DeepLearning.AI(@DeepLearningAI)

💻Learn by building with an AI coding agent, right in your browser. 👀Live preview, nothing to insta...

DeepLearning.AI (@DeepLearningAI) — Sun, 18 Oct 2026 16:05:01 GMT

💻Learn by building with an AI coding agent, right in your browser. 👀Live preview, nothing to install.

📚TDeepLearning.AIJ7H’s new agentic coding lab in our course, Building AI Assistants with On-Device Memory.

👉Enroll for frdeeplearning.ai/courses/buildi…UL#AI#AIAgentse#AIEngineeringring

Your browser does not support the video tag.

🔗 View on Twitter

💬10🔄29❤️193👀12248📊48

⚡ Powered by xgo.ing

🧠 Yann LeCun helped invent the convolutional neural network and shared the 2018 Turing Award with H...

DeepLearning.AI (@DeepLearningAI) — Sat, 17 Oct 2026 16:05:14 GMT

🧠 Yann LeCun helped invent the convolutional neural network and shared the 2018 Turing Award with Hinton and Bengio.

Now he joins us at AI Dev NYC to share his latest work at AMI Labs.

📍 NYC
 🗓️ Nov 30 to Dec 1
ai-dev.deeplearning.aitVBz

Just. Keep. Building.

💬6🔄16❤️153👀11894📊28

⚡ Powered by xgo.ing

🧭In this week's letter from Andrew Ng: AI improves fastest on tasks you can verify. Judgment tasks ...

DeepLearning.AI (@DeepLearningAI) — Fri, 16 Oct 2026 20:35:13 GMT

🧭In this week's letter from Andrew Ng: AI improves fastest on tasks you can verify. Judgment tasks are harder, and it's easy to overgeneralize progress in math and code to the rest of human activity.

Also inside:

 🤖Claude Haiku 5.5 and Sonnet 5.5
 🇪🇺Mistral Large 4
 💻Computers for local AI
 📊Causaldeeplearning.ai/the-batch/issu…qo#DeepLearningAIr#AIEngineeringn#MachineLearningearning

💬13🔄9❤️51👀7346📊21

⚡ Powered by xgo.ing

1/ 📰Missed a few days of AI news? Here's what happened in this week's Data Points 👇 2/ 🪶Claude H...

DeepLearning.AI (@DeepLearningAI) — Fri, 16 Oct 2026 00:10:07 GMT

1/ 📰Missed a few days of AI news? Here's what happened in this week's Data Points 👇

2/ 🪶Claude Haiku 5.5: $0.10/$0.50 per million tokens for prompts up to 100K, ~90% cheaper than Haiku 4.5. Super fast and highly capable.
3/ 🎯Microsoft-Decision-1: calibrated probabilities over fixed options in one pass. Built for classification, routing, agent gating. This decision model costs $0.042 per million input tokens, and output is free. Check independent benchmarks to compare it with Jev and other decision models.
4/ 🔌Meta's Muse Wonder: Comparable with top models from Google and OpenAI, costs $4/$20 per million tokens. No full safety report yet.
5/ 📄Gemini 4 Argon: the official wide release has a 1M token output limit, up from 64K. Input and output share the window. $2/$10 intro pricing (per million tokens of input/output) until Nov 30.
6/ 🐍Python 3.15 is out, but 3.10 is end of life. Update your projects to support the new features where you can (3.11 remains a good backwards-compatible option).

7/ 📬Subscribe to our Data Points newsletter for authoritative, short-form, real-time Adeeplearning.ai/the-batch/tag/…hl#DeepLearningAIa#AIEngineeringi#Python#Python

Your browser does not support the video tag.

🔗 View on Twitter

💬14🔄13❤️81👀10015📊26

⚡ Powered by xgo.ing

🧰 Picking the most relevant tools one by one leaves gaps. HYSET scores tools as a set. 📊 Recall@5...

DeepLearning.AI (@DeepLearningAI) — Thu, 15 Oct 2026 16:00:06 GMT

🧰 Picking the most relevant tools one by one leaves gaps. HYSET scores tools as a set.

📊 Recall@5: 88.6% vs. 81.4%
✅ Tasks resolved: 69.9% vs. 61.8%

Full story in our weekly newsletter for AI news and research, The Batch hubs.la/Q04zXp-p0cF#DeepLearningAIg#AIAgentsn#AIEngineeringing

💬15🔄9❤️49👀5947📊20

⚡ Powered by xgo.ing

🦾 FLUX 3 Action, a video-first world-action model, ranks first on RoboLab-120’s simulations, with a...

DeepLearning.AI (@DeepLearningAI) — Wed, 14 Oct 2026 16:00:00 GMT

🦾 FLUX 3 Action, a video-first world-action model, ranks first on RoboLab-120’s simulations, with a success rate of 42.9%.
🎥 It was pretrained on more than 95% video.
🔧 It adapted to a new arm with about 200 demonstrations.
⚠️ It hasn’t been tested on real robot limbs at the independent RoboArena yet.

Full story in our weekly AI newsletter, The Batchhubs.la/Q04zXgPK0L4#DeepLearningAIn#Roboticst#OpenWeightsghts

💬16🔄6❤️53👀6422📊21

⚡ Powered by xgo.ing

🎯 Gemini 4 Argon has a 15% hallucination rate on AA-Omniscience, compared with 51% for GPT-6 Astra....

