qwen3.8-Max by @Alibaba_Qwen just landed at #4 on the Frontend Code Arena leaderboard with a score of 1,668! With 1,668 points, Qwen3.8-Max
Open letters about AI development I wrote this summary of the past few weeks of open letters as a section of my sponsors-only newsletter but I've decided to share it here as well. Open Weights and Ame