Search: “agents”

Searching for the right context in a sea of information is such a timeless problem in our field. I'm excited to talk about some of the approaches we've learned and benefited from at Thrive next week a

We already had gemini-3.1-flash-lite-preview back on March 3rd, not clear if this new gemini-3.1-flash-lite is different other than no longer being marked as a 'preview'. Pricing appears to be the sam

We've teamed up with @cerebras to offer free Windsurf plans for SWE-1.6 Fast Mode at up to 1000 tok/s! Fast Mode is built on Cerebras inference, enabling superior speed for planning and development wi

@PPLXfinance @PPLXDevs On FinSearchComp T1, Finance Search delivered the highest accuracy for live financial data and the lowest cost per correct answer in the cohort. Every result includes citations,

Two weeks after release, Hy3 preview is #1 on @OpenRouter's weekly leaderboard with 3.66T tokens processed, up 298% week-over-week. #1 in overall usage, tool calls, and coding. 15.4% market share acro

We built a simple app that's also probably the best PDF -> text phone app there. Take a picture of any document: a filled out form, identification, a statement, an essay - and we'll convert it into we

we're continuing to see clear examples where a model's harness is a major determinant of overall performance. with the same model, running on same task, it's easy to observe very different scores depe

i have yet to meet a single person who feels like claude code is getting exponentially better on some kind of fast take off Anthropic pays $750K/ year per senior engineer. The creator of Claude Code j

toodles from mickey mouse clubhouse was weirdly ahead of its time wake phrase: mickey mouse clubhouse launched in 2006, and “oh toodles” trained toddlers on the assistant wake phrase years before siri

This is why I keep going on about LangGraph 1.2 alpha is looking great: node-level error handlers, timeouts, improved performance, and stronger typing LangGraph is the runtime layer you want underneat

this one is doing v well btw if you want the popular vote filter on the firehose of all the things @patrickdebois was one of the track keynotes i gave a 'blank check' to based on his sincere support s

Are AIs about to subjugate humanity? In the debate about catastrophic AI risk, evolutionary scenarios receive far too little attention compared to largely speculative arguments about “instrumental con

Grok Voice is used by Starlink right now Grok Voice brutally dominates the top of the τ-voice Bench Grok scores 67.3%, while Gemini sits at 43.8% and GPT Realtime at 35.3% This is a massive lead over

I was quoted a couple times in this Atlantic article, but that isn’t (the only) reason I think it is good. It lays out the reasons why we whipsawed from “AI is a bubble” to “there are not enough data

People are really enjoying our full workshops showing end to end walkthroughs of real production workflows! This is a rare double header with @braintrust's Giran Moodley and @OussamaHaff walking thoug

Cool paper from Meta FAIR. It's on self-improving LLMs but on the pretraining side. (bookmark it) Most LLM safety, factuality, and reasoning fixes get bolted on at post-training. By then, the patterns

On 5/5 @realDanFu and team will discuss DSV4’s hybrid attention and KV cache efficiency, should be a great session! Join us Tue 5/5: #DeepSeek-V4's hybrid attention + sparse MoE reduces KV cache up to

One week since the launch of GPT-5.5, and it’s already our strongest model launch yet. API revenue is growing more than 2x faster than any prior release, while Codex doubled revenue in under seven day

Our CEO @jerryjliu0 in @VentureBeat , on what's actually changing in the LLM stack: 'We've really identified that there's a core set of data that has been locked up in all these file format containers

The new Grok comes in below the latest Chinese open weights models, Grok 4 was at the frontier when released. (& Artificial Analysis: please stop using GDPval-AA which is not a useful test of anything

When training Grok 4.3, we spoke directly with devs and businesses to understand what they actually needed: a model that’s fast, affordable, and great at tool calling. The result is a daily driver tha

This post by Ethan Mollick likely discusses how advanced AI systems like hypothetical future GPT versions could autonomously execute complex, real-world tasks with minimal human direction, using a hum

At @sequoia’s AI Ascent last week, @gdb told me something that stuck: in late 2024, AI wrote ~20% of @OpenAI's code. That number is now 80%. We also got into why human attention, not compute, is the r

ml-intern is fully on mobile now you can launch 8 A100s from your phone. while on the couch. while commuting. wherever I just did this while biking. same sessions as your desktop too — start a run on

// When to Retrieve During Reasoning // Pay attention to this one, AI devs. (bookmark it) Most RAG systems retrieve once, before the model starts reasoning. Large reasoning models like o1 and R1 don't

A million-token context window is not a strategy. 🛑 Our Head of DevRel, @RoieSchwabco , explains why dumping data is killing your RAG performance: 📍 One needle in a haystack? Easy. 📍 Multiple needles?