DeepLearning.AI (@DeepLearningAI) — Tue, 13 Oct 2026 16:00:00 GMT

🎯 Gemini 4 Argon has a 15% hallucination rate on AA-Omniscience, compared with 51% for GPT-6 Astra.
 📊 It ranks first on the Vals Index, reflecting its high performance in legal and other knowledge work. 
🔐 For now, only cybersecurity defenders in Google's Fairwind program can use it.

Full story in our weekly AI newsletter, The Batchhubs.la/Q04zX8YW04O#DeepLearningAIn#AIEngineeringr#Cybersecurityrity

💬21🔄31❤️399👀19014📊66

⚡ Powered by xgo.ing

📊 GPT-6.1 Sol: 52 on the AA Intelligence Index, at $0.72 per task. GPT-6 Astra: 53, at $3.26 per t...

DeepLearning.AI (@DeepLearningAI) — Mon, 12 Oct 2026 16:39:59 GMT

📊 GPT-6.1 Sol: 52 on the AA Intelligence Index, at $0.72 per task.
 GPT-6 Astra: 53, at $3.26 per task.

⏸️ OpenAI also canceled GPT-6.1 Astra’s release after the model showed deception in internal tests.

Full breakdown in The Batch �hubs.la/Q04zWKLz0HW#DeepLearningAIA#AIEngineeringn#AIAgentsts

💬8🔄34❤️148👀11680📊29

⚡ Powered by xgo.ing

🖥️ Agents don't just consume tokens for input and output like humans do with early chatbots. Agents...

DeepLearning.AI (@DeepLearningAI) — Sat, 10 Oct 2026 15:00:00 GMT

🖥️ Agents don't just consume tokens for input and output like humans do with early chatbots. Agents use computers: searching, storing, analyzing, transacting, at a scale no person matches.

In this week's Andrew's Letter in The Batch, Andrew Ng explains why that means we need much more infrastructure, and faster tools, not just faster models. 🏗️

hubs.ly/Q04zR8n20nG#DeepLearningAIg#AIEngineeringi#AIAgentsnts

💬16🔄11❤️81👀10884📊27

⚡ Powered by xgo.ing

🏗️ In this week’s letter from Andrew Ng in The Batch: One of his agents makes 5,000 to 10,000 web s...

DeepLearning.AI (@DeepLearningAI) — Fri, 09 Oct 2026 19:59:31 GMT

🏗️ In this week’s letter from Andrew Ng in The Batch: One of his agents makes 5,000 to 10,000 web searches a day. Agents will need far more data centers.

Also inside:

🤖 GPT-6.1 Sol
⚖️ Gemini 4 Argon
🦾 FLUX 3 Action
🧰 HYSEThubs.la/Q04zPZP60i2#DeepLearningAIi#AIEngineeringe#AIAgentsgents

💬7🔄7❤️58👀7464📊14

⚡ Powered by xgo.ing

A new agentic research model and harness called AREX checks its answers requirement by requirement, ...

DeepLearning.AI (@DeepLearningAI) — Fri, 09 Oct 2026 00:00:00 GMT

A new agentic research model and harness called AREX checks its answers requirement by requirement, keeps what's verified, and researches only the gaps. 📰✅

📊 82.5% BrowseComp, 82.0 F1 WideSearch-en
📈 Harness alone: up to +10 pts
🧠 Fine tuned 4B beat untuned 35B on 5 of 6 benchmarhubs.la/Q04ztJKG0aL#DeepLearningAIn#AIAgentse#LLMsLLMs

💬13🔄30❤️165👀11783📊46

⚡ Powered by xgo.ing

This assistant remembers where you left your keys. No network connection. No remote server. Build ...

DeepLearning.AI (@DeepLearningAI) — Thu, 08 Oct 2026 20:35:59 GMT

This assistant remembers where you left your keys. No network connection. No remote server. 

Build one yourself in a course built in partnership with Qdrant and taught by Dylan Couzon. 

👉 Enroll for free:hubs.la/Q04zGYrF0C
#AII#VectorSearchh#AIEngineeringg

Your browser does not support the video tag.

🔗 View on Twitter

💬4🔄13❤️62👀8623📊18

⚡ Powered by xgo.ing

Missed a few days of AI news? Here’s what happened in this week’s Data Points 🧵 🔹Google is back a...

DeepLearning.AI (@DeepLearningAI) — Thu, 08 Oct 2026 16:00:00 GMT

Missed a few days of AI news? Here’s what happened in this week’s Data Points 🧵

🔹Google is back at the frontier. Gemini 4 Argon ties GPT-6 Astra at 53 on the Artificial Analysis Intelligence Index, at about 60% of the cost per task.
🔹Europe closes the gap. Mistral Large 4, a 1T-parameter model with open weights coming late October, is now the most intelligent model built outside the US and China.
🔹Reflection AI’s open-weight Beam claims 3–4x less compute to reason than comparable open models.  🔹OpenAI published a batch of new math results from an unreleased model, with proofs formalized in Lean.
🔹Microsoft’s MAI-Transcribe-2-Streaming ranks #1 of 38 for streaming speech-to-text accuracy.  
🔹Google’s EmbeddingGemma 2 runs multimodal search on a phone; Cohere’s Embed 5 targets enterprise RAG.
🔹Meta’s Muse agent and your friends’ data, OpenAI’s opt-in text watermarks, arXiv’s new submission caps, and which AI subscriptions give the most value per dollar.

