エピソード

  • ThursdAI - Apr 17 - OpenAI o3 is SOTA llm, o4-mini, 4.1, mini, nano, G. Flash 2.5, Kling 2.0 and 🐬 Gemma? Huge AI week + A2A protocol interview

    ThursdAI - Apr 17 - OpenAI o3 is SOTA llm, o4-mini, 4.1, mini, nano, G. Flash 2.5, Kling 2.0 and 🐬 Gemma? Huge AI week + A2A protocol interview
    2025/04/17
    Hey everyone, Alex here 👋Wow. Just… wow. What a week, folks. Seriously, this has been one for the books. This week was dominated by OpenAI's double whammy: first the GPT-4.1 family dropped with a mind-boggling 1 million token context window, followed swiftly by the new flagship reasoning models, o3 and o4-mini, which are already blowing minds with their agentic capabilities. We also saw significant moves from Google with VEO-2 going GA, the fascinating A2A protocol launch (we had an amazing interview with Google's Todd Segal about it!), and even an attempt to talk to dolphins with DolphinGemma. Kling stepped up its video game, Cohere dropped SOTA multimodal embeddings, and ByteDance made waves in image generation. Plus, the open-source scene had some interesting developments, though perhaps overshadowed by the closed-source giants this time.o3 has absolutely taken the crown as the conversation piece, so lets start with it (as always, TL;DR and shownotes at the end, and here's the embedding of our live video show) Big Company LLMs + APIsOpenAI o3 & o4‑mini: SOTA Reasoning Meets Tool‑Use (Blog, Watch Party)The long awaited o3 models (promised to us in the last days of x-mas) is finally here, and it did NOT disappoint and well.. even surprised! o3 is not only SOTA on nearly all possible logic, math and code benchmarks, which is to be expected from the top reasoning model, it also, and I think for the first time, is able to use tools during its reasoning process. Tools like searching the web, python coding, image gen (which it... can zoom and rotate and crop images, it's nuts) to get to incredible responses faster. Tool using reasoner are... almost AGI? This is the headline feature for me. For the first time, these o-series models have full, autonomous access to all built-in tools (web search, Python code execution, file search, image generation with Sora-Image/DALL-E, etc.). They don't just use tools when told; they decide when and how to chain multiple tool calls together to solve a problem. We saw logs with 600+ consecutive tool calls! This is agent-level reasoning baked right in.Anecdote: We tested this live with a complex prompt: "generate an image of a cowboy that on his head is the five last digits of the hexadecimal code of the MMMU score of the latest Gemini model." o3 navigated this multi-step task flawlessly: figuring out the latest model was Gemini 2.5, searching for its MMMU score, using the Python tool to convert it to hex and extract the digits, and then using the image generation tool. It involved multiple searches and reasoning steps. Absolutely mind-blowing 🤯.Thinking visually with imagesThis one also blew my mind, this model is SOTA on multimodality tasks, and a reason for this, is these models can manipulate and think about the images they received. Think... cropping, zooming, rotating. The models can now perform all these tasks to multimodal requests from users. Sci-fi stuff! Benchmark Dominance: As expected, these models crush existing benchmarks.o3 sets new State-of-the-Art (SOTA) records on Codeforces (coding competitions), SWE-bench (software engineering), MMMU (multimodal understanding), and more. It scored a staggering $65k on the Freelancer eval (simulating earning money on Upwork) compared to o1's $28k!o4-mini is no slouch either. It hits 99.5% on AIME (math problems) when allowed to use its Python interpreter and beats the older o3-mini on general tasks. It’s a reasoning powerhouse at a fraction of the cost.Incredible Long Context PerformanceYam highlighted this – on the Fiction Life benchmark testing deep comprehension over long contexts, o3 maintained nearly 100% accuracy up to 120,000 tokens, absolutely destroying previous models including Gemini 2.5 Pro and even the new GPT-4.1 family on this specific eval. While its context window is currently 200k (unlike 4.1's 1M), its performance within that window is unparalleled.Cost-Effective Reasoning: They're not just better, they're cheaper for the performance you get.* o3: $10 input / $2.50 cached / $40 output per million tokens.* o4-mini: $1.10 input / $0.275 cached / $4.40 output per million tokens. (Cheaper than GPT-4.0!)Compute Scaling Validated: OpenAI confirmed these models used >10x the compute of o1 and leverage test-time compute scaling (spending longer on harder problems), further proving their scaling law research.Memory Integration: Both models integrate with ChatGPT's recently upgraded memory feature which has access to all your previous conversations (which we didn't talk about but is absolutely amazing, try asking o3 stuff it knows about you and have ti draw conclusions!)Panel Takes & Caveats:While the excitement was palpable, Yam noted some community observations about potential "rush" – occasional weird hallucinations or questionable answers compared to predecessors, possibly a side effect of cramming so much training data. Nisten, while impressed, still found the style of GPT-4.1 preferable ...
