TechniqueRLHF / Alignment8 recent entries29 Sept 2026GPT-6.1 Sol shows major improvements over GPT-6 Sol in our alignment evaluations, bringing it more in line with GPT-6 Astra. It’s more trans…GPT-6.1 Sol shows major improvements over GPT-6 Sol in our alignment evaluations, bringing it more in line with GPT-6 Astra. It’s more transparent about its limitations and more reliable at respecting→29 Sept 2026Fwiw I am certain you can build a DeepSeek/Zhipu/Minmax etc level AI lab in the UK Not easy ofc, great teams thereFwiw I am certain you can build a DeepSeek/Zhipu/Minmax etc level AI lab in the UK Not easy ofc, great teams there 🚨 WATCH: Andy Burnham says he will create a 'global code' for AI so Britain can 'capt
TechniqueRAG8 recent entries28 Sept 2026Didn't expect this 🤯 We replaced embeddings with Jev in GPT Researcher's RAG pipeline and tested both on 28 research tasks from SimpleQA an…Didn't expect this 🤯 We replaced embeddings with Jev in GPT Researcher's RAG pipeline and tested both on 28 research tasks from SimpleQA and open ended research. Jev beat embeddings on every quality m→30 Sept 2026View pplx-embed-v2-context-9b-preview on Hugging Face: https://huggingface.co/perplexity-ai/pplx-embed-v2-context-9b-previewPerplexity AI released a preview of its embedding model “pplx‑embed‑v2‑context‑9b” on Hugging Face on September 30, 2026 (7:07 PM local time). The Hugging Face repository page displays 3 122 views and→2 Oct 2026Can your agent read the documents your business runs on? @jerryjliu0 on parsing, search & source citations. World’s Fair 2026 recording: htt…Can your agent read the documents your business runs on? @jerryjliu0 on parsing, search & source citations. World’s Fair 2026 recording: https://www.youtube.com/watch?v=RQi7x-navxU Keep learning with →6 Oct 2026We analyzed a year of agent research across 4 tasks: deep research, RAG indexing, agentic search and coding. Found that first asking ‘Is thi…We analyzed a year of agent research across 4 tasks: deep research, RAG indexing, agentic search and coding. Found that first asking ‘Is this task verifiable?’ exposed inefficiencies in the agent arch→6 Oct 2026There's one question you should ask before you build an agent. Most people skip it (and pay for it in compute). Over a year of agent researc…There's one question you should ask before you build an agent. Most people skip it (and pay for it in compute). Over a year of agent research at @AI21Labs across deep research, RAG indexing, agentic s→7 Oct 2026Introducing MCP tools for @dair_ai. Connect the MCP to your Codex/Claude/Grok Bot to discover and explore the top AI papers. We carefully cu…Introducing MCP tools for @dair_ai. Connect the MCP to your Codex/Claude/Grok Bot to discover and explore the top AI papers. We carefully curate the papers, so you can expect mostly bangers. The index→7 Oct 2026Explore the top AI papers of the week with our brand-new MCP tools. Connect it to Codex, Claude Code, or Grok Bot.Explore the top AI papers of the week with our brand-new MCP tools. Connect it to Codex, Claude Code, or Grok Bot. Introducing MCP tools for @dair_ai. Connect the MCP to your Codex/Claude/Grok Bot to →12 Oct 2026Must-read paper on the effectiveness of multi-agent systems and persistent memory. We have recently seen many viral examples of multi-agent …Must-read paper on the effectiveness of multi-agent systems and persistent memory. We have recently seen many viral examples of multi-agent systems scaled via persistent memory. This work takes a clos
TechniqueAgents8 recent entries11 Oct 2026Anatomy skill for building wireframe designs and interactive prototype machines is now an officially integrated optional skill in Hermes Age…Anatomy skill for building wireframe designs and interactive prototype machines is now an officially integrated optional skill in Hermes Agent You can find it in the optional built in skills in the sk→12 Oct 2026world’s first full length workshop on claude flows @cjav_dev and Harrison Stall are kicking off @aidotengineer bright and early on a monday …world’s first full length workshop on claude flows @cjav_dev and Harrison Stall are kicking off @aidotengineer bright and early on a monday morning to a PACKED room, standing room only #AIEngineerNY @→12 Oct 2026We need a name for the kind of people that conflate 2022 pure LLMs that were in fact a tiny bit like stochastic parrots (not my phrase, and …We need a name for the kind of people that conflate 2022 pure LLMs that were in fact a tiny bit like stochastic parrots (not my phrase, and not one I ever endorsed) with 2026 systems that couple those→12 Oct 2026New paper from Microsoft and colleagues on generating enterprise data for agents. If you train or evaluate agents on long-running business w…New paper from Microsoft and colleagues on generating enterprise data for agents. If you train or evaluate agents on long-running business work, it's worth your time. (bookmark it) MiniCorp