Read ithubs.la/Q04ztBjc0RaFlTN6HH

💬21🔄9❤️96👀10871📊31

⚡ Powered by xgo.ing

Agents read more than they write, so DeepSeek shrank what they remember. Read the technical breakdow...

DeepLearning.AI (@DeepLearningAI) — Wed, 07 Oct 2026 23:59:59 GMT

Agents read more than they write, so DeepSeek shrank what they remember. Read the technical breakdown in this week's issue of The Batch. 📰🗜️

📉 890 bytes of cache per token, 437x smaller than DeepSeek-V1
⚡ +25% compute per output token from 4K to 1M input
🏆 Flash beats V4-Pro: 39 vs 36 on AA Index, $0.27 vs $0.67/tahubs.la/Q04ztt000TC#DeepLearningAIn#LLMsL#AIAgentsents

💬11🔄21❤️121👀12055📊32

⚡ Powered by xgo.ing

Most voice assistants work like a relay race: speech becomes text, text goes to a model, the answer ...

DeepLearning.AI (@DeepLearningAI) — Wed, 07 Oct 2026 15:33:41 GMT

Most voice assistants work like a relay race: speech becomes text, text goes to a model, the answer becomes speech again. Every handoff adds a pause. ⏱️

Speech-to-speech models skip the relay. Google's new Gemini 3.8 Live models listen, reason, and respond in one system.

🎯 The Extended Thinking version ranks first on Artificial Analysis' Speech to Speech Index
🗣️ The standard version ranks second in blind live conversations judged by people
💰 The standard version costs $0.84 per hour of input audio, the lowest in the index

Both models also take in image and video input. Picture asking an assistant for help with whatever is on your screen, and it simply answers. 📱

Read the full story in The Batchubs.la/Q04ztmlL0zb#DeepLearningAIi#VoiceAgentsg#AIs #AI

💬15🔄10❤️78👀10896📊24

⚡ Powered by xgo.ing

This assistant remembers where you left your keys. No network connection. No remote server. Build ...

DeepLearning.AI (@DeepLearningAI) — Wed, 07 Oct 2026 01:00:01 GMT

This assistant remembers where you left your keys. No network connection. No remote server. 

Build one yourself in a course built in partnership with Qdrant and taught by Dylan Couzon. 

👉 Enroll for free:hubs.la/Q04zn4_N0y
#AII#VectorSearchh#AIEngineeringg

💬10🔄16❤️151👀11761📊35

⚡ Powered by xgo.ing

A model trained only to pass tests learned to add unrequested code and let errors pass silently. 🧪 ...

DeepLearning.AI (@DeepLearningAI) — Tue, 06 Oct 2026 20:34:11 GMT

A model trained only to pass tests learned to add unrequested code and let errors pass silently. 🧪

Xiaomi fixed it by multiplying each test result by quality checklist scores.

Result: MiMo-V2.6-Pro RL leads open weights models on Artificial Analysis’ Intelligence Index (46). 📊

How it works hubs.la/Q04zmF35067#DeepLearningAIg#OpenWeightsh#RL#RL

💬21🔄4❤️85👀11715📊30

⚡ Powered by xgo.ing

An open model nearly matches Claude Mythos on cybersecurity capabilities: GLM-5.3 solves 12% and Cla...

DeepLearning.AI (@DeepLearningAI) — Sun, 04 Oct 2026 02:59:59 GMT

An open model nearly matches Claude Mythos on cybersecurity capabilities: GLM-5.3 solves 12% and Claude Mythos 14% of ExploitBench exploit tasks, per Anthropic. Just $20.40 in tokens found a recent security exploit in Google Chrome. 💸

In this week’s letter, Andrew Ng has a different take from those who worry about these capabilities in the wrong hands: This is an engineering problem, and defenders hold the long term edge 🛡️

hubs.la/Q04z3MJH0eF#DeepLearningAIg#Cybersecurityi#OpenWeightshts

💬21🔄14❤️123👀12411📊37

⚡ Powered by xgo.ing

This week in The Batch, Andrew's Letter covers how open weights model GLM-5.3 nearly matched Claude ...

DeepLearning.AI (@DeepLearningAI) — Fri, 02 Oct 2026 14:59:12 GMT

This week in The Batch, Andrew's Letter covers how open weights model GLM-5.3 nearly matched Claude Mythos at exploiting vulnerabilities, 12% vs. 14%.

Also inside:

 🧪 Xiaomi's new open weights leader
 🎙️ Gemini 3.8 Live
 💾 DeepSeek-V4.1-Flash
 🔁 AREX agentshubs.la/Q04z20mv0Hm#DeepLearningAIi#AIEngineeringe#OpenWeightsights

💬14🔄10❤️86👀12242📊28

⚡ Powered by xgo.ing

Andrew Ng's AI Engineering Skills Map shows what to learn. AI Dev is where you hear from the people ...

DeepLearning.AI (@DeepLearningAI) — Thu, 01 Oct 2026 16:00:25 GMT

Andrew Ng's AI Engineering Skills Map shows what to learn. AI Dev is where you hear from the people who built it in the real world. Keynotes from Andrew Ng and Yann LeCun. Engineers from Hugging Face, Google DeepMind, and BlackRock.