    続きを読む 一部表示
    1 時間 56 分
  • 💯 ThursdAI - 100th episode 🎉 - Meta LLama 4, Google tons of updates, ChatGPT memory, WandB MCP manifesto & more AI news

    💯 ThursdAI - 100th episode 🎉 - Meta LLama 4, Google tons of updates, ChatGPT memory, WandB MCP manifesto & more AI news
    2025/04/10
    Hey Folks, Alex here, celebrating an absolutely crazy (to me) milestone, of #100 episodes of ThursdAI 👏 100 episodes in a year and a half (as I started publishing much later than I started going live, and the first episode was embarrassing), 100 episodes that documented INCREDIBLE AI progress, we mention on the show today, we used to be excited by context windows jumping from 4K to 16K! I want to extend a huge thank you to every one of you, who subscribes, listens to the show on podcasts, joins the live recording (we regularly get over 1K live viewers across platforms), shares with friends and highest thank you for the paid supporters! 🫶 Sharing the AI news progress with you, energizes me to keep going, despite the absolute avalanche of news every week.And what a perfect way to celebrate the 100th episode, on a week that Meta dropped Llama 4, sending the open-source world into a frenzy (and a bit of chaos). Google unleashed a firehose of announcements at Google Next. The agent ecosystem got a massive boost with MCP and A2A developments. And we had fantastic guests join us – Michael Lou diving deep into the impressive DeepCoder-14B, and Liad Yosef & Ido Salomon sharing their wild ride creating the viral GitMCP tool.I really loved today's show, and I encourage those of you who only read, to give this a watch/listen, and those of you who only listen, enjoy the recorded version (though longer and less edited!) Now let's dive in, there's a LOT to talk about (TL;DR and show notes as always, at the end of the newsletter) Open Source AI & LLMs: Llama 4 Takes Center Stage (Amidst Some Drama)Meta drops Llama 4 - Scout 109B/17BA & Maverick 400B/17BA (Blog, HF, Try It)This was by far the biggest news of this last week, and it dropped... on a Saturday? (I was on the mountain ⛷️! What are you doing Zuck) Meta dropped the long awaited LLama-4 models, huge ones this time* Llama 4 Scout: 17B active parameters out of ~109B total (16 experts).* Llama 4 Maverick: 17B active parameters out of a whopping ~400B total (128 experts).* Unreleased: Behemoth - 288B active with 2 Trillion total parameters chonker!* Both base and instruct finetuned models were releasedThese new models are all Multimodal, Multilingual MoE (mixture of experts) architecture, and were trained with FP8, for significantly more tokens (around 30 Trillion Tokens!) with interleaved attention (iRoPE), and a refined SFT > RL > DPO post-training pipeline.The biggest highlight is the stated context windows, 10M for Scout and 1M for Maverick, which is insane (and honestly, I haven't yet seen a provider that is even remotely able to support anything of this length, nor do I have the tokens to verify it) The messy release - Big Oof from Big ZuckNot only did Meta release on a Saturday, messing up people's weekends, Meta apparently announced a high LM arena score, but the model they provided to LMArena was... not the model they released!?It caused LMArena to release the 2000 chats dataset, and truly, some examples are quite damning and show just how unreliable LMArena can be as vibe eval. Additionally, during the next days, folks noticed discrepancies between the stated eval scores Meta released, and the ability to evaluate them independently, including our own Wolfram, who noticed that a quantized version of Scout, performed better on his laptop while HIGHLY quantized (read: reduced precision) than it was performing on the Together API inference endpoint!? We've chatted on the show that this may be due to some VLLM issues, and speculated about other potential reasons for this. Worth noting the official response from Ahmad Al-Dahle, head of LLama at Meta, who mentioned stability issues between providers and absolutely denied any training on any benchmarksToo big for its own good (and us?)One of the main criticism the OSS community had about these releases, is that for many of us, the reason for celebrating Open Source AI, is the ability to run models without network, privately on our own devices. Llama 3 was released in 8-70B distilled versions and that was incredible for us local AI enthusiasts! These models, despite being "only" 17B active params, are huge and way to big to run on most local hardware, and so the question then is, if we're getting a model that HAS to run on a service, why not use Gemini 2.5 that's MUCH better and faster and cheaper than LLama? Why didn't Meta release those sizes? Was it due to an inability to beat Qwen/DeepSeek enough? 🤔 My TakeDespite the absolutely chaotic rollout, this is still a monumental effort from Meta. They spent millions on compute and salaries to give this to the community. Yes, no papers yet, the LM Arena thing was weird, and the inference wasn't ready. But Meta is standing up for Western open-source in a big way. We have to celebrate the core contribution while demanding better rollout practices next time. As Wolfram rightly said, the real test will be the fine-tunes and distillations the community ...
    続きを読む 一部表示
    1 時間 32 分
  • ThursdAI - Apr 3rd - OpenAI Goes Open?! Gemini Crushes Math, AI Actors Go Hollywood & MCP, Now with Observability?

