Knowledge catalogue
Professional services automation software company Kantata Inc. today unveiled Agent Studio, a tool that lets services firms build custom artificial intelligence agents by describing the job they want
Release: llm-typesafe 0.1a0 I built this new plugin for LLM to add support for TypeSafe AI's new Jev model. Install it like this: llm install llm-typesafe Then set an API key (get one here, the waitli
arXiv:2609.24144v1 Announce Type: new Abstract: Group-relative reinforcement learning compares rollouts of the same prompt, but independent environment noise can obscure these comparisons. We study pa
arXiv:2609.23121v1 Announce Type: new Abstract: Multimodal Agentic Retrieval (MAR) requires agents to solve complex information-seeking tasks by iteratively invoking external tools. Typical frameworks
arXiv:2609.24983v1 Announce Type: new Abstract: We present onPanda, an interactive tool for efficiently annotating LLM alignment data and agent trajectories. onPanda adopts token-level correction as i
arXiv:2609.23132v1 Announce Type: new Abstract: Soft everting robots can traverse long, confined paths by continuously growing, yet active interaction remains limited to a single tool fixed at or near
Jev and the System One Model: RLCD, intelligence/, reliable AI, & the end of chat-first AI https://www.latent.space/p/jev @typesafeai CEO @CompleteSkeptic explains why AI can solve extraordinarily har
Jev pod tomorrow subscribe on apple /youtube @latentspacepod thanks to @allenpark and Ke for making this happen! After co-inventing ChatGPT, I kept asking myself: why have superhuman chat models not l
github repo: https://github.com/athulg93/vscode-localllm Alright, So i have made some major updates to this extension Update the git flow: Found out that there were some issues and the / part was a me
chat : add dedicated Ling 3.0 (Bailing V3) parser (#28682) chat: add dedicated Ling 3.0 (Bailing V3) parser Ling 3.0 Flash templates pre-open the think block in the generation prompt, so the model nev
Given the recent interest in tools like Jev, I wanted to share ProgramAsWeights (PAW), an open-source research project I'm working on at the University of Waterloo. You describe a text function in Eng
arXiv:2609.20301v1 Announce Type: new Abstract: AI agents increasingly orchestrate long-running activities with users, tools, and system resources for days and weeks. To improve agent quality, safety,
Being a computer scientist who refuses to find anything about LLMs interesting right now is a bit like being a geneticist who refuses to find anything interesting about the recently opened Jurassic Pa
TypeSafe’s Jev classifies, scores, and routes without generating text — up to hundreds of times cheaper than an LLM judge. What that changes for evals, confidence routing, and application architecture
Why @CompleteSkeptic created ChatGPT and then spent 2 years in stealth building Jev Media After co-inventing ChatGPT, I kept asking myself: why have superhuman chat models not led to AGI? I’ve spent t
arXiv:2609.18994v1 Announce Type: new Abstract: We present the first benchmark suite for formal verification of Programmable Logic Controller (PLC) programs that combines controlled ground truth with
arXiv:2609.18864v1 Announce Type: cross Abstract: Privacy evaluations of tool-using LLM agents often inspect a designated action, final response, or attacker report. These local proxies can miss unaut
arXiv:2609.17632v1 Announce Type: new Abstract: Large language model (LLM) trading agents can combine market data, news, and executable analysis, but their behavior is often controlled by static hand-
arXiv:2609.18274v1 Announce Type: cross Abstract: Classroom observations are widely recognized as a key tool for establishing benchmarks of education quality and guiding pedagogical improvement, yet t
OpenAI says AI can automate 80% of GDP. Today, with current models. So why hasn't it been automated yet? @swyx says the constraint is supply. Supply of chips and memory. Demand shot through the roof b
congrats to Diogo on a full launch! for more on typesafe: check his aie talk: https://www.youtube.com/watch?v=cJ0EOzey--o out now! After co-inventing ChatGPT, I kept asking myself: why have superhuman
arXiv:2609.16461v1 Announce Type: cross Abstract: Agentic large language model (LLM) systems rely on long interaction histories to preserve instructions, tool states, intermediate decisions, and unres
Setup for one long agentic coding session (tools + vision) on a single 5090: Qwen3.8-27B RVN Heretic (ARA abliterated) at Q6_K, 159744 context, 1 slot, q8_0 K/V, DFlash2 speculative decoding, vision p
After co-inventing ChatGPT, I kept asking myself: why have superhuman chat models not led to AGI? I’ve spent the last 2 years in stealth building a new way to train models (RLCD), and a new type of fr
During an outage, every second matters. That is one of the reasons OpenAI is using @cerebras internally. @seanlie describes how fast inference is being used for incident response and critical research
arXiv:2511.03728v2 Announce Type: replace Abstract: On-device AI agents offer the potential for personalized, low-latency assistance, but their deployment is fundamentally constrained by limited memor
arXiv:2609.13206v1 Announce Type: cross Abstract: Marine ecosystems are increasingly impacted by climate change, necessitating tools to identify and predict spatial habitat information. To build such
Tool: Gemini Live audio Google released Gemini 3.8 Live and 3.8 Live Extended Thinking today - two new speech-to-speech models that are a similar shape to OpenAI's GPT-Live family. I pointed GPT-6 Ast
arXiv:2609.14198v1 Announce Type: new Abstract: Surgical tissue manipulation demands precision; however, tool-tissue manipulation force magnitudes under realistic conditions are rarely quantified. To
arXiv:2609.14699v1 Announce Type: new Abstract: Visual content shapes audience perception and opinion on social media, and computational social science increasingly relies on automated tools to analyz
arXiv:2609.13672v1 Announce Type: new Abstract: AI agents can be interrupted while editing files, calling tools, or carrying out multi-step tasks. Restarting repeats completed work, but continuing fro
arXiv:2609.15494v1 Announce Type: new Abstract: Recent investigations of the July 2026 OpenAI--Hugging Face incident motivate two questions about agent behavior under task failure: when an assigned ta
arXiv:2609.15309v1 Announce Type: new Abstract: Large language model (LLM) agents allocate test-time compute adaptively as they revise solutions, use tools, explore alternatives, and decide when to st
I reallise this is not exactly a locally hostable model, at least definitly not on my hardware. But I figured some of you might have some insight on this. I run an agentic coding benchmark. The model
Deel handles compliance, payroll, and HR questions across 150+ countries. Instead of searching for the answer through an external LLM each time, they fine-tuned small models built on Deel's own compli
I CAN FINALLY TALK ABOUT IT The last few months, my team at @g2i_ai has been helping organize AIE Code Summit in SF this Nov alongside the AIE core team. So grateful for the opportunity to run point o
“Just-in-Time” OCR The latest agent harnesses (e.g. Cowork, Codex, Grok) do 2 passes of ad-hoc document processing when executing over a user-uploaded ‘data room’ of documents: 1️⃣ A fast and light pa
The contagion of fear Bryan Cantrill responds to the tweet by former Anthropic employee Jacob Coxon confirming that many Anthropic researchers believe AI 'could kill us all by the end of the decade'.