🗓️ Nov 30 to Dec 1
📍 New York City 
🎟️ Grab early bird tickets at $599 while they last

Get your tickehubs.la/Q04yWnyV0FNN#DeepLearningAIg#AIEngineeringi#MachineLearninging

💬9🔄13❤️105👀11731📊27

⚡ Powered by xgo.ing

The Data Engineering Professional Certificate is now available on DeepLearningAI. Across four cours...

DeepLearning.AI (@DeepLearningAI) — Tue, 29 Sep 2026 15:30:31 GMT

The Data Engineering Professional Certificate is now available on DeepLearningAI.

Across four courses, design and build the systems that generate, ingest, store, transform, and serve data, including batch and streaming pipelines on AWS and open-source tools.

Built in partnership with @awscloud and taught by Joe Reis, co-author of Fundamentals of Data Engineering.

Enroll for free: hubs.la/Q04yxqxW0

Your browser does not support the video tag.

🔗 View on Twitter

💬4🔄39❤️271👀12671📊64

⚡ Powered by xgo.ing

Everyone knows that applying rigid testing requirements to early stage AI projects causes them to st...

DeepLearning.AI (@DeepLearningAI) — Sat, 26 Sep 2026 15:30:00 GMT

Everyone knows that applying rigid testing requirements to early stage AI projects causes them to stall… but some companies do it anyway.

Andrew Ng explains why AI engineering tactics must adapt to the stage of the project, not just for speed, but for reliability.

Read about how to calibrate your approach:
🛠️ Scaling evaluation pipelines and metrics
🛠️ Selecting software architecture for scale
🛠️ Structuring product feedback loops

Read the full letter in The Batchubs.la/Q04ymLtP0p2#AI##MachineLearningi#TechNewse#DeepLearningAIgAI

💬14🔄13❤️77👀12522📊28

⚡ Powered by xgo.ing

Early stage AI projects don’t need rigid testing, but mature products do. Andrew Ng explains why AI ...

DeepLearning.AI (@DeepLearningAI) — Fri, 25 Sep 2026 21:11:36 GMT

Early stage AI projects don’t need rigid testing, but mature products do. Andrew Ng explains why AI engineering tactics must adapt to the project lifecycle.

Also in this week's The Batch:
🛠️ Claude Opus 5.5 performance metrics
🛠️ Jev classification model goes viral
🛠️ Devin Fusion lead and sidekick models in one harness
🛠️ Message Passing for decentralized agents

Read the full ishubs.la/Q04ymKnv0Oy#AIEngineeringr#MachineLearningn#DeepLearningAIngAI

💬8🔄12❤️104👀12022📊27

⚡ Powered by xgo.ing

Long contexts cause AI agents to forget early mistakes. Meta AI paired primary action agents with d...

DeepLearning.AI (@DeepLearningAI) — Thu, 24 Sep 2026 16:47:08 GMT

Long contexts cause AI agents to forget early mistakes.

Meta AI paired primary action agents with dedicated memory agents to fix context rot:

📝 Keeps structured notes on tools and past errors
🎯 Injects short reminders only at crucial moments
📈 Raised Claude Sonnet 4.5 benchmarks from 37.6% to 45.9%

Read the full technical analysishubs.la/Q04yf27q04F#DeepLearningAIg#AIAgentsn#LLMsLMs

💬21🔄20❤️156👀12789📊50

⚡ Powered by xgo.ing

Can you distill your way to a frontier model? 🧠 Anthropic's latest report highlights proxy query r...

DeepLearning.AI (@DeepLearningAI) — Wed, 23 Sep 2026 13:30:00 GMT

Can you distill your way to a frontier model? 🧠

Anthropic's latest report highlights proxy query routing supporting massive distillation campaigns across commercial platforms.

🚨 Unauthorized proxies routed user prompts to Claude APIs
🛡️ This type of query forwarding creates severe data privacy risks

Read our full breakdowhubs.la/Q04x_m800NE#DeepLearningAIg#LLMsL#AISecurityity

💬12🔄10❤️78👀11838📊24

⚡ Powered by xgo.ing

10,000 AI agents spent 88 hours tackling Navier-Stokes equations in Lean. The resulting controversy ...

DeepLearning.AI (@DeepLearningAI) — Tue, 22 Sep 2026 13:30:05 GMT

10,000 AI agents spent 88 hours tackling Navier-Stokes equations in Lean. The resulting controversy teaches vital lessons to AI developers.

🧩 Agents can formalize complex mathematical proofs at massive scale
🧠 Human evaluation remains essential to interpret why proofs work
🔒 Enterprise data privacy and zero-data retention settings are mandatory

Read our full technical analysihubs.la/Q04x_jNp09D#DeepLearningAIg#AIAgentsn#AISecurityity

💬21🔄41❤️224👀14037📊59

⚡ Powered by xgo.ing

Prompt injection defenses shouldn't rely solely on a model’s own training. Meta's Muse agent assume...

DeepLearning.AI (@DeepLearningAI) — Mon, 21 Sep 2026 16:20:08 GMT

Prompt injection defenses shouldn't rely solely on a model’s own training.

Meta's Muse agent assumes the model will be tricked; instead, it builds security at the OS level.