is an offi→12 Oct 2026Must-read paper on the effectiveness of multi-agent systems and persistent memory. We have recently seen many viral examples of multi-agent …Must-read paper on the effectiveness of multi-agent systems and persistent memory. We have recently seen many viral examples of multi-agent systems scaled via persistent memory. This work takes a clos→12 Oct 2026Introducing RSI-Anything: Unlocking Recursive Self-Improvement with World Models 🚀 Can AI learn to improve itself by predicting the consequ…Introducing RSI-Anything: Unlocking Recursive Self-Improvement with World Models 🚀 Can AI learn to improve itself by predicting the consequences of its actions? Built on JEPA-Anything, RSI-Anything us→12 Oct 2026Introducing QwenGyre, bringing elastic RL to extreme-long-horizon (XLong) agent training. ✨ It launches with two core designs: 🥳 - Elastic …Introducing QwenGyre, bringing elastic RL to extreme-long-horizon (XLong) agent training. ✨ It launches with two core designs: 🥳 - Elastic Scheduler: reallocates GPUs between rollout & training as dem→12 Oct 2026Ha gave this take to our team last week Will share some (very basic) stuff I vibe coded around this shortly Lots to be explored here!Ha gave this take to our team last week Will share some (very basic) stuff I vibe coded around this shortly Lots to be explored here! One of my more controversial bets: the AI feed will be the form fa
TechniqueFine-tuning8 recent entries7 Oct 2026Introducing River Recipes: our open-source initiative for turning promising research into vetted, reproducible training recipes. Our first r…Introducing River Recipes: our open-source initiative for turning promising research into vetted, reproducible training recipes. Our first recipe tackles text-to-SQL, where our trained open models bea→8 Oct 2026Big new paper nobody is talking about ‼️ 🌎 Robot world models now have scaling laws. Meta trained an 8B-parameter JEPA on 15,000 hours of r…Big new paper nobody is talking about ‼️ 🌎 Robot world models now have scaling laws. Meta trained an 8B-parameter JEPA on 15,000 hours of robot video to prove it. RoboJEPA (FAIR at Meta + Mila) imagin→10 Oct 2026Recommended paper from Sakana AI on recursive self-improvement. They propose an interesting way to scale recursive self-improvement through …Recommended paper from Sakana AI on recursive self-improvement. They propose an interesting way to scale recursive self-improvement through multi-agent self-supervision. In this line of research, self→10 Oct 2026Finetuned Qwen3.5-4B into a decision model like Jev using @UnslothAI. - 4-bit QLoRA, bf16, single A100, 15 min. - Train/val loss flatten aft…Finetuned Qwen3.5-4B into a decision model like Jev using @UnslothAI. - 4-bit QLoRA, bf16, single A100, 15 min. - Train/val loss flatten after 2 epochs so most of the learning happens fast. - Trained →11 Oct 2026We were able to fine tune an open weight model (Qwen3.5-9B) on proprietary internal data at @coinbase, and it out performed frontier models,…We were able to fine tune an open weight model (Qwen3.5-9B) on proprietary internal data at @coinbase, and it out performed frontier models, at much lower cost and speed, for a specialized task (fraud→11 Oct 2026New paper from the team at Sakana AI: Recursive Self-Improvement through Multi-Agent Self-Supervision (MASS) How do we keep improving AI whe…New paper from the team at Sakana AI: Recursive Self-Improvement through Multi-Agent Self-Supervision (MASS) How do we keep improving AI when the tasks become too complex for humans to reliably evalua→11 Oct 2026I've been having a lot of fun trying a wide range of LLM post-training experiments using KerasHub + JAX + TPUs. Might open-source some of th…On October 11 2026 François Chollet announced that he has been experimenting with large‑language‑model post‑training techniques using KerasHub, JAX, and TPUs. He indicated that portions of his work ma→11 Oct 2026A good example of why open weight and open source models are important - they permit users to fine-tune specific use cases with greater cost…A good example of why open weight and open source models are important - they permit users to fine-tune specific use cases with greater cost efficiency. As has been the case in other technology market