    ThursdAI - Apr 3rd - OpenAI Goes Open?! Gemini Crushes Math, AI Actors Go Hollywood & MCP, Now with Observability?
    2025/04/03
    Woo! Welcome back to ThursdAI, show number 99! Can you believe it? We are one show away from hitting the big 100, which is just wild to me. And speaking of milestones, we just crossed 100,000 downloads on Substack alone! [Insert celebratory sound effect here 🎉]. Honestly, knowing so many of you tune in every week genuinely fills me with joy, but also a real commitment to keep bringing you the the high-signal, zero-fluff AI news you count on. Thank you for being part of this amazing community! 🙏And what a week it's been! I started out busy at work, playing with the native image generation in ChatGPT like everyone else (all 130 million of us!), and then I looked at my notes for today… an absolute mountain of updates. Seriously, one of those weeks where open source just exploded, big companies dropped major news, and the vision/video space is producing stuff that's crossing the uncanny valley.We’ve got OpenAI teasing a big open source release (yes, OpenAI might actually be open again!), Gemini 2.5 showing superhuman math skills, Amazon stepping into the agent ring, truly mind-blowing AI character generation from Meta, and a personal update on making the Model Context Protocol (MCP) observable. Plus, we had some fantastic guests join us live!So buckle up, grab your coffee (or whatever gets you through the AI whirlwind), because we have a lot to cover. Let's dive in! (as always, show notes and links in the end)OpenAI Makes Waves: Open Source Tease, Tough Evals & Billions RaisedIt feels like OpenAI was determined to dominate the headlines this week, hitting us from multiple angles.First, the potentially massive news: OpenAI is planning to release a new open source model in the "coming months"! Kevin Weil tweeted that they're working on a "highly capable open language model" and are actively seeking developer feedback through dedicated sessions (sign up here if interested) to "get this right." Word on the street is that this could be a powerful reasoning model. Sam Altman also cheekily added they won't slap on a Llama-style <700M user license limit. Seeing OpenAI potentially re-embrace its "Open" roots with a potentially SOTA model is huge. We'll be watching like hawks!Second, they dropped PaperBench, a brutal new benchmark evaluating an AI's ability to replicate ICML 2024 research papers from scratch (read paper, write code, run experiments, match results - no peeking at original code!). It's incredibly detailed (>8,300 tasks) and even includes meta-evaluation for the LLM judge they built (Nano-Eval framework also open sourced). The kicker? Claude 3.5 Sonnet (New) came out on top with just 21.0% replication score (human PhDs got 41.4%). Props to OpenAI for releasing an eval where they don’t even win. That’s what real benchmarking integrity looks like. You can find the code on GitHub and read the full paper here.Third, the casual 40 Billion Dollars funding round led by SoftBank. Valuing the company at 300 Billion. Yes, Billion with a B. More than Coke, more than Disney. The blog post was hilariously short for such a massive number. They also mentioned500 million weekly ChatGPT usersand the insane onboarding rate (1M users/hr!) thanks to native image generation, especially seeing huge growth in India. The scale is just mind-boggling.Oh, and for fun, try the new grumpy, EMO "Monday" voice in advanced voice mode. It's surprisingly entertaining.Open Source Powerhouses: Nomic & OpenHands Deliver SOTABeyond the OpenAI buzz, the open source community delivered some absolute gems, and we had guests from two key projects join us!Nomic Embed Multimodal: SOTA Embeddings for Visual DocsOur friends at Nomic AI are back with a killer release! We had Zach Nussbaum on the show discussing Nomic Embed Multimodal. These are new 3B & 7B parameter embedding models (available on Hugging Face) built on Alibaba's excellent Qwen2.5-VL. They achieved SOTA on visual document retrieval by cleverly embedding interleaved text-image sequences – perfect for PDFs and complex webpages.Zach highlighted that they chose the Qwen base because high-performing open VLMs under 3B params are still scarce, making it a solid foundation. Importantly, the 7B model comes with an Apache 2.0 license, and they've open sourced weights, code, and data. They offer both a powerful multi-vector version (ColNomic) and a faster single-vector one. Huge congrats to Nomic!OpenHands LM 32B & Agent: Accessible SOTA CodingRemember OpenDevin? It evolved into OpenHands, and the team just dropped their own OpenHands LM 32B! We chatted with co-founder Xingyao "Elle" Wang about this impressive Qwen 2.5 finetune (MIT licensed, on Hugging Face).It hits a remarkable 37.2% on SWE-Bench Verified (a coding benchmark measuring real-world repo tasks), competing with much larger models. Elle stressed they didn't just chase code completion scores; they focused on tuning for agentic capabilities – tool use, planning, self-correction – using trajectories from their ...