🔑 Model never handles real credentials
🛡️ Tools run in isolated Linux containers
🛑 Independent gatekeeper verifies outbound calls

Read the full analysishubs.la/Q04xZx5006V#DeepLearningAIg#AIAgentsn#AISecurityity

💬24🔄19❤️163👀12046📊52

⚡ Powered by xgo.ing

Massive agent swarms define this week in AI. Here is what we covered in our twice-weekly shortform ...

DeepLearning.AI (@DeepLearningAI) — Sun, 20 Sep 2026 12:30:00 GMT

Massive agent swarms define this week in AI.

Here is what we covered in our twice-weekly shortform newsletter Data Points:

🧮 OpenAI used 10,000 agents to show that the Navier-Stokes equations break down, sparking a debate on prompt data privacy and the role of AI in mathematics.

📉 DeepSeek V4.1 Flash introduced a brand-new architecture for cheaper long-context workloads.

Subscribe to Data Points to get technical insights delivered twice a weekhubs.la/Q04xTwMP0Tz#DeepLearningAIA#MachineLearningn#AIAgentsts

💬15🔄5❤️85👀12080📊26

⚡ Powered by xgo.ing

In this week’s letter, Andrew Ng addresses the calls from AI companies and recently departed researc...

DeepLearning.AI (@DeepLearningAI) — Sat, 19 Sep 2026 13:30:00 GMT

In this week’s letter, Andrew Ng addresses the calls from AI companies and recently departed researchers for a slowdown on development. Recent reports highlighted a swarm of 1,200 OpenAI agents compromising Hugging Face’s system. But the actual breach stemmed from inadequate sandboxing and monitoring processes. Companies need to stop assigning responsibility to runaway AI agents when it’s poor human decisions that lead to big mistakes.

Read Andrew’s full argument against AI doomsayers in The Batch. hubs.la/Q04xTv-20

💬14🔄5❤️85👀12924📊24

⚡ Powered by xgo.ing

🛑 The latest AI doom hype is overblown. In The Batch, Andrew Ng breaks down why sloppy sandboxing,...

DeepLearning.AI (@DeepLearningAI) — Fri, 18 Sep 2026 16:29:04 GMT

🛑 The latest AI doom hype is overblown.

In The Batch, Andrew Ng breaks down why sloppy sandboxing, not runaway software, is the true root of recent cybersecurity incidents. Blaming too-powerful AI agents for a predictable hack is like blaming your own hammer when you foolishly break a window.

Our team also breaks down the week’s most important AI news and research, including the dispute over OpenAI’s breakthrough math proof, Anthropic’s accusations against Moonshot, DeepSeek, and Alibaba, and Meta’s security protocols for its latest agent.

Read the full analysis at The Batch:hubs.la/Q04xSL9J0m 
#DeepLearningAII#Cybersecurityy#LLMss

💬16🔄3❤️69👀12213📊24

⚡ Powered by xgo.ing

The traditional developer role is evolving fast. With modern AI tools, the traditional lines betwee...

DeepLearning.AI (@DeepLearningAI) — Thu, 17 Sep 2026 12:57:59 GMT

The traditional developer role is evolving fast.

With modern AI tools, the traditional lines between developer, product manager, and designer are blurring. Today's most effective AI engineers don't just implement specs, they actively shape the build.

To help developers master this shift, we’ve mapped out the essential skills required to take greater ownership of the development process.

Master these core skills to accelerate your workflow and deliver maximum impact:

🔄 Driving the Build Loop: Rapidly drive the build, feedback and decision loop by making informed decisions based on product vision, project stage, technical feasibility, risks, effort and budget.
🎯 Making Product Decisions: Cultivate deep user empathy and business sense to confidently steer product direction and design when a spec isn't provided.
🗣️ Communicating and leading: Act as a technical guide for your broader organization, aligning cross-functional teams (like marketing and legal) and explaining what is technically feasible.
🚀 High-Agency Ownership: Spot opportunities and deliver solutions despite ambiguity. Measure success by the value you create, not just tasks completed.

Read Andrew Ng's full breakdown on shaping the build hehubs.la/Q04xKz950Myw#DeepLearningAIn#AIEngineeringr#AI#AI

💬11🔄35❤️171👀12950📊51

⚡ Powered by xgo.ing

Context limits and information loss pose huge problems for long-running AI agents. 🛑 A new tool fo...

DeepLearning.AI (@DeepLearningAI) — Wed, 16 Sep 2026 19:30:00 GMT

Context limits and information loss pose huge problems for long-running AI agents. 🛑

A new tool for better context management is helping developers optimize memory and cut API costs. Efficient information retrieval is a key skill for production AI.

Read the full analysis in The Batch: hubs.la/Q04xyjFN0t  📖#DeepLearningAIA#AIAgentst#MachineLearningng

💬15🔄22❤️129👀12540📊45

⚡ Powered by xgo.ing

Transcription battles are heating up! 🔥 While generative text models dominate the conversation, sp...

DeepLearning.AI (@DeepLearningAI) — Wed, 16 Sep 2026 13:29:59 GMT

Transcription battles are heating up! 🔥

While generative text models dominate the conversation, speech recognition is having its own moment. Google, Meta, and Microsoft are actively fighting for the top spot with powerful new model releases.