TechniqueMultimodal8 recent entries7 Oct 2026We’re open-sourcing pplx-embed-v2-late, multi-vector embeddings for text and images, 9B and 0.6B, in one shared embedding space. You can use…We’re open-sourcing pplx-embed-v2-late, multi-vector embeddings for text and images, 9B and 0.6B, in one shared embedding space. You can use these to index multimodal data with 9B, and query on device→7 Oct 2026We @sequoia are thrilled to lead @MeckaAI’s Series B. AI took the digital world by storm; bringing it into the physical world will be a wave…We @sequoia are thrilled to lead @MeckaAI’s Series B. AI took the digital world by storm; bringing it into the physical world will be a wave at least as large, but harder - it demands excellence acros→7 Oct 2026managed deep agents 0.9 is here! things we shipped: ⏰ agents can schedule tasks OBO themselves or the user 🏭 dynamically configure your mda…managed deep agents 0.9 is here! things we shipped: ⏰ agents can schedule tasks OBO themselves or the user 🏭 dynamically configure your mda per run (models, tools, skills, etc.) 👀 Slack reactions show→8 Oct 2026an open model just beat Jev outright on clinical decisions 🔥 pplx-decider v1.1 got 643 of 669 right vs 628 for Jev, at 42% less per decisio…an open model just beat Jev outright on clinical decisions 🔥 pplx-decider v1.1 got 643 of 669 right vs 628 for Jev, at 42% less per decision and about the same speed. and you can download the weights →9 Oct 2026It’s Friday 🎉 Here’s a look at this week’s announcements: — http://SynthID.com is now available globally in English, allowing anyone to use…It’s Friday 🎉 Here’s a look at this week’s announcements: — http://SynthID.com is now available globally in English, allowing anyone to use our detector portal to easily verify if images, video, or au→10 Oct 2026I was curious about how omni decision models could be used in rescue workers bodycams or smart glasses, so I decided to build a quick demo. …I was curious about how omni decision models could be used in rescue workers bodycams or smart glasses, so I decided to build a quick demo. I went with @liquidai d1-omni-600M since it supports both vi→11 Oct 2026Introducing Decision 3.0: towards open multimodal foundation decision models ⚡ Open and state-of-the-art from 0.6B to 27B: #1 on both Jev De…Introducing Decision 3.0: towards open multimodal foundation decision models ⚡ Open and state-of-the-art from 0.6B to 27B: #1 on both Jev Decision Index boards in our evaluation, on a new Pareto front→11 Oct 2026Decision 3.0 now on Core ML 🍎 d3-lite triaging 1,000 pull requests into vllm-sr workgroups, live on an M5 Pro: 0.12 s per PR, 8.3 PRs/s, no…Decision 3.0 now on Core ML 🍎 d3-lite triaging 1,000 pull requests into vllm-sr workgroups, live on an M5 Pro: 0.12 s per PR, 8.3 PRs/s, nothing leaves the Mac ⚡ lite, nano and mini are all converted
TechniqueSafety8 recent entries9 Oct 2026Assorted things I've been mulling over regarding agents in the economy: • Companies are in some sense the original superintelligence. It's o…Assorted things I've been mulling over regarding agents in the economy: • Companies are in some sense the original superintelligence. It's often the case that they can use their amortized cognitive su→10 Oct 2026Reasoning From Scratch: Reinforcement Learning with Verifiable Rewards (RLVR) round 2. Covering clipped policy ratios, KL loss term, format …Reasoning From Scratch: Reinforcement Learning with Verifiable Rewards (RLVR) round 2. Covering clipped policy ratios, KL loss term, format rewards, and other GRPO tips & tricks. 00:00 Introduction an→11 Oct 2026Introducing Multi-Agent Self-Supervision (MASS): Recursive self-improvement through collective intelligence Blog: https://pub.sakana.ai/mass…Introducing Multi-Agent Self-Supervision (MASS): Recursive self-improvement through collective intelligence Blog: https://pub.sakana.ai/mass/ As AI systems tackle increasingly open-ended research prob→12 Oct 2026We need a name for the kind of people that conflate 2022 pure LLMs that were in fact a tiny bit like stochastic parrots (not my phrase, and …We need a name for the kind of people that conflate 2022 pure LLMs that were in fact a tiny bit like stochastic parrots (not my phrase, and not one I ever endorsed) with 2026 systems that couple those→12 Oct 2026Sure does look like @GavinSBaker is “suggesting that public companies are materially inflating their remaining performance obligations”. yet…Sure does look like @GavinSBaker is “suggesting that public companies are materially inflating their remaining performance obligations”. yet another way the Ai industry is trying to con retail investo→12 Oct 2026No Generative AI. Just one gorgeous building, beautiful light, and an Phone 16 Pro.On October 12, 2026, Gary Marcus (@GaryMarcus) posted on Twitter saying, “No Generative AI. Just one gorgeous building, beautiful light, and an Phone 16 Pro.” The tweet, timestamped 7:01 AM UTC, recei→12 Oct 2026Introducing RSI-Anything: Unlocking Recursive Self-Improvement with World Models 🚀 Can AI learn to improve itself by predicting the consequ…Introducing RSI-Anything: Unlocking Recursive Self-Improvement with World Models 🚀 Can AI learn to improve itself by predicting the consequences of its actions? Built on JEPA-Anything, RSI-Anything us→12 Oct 2026i don’t know whether this is a joke or serious but the whole challenge with generative AI is that it literally cannot be trusted to follow “…i don’t know whether this is a joke or serious but the whole challenge with generative AI is that it literally cannot be trusted to follow “simple, generalizable instructions”. the inability of most p