Law enforcers already have authority to charge companies and their CEOs for creating and releasing dangerous, unvetted, or defective products. We shouldn’t let discussions about new legal regimes dist
This is pretty neat: ChatGPT Work and GPT-6 Astra (I used 'Max') can take an address and produce a 5K/10K circular running route starting from that address, using OSM data https://simonwillison.net/20
arXiv:2609.11028v1 Announce Type: cross Abstract: LM-agent benchmarks increasingly function as interactive evaluation infrastructure. Agents observe state, call tools, modify workspaces, submit artifa
Dario is making the case for the opposite. This actually makes our life harder and makes it easier for others to catch up with us, but we still think it is the right thing to do. Happy to come on the
For a while, I must admit, it looked as if software developer roles like mine were done for. How could we fight against tireless robots? But our industry is slowly realizing that making truly cutting-
arXiv:2609.09404v1 Announce Type: cross Abstract: Agentic AI frameworks let a language model plan, keep memory, and call tools that reach real files, mail, and services. Most of these agents also read
arXiv:2609.10892v1 Announce Type: cross Abstract: When an indirect prompt injection succeeds against an LLM agent, the compromise is visible in the agent's own behavior: a benign prefix of tool calls,
If you can write down how you do your work, you can automate it. Here's what I did to support GitHub's APAC marketing team. The post Marketing ops as code: Automating events from planning to follow-up
So you want to use OpenRouter? One of OpenRouter's selling points is that it 'handles fallbacks automatically and picks the most cost-effective option for each request', so you can call a single API e
Together Fine-Tuning adds the latest open-weight models, live experiment tracking, Expert LoRA, early stopping, tokenized dataset previews, pre-flight validation, and lower training prices on selected
together fine-tuning now supports glm-5.3, kimi k2.7-code + more we also added live run metrics, experiment comparisons, early stopping, dataset previews + finer training controls prices are down 30–7
arXiv:2609.09856v1 Announce Type: cross Abstract: The rapid adoption of generative AI tools such as ChatGPT has sparked intense debate about their risks and opportunities for education, as well as the
arXiv:2609.06543v1 Announce Type: new Abstract: Enterprise AI is evolving into an Enterprise Operating System where autonomous AI agents can plan, reason, use memory, invoke tools, execute workflows,
GLM-5.3 is now available for training on Fireworks Dedicated Training API and Managed Training surfaces. Built for complex coding and long-horizon agents and now available to train on our dedicated in
Here's a Blender model of a Pluribus themed Fabergé egg I had GPT-6 Astra build - I generated the concept image using ChatGPT Images 2.5, then pasted the image into Codex and told Astra to turn that i
Native is now the future of mobile at Shopify Shopify are moving from React Native back to separate Swift and Kotlin codebases for their native apps, for the exact reason you would expect: We decided
Reinforcement learning at @cognition's scale is a hard infrastructure problem. We are proud to be part of the stack behind it. Congrats to the team on SWE-2! Read more about how we think about RL at F
arXiv:2609.09815v1 Announce Type: cross Abstract: Compound LLM systems often solve a coordination problem by adding a higher-level LLM. The resulting meta-agent reads workers' outputs, writes the fina
arXiv:2609.05531v1 Announce Type: cross Abstract: No specification says how a governed autotelic AI agent organization, where agents pursue self-generated goals inside guardrails, should be designed a
arXiv:2609.09402v1 Announce Type: cross Abstract: Enterprises managing large X.509 certificate inventories face a prioritization problem: deterministic analysis tools that precisely identify standards
arXiv:2609.06972v1 Announce Type: cross Abstract: LLM agents complete tasks by issuing sequences of tool calls, and every observation they read is a channel through which an indirect prompt injection
at long lake, we've bought 40+ services businesses to build AI where work actually happens we're working on: - deploying agents to complete knowledge work - frontier eval generation from real workflow