Learn what this means for your AI builds in The Batch:hubs.la/Q04xyhnw0g  📖#DeepLearningAIA#SpeechRecognitiono#MachineLearningng

💬6🔄7❤️68👀13926📊16

⚡ Powered by xgo.ing

Claude Fable 5.1 held on to the number one spot on Artificial Analysis’ Intelligence Index v4.2, and...

DeepLearning.AI (@DeepLearningAI) — Tue, 15 Sep 2026 14:30:37 GMT

Claude Fable 5.1 held on to the number one spot on Artificial Analysis’ Intelligence Index v4.2, and tied with OpenAI’s new model on the updated benchmarks 🏆.

What you need to know:
📊 Scores 57 on the v4.2 index, edging out GPT 6 Astra.
🔬 Achieves 52.6% on Terminal Bench Science 0.1 for agentic research.
💰 Saves costs for repeated agentic workflows via cheaper cache reads.

Get the full breakdown in The Bathubs.la/Q04xy0h-0HknC #DeepLearningAIi#Anthropicr#AIAgentsgents

💬11🔄7❤️64👀12302📊18

⚡ Powered by xgo.ing

GPT-6 Astra tops the ARC-AGI-3 leaderboard while cutting token costs. Here is what matters for devel...

DeepLearning.AI (@DeepLearningAI) — Mon, 14 Sep 2026 15:31:54 GMT

GPT-6 Astra tops the ARC-AGI-3 leaderboard while cutting token costs. Here is what matters for developers: 🚀

⚡ Tied with Claude Fable 5.1 on Artificial Analysis’ Intelligence Index
⚡ Asynchronous tool calls for parallel execution
⚡ Retained reasoning memory across API calls

Efficient context management is essential to scaling agents.

Read our full analysis in The Batch:hubs.la/Q04xp3NY0O  📖#DeepLearningAIA#AIAgentst#MachineLearningng

💬19🔄10❤️97👀12879📊30

⚡ Powered by xgo.ing

In his latest letter in The Batch, Andrew Ng explains why the best AI engineers do not just write co...

DeepLearning.AI (@DeepLearningAI) — Sat, 12 Sep 2026 13:30:00 GMT

In his latest letter in The Batch, Andrew Ng explains why the best AI engineers do not just write code to spec. They shape the build. 🧵

Four core skills Andrew highlights to level up your engineering workflow:

🔄 Drive the build loop | Prototype fast and iterate on real user feedback.
💡 Make product decisions | Pair technical feasibility with business sense and user empathy.
📢 Communicate broadly | Align product goals across marketing, legal, and finance.
⚡ High agency ownership | Spot problems and execute solutions without waiting for top-down direction.

Read Andrew's full perspective in The Bathubs.la/Q04xg-090ENMC#DeepLearningAIn#AIEngineeringr#TechLeadershipship

💬19🔄19❤️169👀14261📊54

⚡ Powered by xgo.ing

The skills required to be an engineer in the age of AI are changing fast. Here is your quick summary...

DeepLearning.AI (@DeepLearningAI) — Fri, 11 Sep 2026 14:32:07 GMT

The skills required to be an engineer in the age of AI are changing fast. Here is your quick summary of this week's issue of The Batch: 🧵

1️⃣ Shaping the Build
AI engineering requires more than using AI to write code. To drive impact, developers must master:
• Fast build-and-feedback loops
• Product and design judgment
• Stakeholder communication
• High agency ownership

2️⃣ GPT-6 Astra
OpenAI launched GPT-6 Astra with 1M+ input tokens and 5 reasoning levels. Benchmark data on ARC AGI 3 and other tasks shows higher per token rates can yield lower total cost per task due to better efficiency.

3️⃣ Claude Fable 5.1
Anthropic updated Fable 5.1, tying for top marks on the Artificial Analysis Intelligence Index v4.3. The model loosens some restrictions on cybersecurity tasks and is less wordy.

4️⃣ Transcription Wars
Google, Meta, and Microsoft released new speech to text models. Gemini 3.5 Transcribe, Muse Voice Transcribe, and MAI-Transcribe 2 all achieved word error rates below 4%.

5️⃣ SelfCompact
Johns Hopkins and Apple published SelfCompact, a method that uses explicit rubrics to prune LLM context history without parameter updates or fine-tuning.

6️⃣ Events
DeepLearningAI is hosting another installment of our AI Dev developer event in NYC on November 30 and December 1. Early bird tickets are available now!

Subscribe to read the full technical analyses: ⚡hubs.la/Q04xfcHh0k
#DeepLearningAII#AIEngineeringg#LLMss

💬11🔄24❤️136👀12493📊40

⚡ Powered by xgo.ing

Coding agents are transforming how we build software. Developers are moving from writing raw code to...

DeepLearning.AI (@DeepLearningAI) — Wed, 09 Sep 2026 20:54:07 GMT

Coding agents are transforming how we build software. Developers are moving from writing raw code to defining specs, designing architecture, and evaluating agent-generated results.