    続きを読む 一部表示
    1 時間 38 分
  • 📆 ThursdAI - Mar 27 - Gemini 2.5 Takes #1, OpenAI Goes Ghibli, DeepSeek V3 Roars, Qwen Omni, Wandb MCP & more AI news

    📆 ThursdAI - Mar 27 - Gemini 2.5 Takes #1, OpenAI Goes Ghibli, DeepSeek V3 Roars, Qwen Omni, Wandb MCP & more AI news
    2025/03/27
    Hey everyone, Alex here 👋 Welcome back to ThursdAI! And folks, what an absolutely insane week it's been in the world of AI. Seriously, as I mentioned on the show, we don't often get weeks this packed with game-changing releases.We saw Google emphatically reclaim the #1 LLM spot with Gemini 2.5 Pro (and OpenAI try really hard to hit back with a new ChatGPT), DeepSeek dropped a monster 685B parameter open-source model, Qwen launched a tiny but mighty 7B Omni model that handles voice and video like a champ, and OpenAI finally gave us native image generation in GPT-4o, immediately unleashing a tidal wave of Ghibli-fication across the internet. It was intense, with big players seemingly trying to one-up each other constantly – remember when Sam Altman dropped Advanced Voice Mode right when Google was about to show Astra? This weeks was this, on steroids. We had a fantastic show trying to unpack it all, joined by the brilliant Tulsee Doshi from the Google Gemini team, my Weights & Biases colleague Morgan McQuire talking MCP tools, and the MLX King himself, Prince Canuma. Plus, my awesome co-hosts Wolfram, Nisten, and Yam were there to add their insights. (watch the LIVE recap or keep reading and listen to the audio pod) So, grab your beverage of choice, buckle up, and let's try to make sense of this AI whirlwind! (TL'DR and show notes at the bottom 👇)Big CO LLMs + APIs🔥 Google Reclaims #1 with Gemini 2.5 Pro (Thinking!)Okay, let's start with the big news. Google came out swinging this week, dropping Gemini 2.5 Pro and, based on the benchmarks and our initial impressions, taking back the crown for the best all-around LLM currently available. (Check out the X announcement, the official blog post, and seriously, go try it yourself at ai.dev).We were super lucky to have Tulsee Doshi, who leads the product team for Gemini modeling efforts at Google, join us on the show to give us the inside scoop. Gemini 2.5 Pro Experimental isn't just an incremental update; it's topping benchmarks in complex reasoning, science, math, and coding. As Tulsee explained, this isn't just about tweaking one thing – it's a combination of a significantly enhanced base model and improved post-training techniques, including integrating those "thinking" capabilities (like chain-of-thought) right into the core models.That's why they dropped "thinking" from the official name – it's not a separate mode anymore, it's becoming fundamental to how Gemini operates. Tulsee mentioned their goal is for the main line models to be thinking models, leveraging inference time when needed to get the best answer. This is a huge step towards more capable and reliable AI.The performance gains are staggering across the board. We saw massive jumps on benchmarks like AIME (up nearly 20 points!) and GPQA. But it's not just about the numbers. As Tulsee highlighted, Gemini 2.5 is proving to be incredibly well-rounded, excelling not only on academic benchmarks but also on human preference evaluations like LM Arena (where style control is key). The "vibes" are great, as Wolfram put it. My own testing on reasoning tasks confirms this – the latency is surprisingly low for such a powerful model (around 13 seconds on my hard reasoning questions compared to 45+ for others), and the accuracy is the highest I've seen yet at 66% on that specific challenging set.It also inherits the strengths of previous Gemini models – native multimodality and that massive long context window (up to 1M tokens!). Tulsee emphasized how crucial long context is, allowing the model to reason over entire code repos, large sets of financial documents, or research papers. The performance on long context tasks, like the needle-in-a-haystack test shown on Live Bench, is truly impressive, maintaining high accuracy even at 120k+ tokens where other models often falter significantly.Nisten mentioned on the show that while it's better than GPT-4o, it might not completely replace Sonnet 3.5 for him yet, especially for certain coding or medical tasks under 128k context. Still, the consensus is clear: Gemini 2.5 Pro is the absolute best model right now across categories. Go play with it!ARC-AGI 2 Benchmark Revealed (X, Interactive Blog)Also on the benchmark front, the challenging ARC-AGI 2 benchmark was revealed. This is designed to test tasks that are easy for humans but hard for LLMs. The initial results are sobering: base LLMs score 0% accuracy, and even current "thinking" models only reach about 4%. It highlights just how far we still have to go in developing truly robust AI reasoning, giving us another hill to climb.GPT-4o got another update (as I'm writing these words!) tied for #1 on LMArena, beating 4.5How much does Sam want to win over Google? So much he's letting it ALL out. Just now, we saw an update from LMArena and Sam, about a NEW GPT-4o (2025-03-26) which jumps OVER GPT 4.5 (like.. what?) and lands at number 2 on the LM Arena, jumping over 3o points.Tied #1 in Coding, Hard ...