IMO DeepSeek v4 demonstrated utter confidence and competence by not benchmaxxing, not focusing on some BS final run cost, not even spending inference-optimal compute. just showed up, demonstrated SOTA

Recreated the app with ml intern to compare. Went faster than in cowork, some things are better (ex direct integration in the desktop reachy mini app), some things are worse (had to debut the install)

Excited to support @NVIDIA Nemotron 3 Nano Omni, now available on Fireworks. It's the first open model that handles vision, audio, video, and text in a single inference loop. Built for multimodal sub-

First open-weight model from @poolsideai! Apache license, and available on Ollama to try. 👇👇👇 model page Today we’re releasing Laguna XS.2, Poolside’s first open-weight model. It’s a 33B total / 3B ac

GLM 5.1 from @Zai_org is now available on @FireworksAI_HQ Training Platform across the Managed and Training API workflows. Try SFT and DPO with smart defaults or your own custom loss function with a 2

No matter what kind of company you are...start making your internal company data legible to AI. Today. As a founder, you are essentially building two versions of your company: the one humans work in a

@NVIDIA Nemotron 3 Nano Omni is now on Together AI. Enterprise multimodal AI — video, audio, image, documents & text — optimized for speed and scale. ✅ ~3B active params, 9x higher throughput ✅ Fully

Open Models & a potential looming Haiku-apocalypse? 🚀 chart comparison UI courtesy of @OpenRouter there's a large class of problems where you don't need frontier intelligence. you want cheap, fast, an

Want to see which frontier models do the best on document understanding? Check out our ParseBench leaderboard on @kaggle! https://www.kaggle.com/benchmarks/llamaindex-org/parsebench For more details o

“Always keep a separate backup.” For sure, every experienced programmer should know this. 𝘉𝘶𝘵 𝘸𝘦 𝘫𝘶𝘴𝘵 𝘤𝘳𝘦𝘢𝘵𝘦𝘥 𝘢 𝘸𝘩𝘰𝘭𝘦 𝘨𝘦𝘯𝘦𝘳𝘢𝘵𝘪𝘰𝘯 𝘰𝘧 𝘷𝘪𝘣𝘦 𝘤𝘰𝘥𝘦𝘳𝘴 𝘸𝘩𝘰 𝘥𝘰𝘯’𝘵. And we now have a legion of synthetic coding

going to buy 2 rtx 6000 just because of the capabilities of local models becoming great! no more outsourcing of research to the api Xiaomi MiMo-V2.5 is now officially open-sourced！ MIT License, suppor

I'm HIRING 5 more people to help me build the future of AI media. The Rundown is closing in on 3M active readers, and the demand is far outpacing what we can handle. 2,000 referral bonus if you help u

Loan processors spend 40–60% of their time reconciling income across tax returns, pay stubs, W-2s, and bank statements. We built an end-to-end pipeline that automates it with LlamaParse + the Claude A

People keep blaming the users for the growing number of vibe-coded reasoners. Doing so is *half* right. Users *are*screwing up - by letting vibe coded stuff access their files, without proper backups,

.@swyx on whether AI infrastructure has finally stabilized: Media Always enjoy getting to chat with @swyx on our annual cross-episode with @latentspacepod on the state of AI. We hit on what’s shifted,

Continued weak spots of AI, from the point of view of a business professional and not a PhD biochemist: 1) SVGs. The ability to 'illustrate' and have that thing be infinitely scalable. See below image

I am increasingly bullish on open source harnesses (like OpenCode) not because they will be better than SOTA closed harnesses, but because they will never pull shady stuff like what Claude Code and ot

Opened a llama.cpp discussion about whether custom GBNF grammars can compose with tool calls in llama-server. Right now tools work alone, grammar works alone, but tools+grammar doesn't. If you use lla

The community can now download pre-quantized weights from MLX community repo on HF thanks to @LambdaAPI Model collection: https://huggingface.co/collections/mlx-community/deepseek-v4 DeepSeek-V4-Flash

Launching pyptx — a Python DSL for writing NVIDIA PTX kernels. One PTX instruction = one Python call. Write pure PTX in Python. Direct Hopper + Blackwell support: wgmma, TMA, tcgen05, mbarriers. JAX +