To help developers master this shift, we’ve mapped out Pillar 3 of the AI Engineering Skills Map: Using Coding Agents. Focus on these fundamental skills to effectively steer agents and get more done: 🧵👇

🧭 Directing the workflow: Strategically balance human oversight and agent autonomy across research, planning, architecture design, and task breakdown.
🤖 Enabling agent autonomy: Choose autonomy level of agent workflows, manage evolving agent context, and orchestrate parallel agent runs while limiting risk of damage.
✅ Reviewing the work: Verify uncertain agent outputs using automated tests, agentic code review, and llm-as-a-judge. Extend this oversight into production with active monitoring and incident management.
🛠️ Customizing the agent and its environment: Extend and customize the agents with skills, hooks, plug-ins, and MCP servers. Maintain their standing context, persist state across sessions, and capture its learnings over time.
🧠 Coding agent foundations: Understand how agents handle search and retrieval, manage their context windows, and make tool calls, so you can recognize failure modes early and intervene when they go off-track.

Read the full breakdown by Andrehubs.la/Q04x53Xh0bz#DeepLearningAIn#AIEngineeringe#CodingAgentsAgents

💬38🔄35❤️231👀16539📊89

⚡ Powered by xgo.ing

General AI may not be enough for highly regulated fields. ⚖️🏦 📰 Law, news, and finance are rapidl...

DeepLearning.AI (@DeepLearningAI) — Wed, 09 Sep 2026 13:51:52 GMT

General AI may not be enough for highly regulated fields. ⚖️🏦

📰 Law, news, and finance are rapidly adopting custom models. 
🎯 Retraining open models on proprietary data ensures higher accuracy and strict instruction-following. 
🚀 Specialized AI is an important future paradigm for enterprise tech. 

Dive into the details in The Bathubs.la/Q04x1F3G0QE8#DeepLearningAIn#LLMsL#EnterpriseAIseAI

💬11🔄14❤️98👀11596📊28

⚡ Powered by xgo.ing

OpenAI and Anthropic just rewrote their enterprise data policies. 🚨 🔹 Anthropic now lets business...

DeepLearning.AI (@DeepLearningAI) — Tue, 08 Sep 2026 20:00:01 GMT

OpenAI and Anthropic just rewrote their enterprise data policies. 🚨

🔹 Anthropic now lets businesses using top models like Claude Fable 5.1 keep data on their own servers for 30 days.
🔹 OpenAI promises Zero Data Retention with a new system of safety processing.
🔹 Both use automated systems to flag misuse, but their systems lack technical transparency.

Dive into the privacy details in The Bathubs.la/Q04wXpvq0zO#DeepLearningAIn#EnterpriseAIs#DataPrivacyvacy

💬7🔄9❤️110👀12400📊25

⚡ Powered by xgo.ing

The viral "Ox Alpha" model is officially GLM-5.3-Flash from Zai. 🔍 📊 320B parameters with 18B act...

DeepLearning.AI (@DeepLearningAI) — Tue, 08 Sep 2026 13:56:33 GMT

The viral "Ox Alpha" model is officially GLM-5.3-Flash from Zai. 🔍

📊 320B parameters with 18B active per token
⚡ Hybrid architecture mixing linear and sparse attention
💰 Leading performance on real world tasks from GDPval AA v2 at just $0.09 per task

The best part? Zai ran the massive free preview entirely on China-made hardware, proving smart memory optimization can overcome hardware limits. 🛠️

Dive into the architecture details in The Bathubs.la/Q04wWZcM05e#DeepLearningAIn#LLMsL#OpenWeightsghts

💬11🔄4❤️72👀11553📊18

⚡ Powered by xgo.ing

🛑 Stop letting your coding agents run autonomously for hours. It is costly and often ineffective. ...

DeepLearning.AI (@DeepLearningAI) — Sun, 06 Sep 2026 15:17:54 GMT

🛑 Stop letting your coding agents run autonomously for hours. It is costly and often ineffective.

Andrew Ng just broke down the real workflows top AI practitioners use. The secret is skilled human judgment, highly iterative planning, and frequent output verification. 🧵👇

Most of your time can now be spent on architecture and writing specs, not writing individual lines of code. You must learn to direct agents’ workflow, calibrate their autonomy, and build robust testing regimes.

Read Andrew's full letter to study the five foundational skills of using coding agenthubs.la/Q04wPQ6v0XZd#DeepLearningAIg#AIEngineeringi#CodingAgentsn#DeveloperToolsols

💬29🔄52❤️401👀22777📊121

⚡ Powered by xgo.ing

⚡ Coding agent workflows, enterprise privacy updates, and open weight models worth studying. Highli...

DeepLearning.AI (@DeepLearningAI) — Fri, 04 Sep 2026 17:38:47 GMT

⚡ Coding agent workflows, enterprise privacy updates, and open weight models worth studying.

Highlights from this week in The Batch:

🤖 Andrew Ng explains how using coding agents requires its own fundamental skill set.
🔐 OpenAI and Anthropic unveiled new enterprise data retention policies.
⚡ Zai released GLM-5.3-Flash, a cost-efficient, open weights, multimodal system.
⚖️ Thomson Reuters launched a 397B parameter model trained specifically for work in law, finance, and news.

👇 Read the full issuhubs.la/Q04wLJr50FhA#DeepLearningAIg#AIEngineeringi#LLMsLMs

💬1🔄13❤️71👀12282📊16

⚡ Powered by xgo.ing

One good AI image is easy. Consistent quality at scale is an evaluation problem. Build a UI design ...

DeepLearning.AI (@DeepLearningAI) — Fri, 04 Sep 2026 13:30:26 GMT

One good AI image is easy. Consistent quality at scale is an evaluation problem.