    続きを読む 一部表示
    1 時間 24 分
  • ThursdAI - Mar 20 - OpenAIs new voices, Mistral Small, NVIDIA GTC recap & Nemotron, new SOTA vision from Roboflow & more AI news

    ThursdAI - Mar 20 - OpenAIs new voices, Mistral Small, NVIDIA GTC recap & Nemotron, new SOTA vision from Roboflow & more AI news
    2025/03/20
    Hey, it's Alex, coming to you fresh off another live recording of ThursdAI, and what an incredible one it's been! I was hoping that this week will be chill with the releases, because of NVIDIA's GTC conference, but no, the AI world doesn't stop, and if you blinked this week, you may have missed 2 or 10 major things that happened. From Mistral coming back to OSS with the amazing Mistral Small 3.1 (beating Gemma from last week!) to OpenAI dropping a new voice generation model, and 2! new whisper killer ASR models with a Breaking News during our live show (there's a reason we're called ThursdAI) which we watched together and then dissected with Kwindla, our amazing AI VOICE and real time expert. Not to mention that we also had dedicated breaking news from friend of the pod Joseph Nelson, that came on the show to announce a SOTA vision model from Roboflow + a new benchmark on which even the top VL models get around 6%! There's also a bunch of other OSS, a SOTA 3d model from Tencent and more! And last but not least, Yam is back 🎉 So... buckle up and let's dive in. As always, TL;DR and show notes at the end, and here's the YT live version. (While you're there, please hit subscribe and help me hit that 1K subs on YT 🙏 )Voice & Audio: OpenAI's Voice Revolution and the Open Source EchoHold the phone, everyone, because this week belonged to Voice & Audio! Seriously, if you weren't paying attention to the voice space, you missed a seismic shift, courtesy of OpenAI and some serious open-source contenders.OpenAI's New Voice Models - Whisper Gets an Upgrade, TTS Gets Emotional!OpenAI dropped a suite of next-gen audio models: gpt-4o-mini-tts-latest (text-to-speech) and GPT 4.0 Transcribe and GPT 4.0 Mini Transcribe (speech-to-text), all built upon their powerful transformer architecture.To unpack this voice revolution, we welcomed back Kwindla Cramer from Daily, the voice AI whisperer himself. The headline news? The new speech-to-text models are not just incremental improvements; they’re a whole new ballgame. As OpenAI’s Shenyi explained, "Our new generation model is based on our large speech model. This means this new model has been trained on trillions of audio tokens." They're faster, cheaper (Mini Transcribe is half price of Whisper!), and boast state-of-the-art accuracy across multiple languages. But the real kicker? They're promptable!"This basically opens up a whole field of prompt engineering for these models, which is crazy," I exclaimed, my mind officially blown. Imagine prompting your transcription model with context – telling it you're discussing dog breeds, and suddenly, its accuracy for breed names skyrockets. That's the power of promptable ASR! I recorded a live reaction aftder dropping of stream, and I was really impressed with how I can get the models to pronounce ThursdAI by just... asking! But the voice magic doesn't stop there. GPT 4.0 Mini TTS, the new text-to-speech model, can now be prompted for… emotions! "You can prompt to be emotional. You can ask it to do some stuff. You can prompt the character a voice," OpenAI even demoed a "Mad Scientist" voice! Captain Ryland voice, anyone? This is a huge leap forward in TTS, making AI voices sound… well, more human.But wait, there’s more! Semantic VAD! Semantic Voice Activity Detection, as OpenAI explained, "chunks the audio up based on when the model thinks The user's actually finished speaking." It’s about understanding the meaning of speech, not just detecting silence. Kwindla hailed it as "a big step forward," finally addressing the age-old problem of AI agents interrupting you mid-thought. No more robotic impatience!OpenAI also threw in noise reduction and conversation item retrieval, making these new voice models production-ready powerhouses. This isn't just an update; it's a voice AI revolution, folks.They also built a super nice website to test out the new models with openai.fm ! Canopy Labs' Orpheus 3B - Open Source Voice Steps UpBut hold on, the open-source voice community isn't about to be outshone! Canopy Labs dropped Orpheus 3B, a "natural sounding speech language model" with open-source spirit. Orpheus, available in multiple sizes (3B, 1B, 500M, 150M), boasts zero-shot voice cloning and a glorious Apache 2 license. Wolfram noted its current lack of multilingual support, but remained enthusiastic, I played with them a bit and they do sound quite awesome, but I wasn't able to finetune them on my own voice due to "CUDA OUT OF MEMORY" alasI did a live reaction recording for this model on XNVIDIA Canary - Open Source Speech Recognition Enters the RaceSpeaking of open source, NVIDIA surprised us with Canary, a speech recognition and translation model. "NVIDIA open sourced Canary, which is a 1 billion parameter and 180 million parameter speech recognition and translation, so basically like whisper competitor," I summarized. Canary is tiny, fast, and CC-BY licensed, allowing commercial use. It even snagged second place on the ...
    続きを読む 一部表示
    1 時間 51 分
  • 📆 ThursdAI Turns Two! 🎉 Gemma 3, Gemini Native Image, new OpenAI tools, tons of open source & more AI news

    📆 ThursdAI Turns Two! 🎉 Gemma 3, Gemini Native Image, new OpenAI tools, tons of open source & more AI news
    2025/03/13
    LET'S GO! Happy second birthday to ThursdAI, your favorite weekly AI news show! Can you believe it's been two whole years since we jumped into that random Twitter Space to rant about GPT-4? From humble beginnings as a late-night Twitter chat to a full-blown podcast, Newsletter and YouTube show with hundreds of thousands of downloads, it's been an absolutely wild ride! That's right, two whole years of me, Alex Volkov, your friendly AI Evangelist, along with my amazing co-hosts, trying to keep you up-to-date on the breakneck speed of the AI worldAnd what better way to celebrate than with a week PACKED with insane AI news? Buckle up, folks, because this week Google went OPEN SOURCE crazy, Gemini got even cooler, OpenAI created a whole new Agents SDK and the open-source community continues to blow our minds. We’ve got it all - from game-changing model releases to mind-bending demos.This week I'm also on the Weights & Biases company retreat, so TL;DR first and then the newsletter, but honestly, I'll start embedding the live show here in the substack from now on, because we're getting so good at it, I barely have to edit lately and there's a LOT to show you guys! TL;DR and Show Notes & Links* Hosts & Guests* Alex Volkov - AI Eveangelist & Weights & Biases (@altryne)* Co Hosts - @WolframRvnwlf @ldjconfirmed @nisten * Sandra Kublik - DevRel at Cohere (@itsSandraKublik)* Open Source LLMs * Google open sources Gemma 3 - 1B - 27B - 128K context (Blog, AI Studio, HF)* EuroBERT - multilingual encoder models (210M to 2.1B params)* Reka Flash 3 (reasoning) 21B parameters is open sourced (Blog, HF)* Cohere Command A 111B model - 256K context (Blog)* Nous Research Deep Hermes 24B / 3B Hybrid Reasoners (X, HF)* AllenAI OLMo 2 32B - fully open source GPT4 level model (X, Blog, Try It)* Big CO LLMs + APIs* Gemini Flash generates images natively (X, AI Studio)* Google deep research is now free in Gemini app and powered by Gemini Thinking (Try It no cost)* OpenAI released new responses API, Web Search, File search and Computer USE tools (X, Blog)* This weeks Buzz * The whole company is at an offsite at oceanside, CA* W&B internal MCP hackathon and had cool projects - launching an MCP server soon!* Vision & Video* Remade AI - 8 LORA video effects for WANX (HF)* AI Art & Diffusion & 3D* ByteDance Seedream 2.0 - A Native Chinese-English Bilingual Image Generation Foundation Model by ByteDance (Blog, Paper)* Tools* Everyone's talking about Manus - (manus.im)* Google AI studio now supports youtube understanding via link droppingOpen Source LLMs: Gemma 3, EuroBERT, Reka Flash 3, and Cohere Command-A Unleashed!This week was absolutely HUGE for open source, folks. Google dropped a BOMBSHELL with Gemma 3! As Wolfram pointed out, this is a "very technical achievement," and it's not just one model, but a whole family ranging from 1 billion to 27 billion parameters. And get this – the 27B model can run on a SINGLE GPU! Sundar Pichai himself claimed you’d need "at least 10X compute to get similar performance from other models." Insane!Gemma 3 isn't just about size; it's packed with features. We're talking multimodal capabilities (text, images, and video!), support for over 140 languages, and a massive 128k context window. As Nisten pointed out, "it might actually end up being the best at multimodal in that regard" for local models. Plus, it's fine-tuned for safety and comes with ShieldGemma 2 for content moderation. You can grab Gemma 3 on Google AI Studio, Hugging Face, Ollama, Kaggle – everywhere! Huge shoutout to Omar Sanseviero and the Google team for this incredible release and for supporting the open-source community from day one! Colin aka Bartowski, was right, "The best thing about Gemma is the fact that Google specifically helped the open source communities to get day one support." This is how you do open source right!Next up, we have EuroBERT, a new family of multilingual encoder models. Wolfram, our European representative, was particularly excited about this one: "In European languages, you have different characters than in other languages. And, um, yeah, encoding everything properly is, uh, difficult." Ranging from 210 million to 2.1 billion parameters, EuroBERT is designed to push the boundaries of NLP in European and global languages. With training on a massive 5 trillion-token dataset across 15 languages and support for 8K context tokens, EuroBERT is a workhorse for RAG and other NLP tasks. Plus, how cool is their mascot?Reka Flash 3 - a 21B reasoner with apache 2 trained with RLOOAnd the open source train keeps rolling! Reka AI dropped Reka Flash 3, a 21 billion parameter reasoning model with an Apache 2.0 license! Nisten was blown away by the benchmarks: "This might be one of the best like 20B size models that there is right now. And it's Apache 2.0. Uh, I, I think this is a much bigger deal than most people realize." Reka Flash 3 is compact, efficient, and excels at chat, coding, instruction following, and ...