Build a UI design agent that self-critiques and iterates based on brand guidelines.

Enroll in our new free course with @GoogleCloud: hubs.la/Q04vs40m0#AIAgents#GenAI#GoogleCloud

Your browser does not support the video tag.

🔗 View on Twitter

💬2🔄9❤️72👀12059📊17

⚡ Powered by xgo.ing

🗑️ AI agents need better garbage collection. Xiaohongshu researchers built Self-GC, using a planne...

DeepLearning.AI (@DeepLearningAI) — Thu, 03 Sep 2026 13:58:51 GMT

🗑️ AI agents need better garbage collection.

Xiaohongshu researchers built Self-GC, using a planner LLM to decide which context tokens to keep, fold, or prune. In tests, it retained necessary details 84.85 percent of the time compared to just 54.55 percent for standard methods.

Master agent memory management:hubs.la/Q04wy8ML0N
#DeepLearningAII#AIAgentss#LLMss

💬19🔄31❤️203👀12526📊64

⚡ Powered by xgo.ing

🛠️ DeepSeek V4 Pro 0813 is out, but just as big of a story may be the company’s open source evaluat...

DeepLearning.AI (@DeepLearningAI) — Wed, 02 Sep 2026 22:30:00 GMT

🛠️ DeepSeek V4 Pro 0813 is out, but just as big of a story may be the company’s open source evaluation harness.

DeepSeek Harness logs every tool call, system prompt, and subagent schedule. Developers can now reproduce performance instead of relying on closed testing environments. And they can easily study, fork, or remake their own harnesses to boot.

Read more in The Batch:hubs.la/Q04wjYXx0q
#DeepLearningAII#OpenSourcee#Developerss

💬5🔄1❤️56👀12134📊13

⚡ Powered by xgo.ing

⚡ Top AI companies think inference speed is an architectural requirement worth paying for. OpenAI a...

DeepLearning.AI (@DeepLearningAI) — Wed, 02 Sep 2026 14:49:55 GMT

⚡ Top AI companies think inference speed is an architectural requirement worth paying for.

OpenAI and Cerebras demonstrated GPT 5.6 Sol running at 750 tokens per second.

Google released Gemini 3.7 Flash averaging 330 tokens per second.

Nvidia launched Nemotron 3.5 Lightning with NeMo Switchyard for dynamic step routing.

Faster throughput and lower latency alleviate developer context switching and power real-time agentic workflows.

Read the complete breakdown in The Batch: 📖
#DeepLearningAII#AII#TechNewss

💬7🔄6❤️74👀11836📊18

⚡ Powered by xgo.ing

Coding agents can write functional code, but relying on "vibe coding" without knowing core software ...

DeepLearning.AI (@DeepLearningAI) — Tue, 01 Sep 2026 22:59:41 GMT

Coding agents can write functional code, but relying on "vibe coding" without knowing core software engineering fundamentals can compromise long-term system reliability, security, and extensibility.
We’ve mapped out Pillar 2 of the AI Engineering Skills Map: Software Engineering Fundamentals to help you bridge the gap.

To build production-ready full-stack applications, focus on building these foundational skills:

🌐 Building Full-Stack Applications
🗄️ Managing Data
📐 Designing System Architectures
🛡️ Making Systems Secure and Reliable
🚀 Scaling and Operating in Production

Master these to steer your agents effectively.

Read the breakdown from Andrew Ng hhubs.la/Q04wbD4h08#AIEngineeringe#SoftwareArchitecturec#BuildWithAIithAI

💬33🔄46❤️346👀19110📊124

⚡ Powered by xgo.ing

⚡ Top AI companies think inference speed is an architectural requirement worth paying for. OpenAI a...

DeepLearning.AI (@DeepLearningAI) — Tue, 01 Sep 2026 18:46:34 GMT

⚡ Top AI companies think inference speed is an architectural requirement worth paying for.

OpenAI and Cerebras demonstrated GPT 5.6 Sol running at 750 tokens per second.

Google released Gemini 3.7 Flash averaging 330 tokens per second.

Nvidia launched Nemotron 3.5 Lightning with NeMo Switchyard for dynamic step routing.

Faster throughput and lower latency alleviate developer context switching and power real-time agentic workflows.

Read the complete breakdown in The Batch: hubs.la/Q04w6R0y0 📖
#DeepLearningAII#AII#TechNewss

💬8🔄3❤️69👀9525📊16

⚡ Powered by xgo.ing

💻 Z .ai's GLM-5.3 just hit 84.5% on the CyberGym vulnerability benchmark, beating top proprietary m...

DeepLearning.AI (@DeepLearningAI) — Tue, 01 Sep 2026 13:32:27 GMT

💻 Z .ai's GLM-5.3 just hit 84.5% on the CyberGym vulnerability benchmark, beating top proprietary models, a huge gain over the performance of its predecessor GLM-5.2.

The kicker?Z.aid’s AI engineers did it purely through fine-tuning and optimization of the model’s agentic capabilities, without changing the base model. The model grew so capable at finding and targeting potential exploits thatZ.aid held back the open weights for safety testing.

Read the full analysis in The Batch:hubs.la/Q04w3GkF0A 📖#DeepLearningAIA#Cybersecurityt#LLMsMs

💬4🔄4❤️118👀11773📊18