    続きを読む 一部表示
    1 時間 32 分
  • ThursdAI - Mar 6, 2025 - Alibaba's R1 Killer QwQ, Exclusive Google AI Mode Chat, and MCP fever sweeping the community!

    ThursdAI - Mar 6, 2025 - Alibaba's R1 Killer QwQ, Exclusive Google AI Mode Chat, and MCP fever sweeping the community!
    2025/03/06
    What is UP folks! Alex here from Weights & Biases (yeah, still, but check this weeks buzz section below for some news!) I really really enjoyed today's episode, I feel like I can post it unedited it was so so good. We started the show with our good friend Junyang Lin from Alibaba Qwen, where he told us about their new 32B reasoner QwQ. Then we interviewed Google's VP of the search product, Robby Stein, who came and told us about their upcoming AI mode in Google! I got access and played with it, and it made me switch back from PPXL as my main. And lastly, I recently became fully MCP-pilled, since we covered it when it came out over thanksgiving, I saw this acronym everywhere on my timeline but only recently "got it" and so I wanted to have an MCP deep dive, and boy... did I get what I wished for! You absolutely should tune in to the show as there's no way for me to cover everything we covered about MCP with Dina and Jason! ok without, further adieu.. let's dive in (and the TL;DR, links and show notes in the end as always!) ThursdAI - Recaps of the most high signal AI weekly spaces is a reader-supported publication. To receive new posts and support my work, consider becoming a free or paid subscriber.🤯 Alibaba's QwQ-32B: Small But Shocking Everyone!The open-source LLM segment started strong, chatting with friend of the show Junyang Justin Lin from Alibaba’s esteemed Qwen team. They've cooked up something quite special: QwQ-32B, a reasoning-focused, reinforcement-learning-boosted beast that punches remarkably above its weight. We're talking about a mere 32B parameters model holding its ground on tough evaluations against DeepSeek R1, a 671B behemoth!Here’s how wild this is: You can literally run QwQ on your Mac! Junyang shared that they applied two solid rounds of RL to amp its reasoning, coding, and math capabilities, integrating agents into the model to fully unlock its abilities. When I called out how insane it was that we’ve gone from "LLMs can't do math" to basically acing competitive math benchmarks like AIME24, Junyang calmly hinted that they're already aiming for unified thinking/non-thinking models. Sounds wild, doesn’t it?Check out the full QwQ release here, or dive into their blog post.🚀 Google Launches AI Mode: Search Goes Next-Level (X, Blog, My Live Reaction).For the past two years, on this very show, we've been asking, "Where's Google?" in the Gen AI race. Well, folks, they're back. And they're back in a big way.Next, we were thrilled to have Google’s own Robby Stein, VP of Product for Google Search, drop by ThursdAI after their massive launch of AI Mode and expanded AI Overviews leveraging Gemini 2.0. Robby walked us through this massive shift, which essentially brings advanced conversational AI capabilities straight into Google. Seriously — Gemini 2.0 is now out here doing complex reasoning while performing fan-out queries behind the scenes in Google's infrastructure.Google search is literally Googling itself. No joke. "We actually have the model generating fan-out queries — Google searches within searches — to collect accurate, fresh, and verified data," explained Robby during our chat. And I gotta admit, after playing with AI Mode, Google is definitely back in the game—real-time restaurant closures, stock analyses, product comparisons, and it’s conversational to boot. You can check my blind reaction first impression video here. (also, while you're there, why not subscribe to my YT?)Google has some huge plans, but right now AI Mode is rolling out slowly via Google Labs for Google One AI Premium subscribers first. More soon though!🐝 This Week's Buzz: Weights & Biases Joins CoreWeave Family!Huge buzz (in every sense of the word) from Weights & Biases, who made waves with their announcement this week: We've joined forces with CoreWeave! Yeah, that's big news as CoreWeave, the AI hyperscaler known for delivering critical AI infrastructure, has now acquired Weights & Biases to build the ultimate end-to-end AI platform. It's early days of this exciting journey, and more details are emerging, but safe to say: the future of Weights & Biases just got even more exciting. Congrats to the whole team at Weights & Biases and our new colleagues at CoreWeave!We're committed to all users of WandB so you will be able to keep using Weights & Biases, and we'll continuously improve our offerings going forward! Personally, also nothing changes for ThursdAI! 🎉MCP Takes Over: Giving AI agents super powers via standardized protocol Then things got insanely exciting. Why? Because MCP is blowing up and I had to find out why everyone's timeline (mine included) just got invaded.Welcoming Cloudflare’s amazing product manager Dina Kozlov and Jason Kneen—MCP master and creator—things quickly got mind-blowing. MCP servers, Jason explained, are essentially tool wrappers that effortlessly empower agents with capabilities like API access and even calling other LLMs—completely ...
    続きを読む 一部表示
    1 時間 51 分
  • 📆 Feb 27, 2025 - GPT-4.5 Drops TODAY?!, Claude 3.7 Coding BEAST, Grok's Unhinged Voice, Humanlike AI voices & more AI news

    📆 Feb 27, 2025 - GPT-4.5 Drops TODAY?!, Claude 3.7 Coding BEAST, Grok's Unhinged Voice, Humanlike AI voices & more AI news
    2025/02/28
    Hey all, Alex here 👋What can I say, the weeks are getting busier , and this is one of those "crazy full" weeks in AI. As we were about to start recording, OpenAI teased GPT 4.5 live stream, and we already had a very busy show lined up (Claude 3.7 vibes are immaculate, Grok got an unhinged voice mode) and I had an interview with Kevin Hou from Windsurf scheduled! Let's dive in! 🔥 GPT 4.5 (ORION) is here - worlds largest LLM (10x GPT4o) OpenAI has finally shipped their next .5 model, which is 10x scale from the previous model. We didn't cover this on the podcast but did watch the OpenAI live stream together after the podcast concluded. A very interesting .5 release from OpenAI, where even Sam Altman says "this model won't crush on benchmarks" and is not the most frontier model, but is OpenAI's LARGEST model by far (folks are speculating 10+ Trillions of parameters) After 2 years of smaller models and distillations, we finally got a new BIG model, that shows scaling laws proper, and while on some benchmarks it won't compete against reasoning models, this model will absolutely fuel a huge increase in capabilities even for reasoners, once o-series models will be trained on top of this. Here's a summary of the announcement and quick vibes recap (from folks who had access to it before) * OpenAI's largest, most knowledgeable model.* Increased world knowledge: 62.5% on SimpleQA, 71.4% GPQA* Better in creative writing, programming, problem-solving (no native step-by-step reasoning).* Text and image input and text output* Available in ChatGPT Pro and API access (API supports Function Calling, Structured Output)* Knowledge Cutoff is October 2023.* Context Window is 128,000 tokens.* Max Output is 16,384 tokens.* Pricing (per 1M tokens): Input: $75, Output: $150, Cached Input: $37.50.* Foundation for future reasoning models4.5 Vibes RecapTons of folks who had access are pointing to the same thing, while this model is not beating others on evals, it's much better at multiple other things, namely creative writing, recommending songs, improved vision capability and improved medical diagnosis. Karpathy said "Everything is a little bit better and it's awesome, but also not exactly in ways that are trivial to point to" and posted a thread of pairwise comparisons of tone on his X threadThough the reaction is bifurcated as many are upset with the high price of this model (10x more costly on outputs) and the fact that it's just marginally better at coding tasks. Compared to the newerSonnet (Sonnet 3.7) and DeepSeek, folks are looking at OpenAI and asking, why isn't this way better? Anthropic's Claude 3.7 Sonnet: A Coding PowerhouseAnthropic released Claude 3.7 Sonnet, and the immediate reaction from the community was overwhelmingly positive. With 8x more output capability (64K) and reasoning built in, this model is an absolute coding powerhouse. Claude 3.7 Sonnet is the new king of coding models, achieving a remarkable 70% on the challenging SWE-Bench benchmark, and the initial user feedback is stellar, though vibes started to shift a bit towards Thursday.Ranking #1 on WebDev arena, and seemingly trained on UX and websites, Claude Sonnet 3.7 (AKA NewerSonner) has been blowing our collective minds since it was released on Monday, especially due to introducing Thinking and reasoning in a combined model. Now, since the start of the week, the community actually had time to play with it, and some of them return to sonnet 3.5 and saying that while the model is generally much more capable, it tends to generate tons of things that are unnecessary. I wonder if the shift is due to Cursor/Windsurf specific prompts, or the model's larger output context, and we'll keep you updated on if the vibes shift again. Open Source LLMsThis week was HUGE for open source, folks. We saw releases pushing the boundaries of speed, multimodality, and even the very way LLMs generate text!DeepSeek's Open Source SpreeDeepSeek went on an absolute tear, open-sourcing a treasure trove of advanced tools and techniques:This isn't your average open-source dump, folks. We're talking FlashMLA (efficient decoding on Hopper GPUs), DeepEP (an optimized communication library for MoE models), DeepGEMM (an FP8 GEMM library that's apparently ridiculously fast), and even parallelism strategies like DualPipe and EPLB.They are releasing some advanced stuff for training and optimization of LLMs, you can follow all their releases on their X accountDual Pipe seems to be the one that got most attention from the community, which is an incredible feat in pipe parallelism, that even got the cofounder of HuggingFace super excitedMicrosoft's Phi-4: Multimodal and Mini (Blog, HuggingFace)Microsoft joined the party with Phi-4-multimodal (5.6B parameters) and Phi-4-mini (3.8B parameters), showing that small models can pack a serious punch.These models are a big deal. Phi-4-multimodal can process text, images, and audio, and it actually beats WhisperV3 on transcription! As Nisten ...
    続きを読む 一部表示
    1 時間 41 分