AI Engineer(@aiDotEngineer)

🆕 Live now: our entire AI x Graphs Track! @emileifrem, CEO, Neo4j @yoheinakajima, Managing Partner...

AI Engineer (@aiDotEngineer) — Thu, 23 Jul 2026 16:43:29 GMT

🆕 Live now: our entire AI x Graphs Track!

@emileifrem, CEO, Neo4j
@yoheinakajima, Managing Partner, Untapped Capital
@danielchalef, Founder & CEO, Zep AI
@le_james94, Head of DX, TwelveLabs
@coyle_frankp, Lecturer, UC Berkeley
Mike Phipps, Lead AI Engineer, Gates Foundation
Ritvik Pandya, Engineering Manager, JP Morgan Chase
Omri Bruchim, Engineering Group Manager, Monday
@steveonjava, VP of Developer Relations, Neo4j
@SQuoraishee, Staff Engineer, The New York Times
Joanne Song, Android Engineer, The New York Times
Subbiah Sethuraman & Abhilash Asokan, ZS Associates

full track drop below!

Peter Steinberger 🦞@steipete

Are we still talking loops or did we shift to graphs yet?

💬4🔄8❤️18👀3037📊8

🆕 Claude for Long-Horizon Tasks https://t.co/hr5Fg6yugz @RLanceMartin returns for the third(!) ti...

AI Engineer (@aiDotEngineer) — Wed, 22 Jul 2026 18:04:37 GMT

🆕 Claude for Long-Horizon Tasks
youtube.com/watch?v=9Qebvr…z

@RLanceMartin returns for the third(!) time to discuss the four core themes for effective agents and claws:

1. Decoupling Brain and Hands (3:21)
2. Using Verifiers (6:20)
3. Self-Learning and Memory (10:11)
4. Global/Org-Level Harnesses (16:08)

Welcome back Lance!

💬5🔄11❤️72👀8722📊30

Our first AI Engineer event in Shanghai China is on Nov 5 - 6, 2026, at the Hilton Shanghai Hongqiao...

AI Engineer (@aiDotEngineer) — Wed, 22 Jul 2026 16:46:40 GMT

Our first AI Engineer event in Shanghai China is on Nov 5 - 6, 2026, at the Hilton Shanghai Hongqiao.

Two tracks: Open Source Models / Infrastructure and Physical AI.

China and the US are building AI through different playbooks. It's worth getting engineers from both perspectives in the same room.

ai.engineer/shanghai/2026

Working with @StandupPartners for AIEi Shanghai

💬4🔄5❤️38👀3588📊13

Live now! @calcsam, CEO of @Mastra on how everything is claw

AI Engineer (@aiDotEngineer) — Tue, 21 Jul 2026 21:23:00 GMT

Live now! @calcsam, CEO of @Mastra on how everything is claw

Erika⚡️⚡️@brickywhat

"Don't give your engineers $20,000 a month of tokens before you fix your procurement process."

At @aiDotEngineer, I sat down with @calcsam, co-founder and CEO of @mastra. We talked about the agent spectrum, why TypeScript just passed Python (in his opinion), and what it actually takes to get agents into production.

00 what @mastra is
59 from Gatsby to two books on building agents
51 why agents belong in TypeScript
54 the token cost creep hitting teams
38 every harness will become a claw
42 the hot take: build agents in TypeScript

Your browser does not support the video tag.

💬0🔄4❤️18👀3433📊4

@Rames_Jusso @trq212 @liu8in @HeyGen https://t.co/9kpCiI7hpz

AI Engineer (@aiDotEngineer) — Tue, 21 Jul 2026 18:57:56 GMT

@Rames_Jusso@trq212@liu8in@HeyGenyoutube.com/watch?v=Cz4v1W…

💬1🔄1❤️15👀10574📊6

live now: @Rames_Jusso's GenMedia track keynote agreeing with @trq212's viral hit - HTML is All Ag...

AI Engineer (@aiDotEngineer) — Tue, 21 Jul 2026 18:57:48 GMT

live now: @Rames_Jusso's GenMedia track keynote agreeing with @trq212's viral hit - 

HTML is All Agents Need!

Fun fact - the AIEWF conf opener many loved was built with HyperFrames! It was a true pleasure to work with @liu8in and team @HeyGen to build it, and to have @joshua_xu_ join to help close out the show!

video link below

James Russo@Rames_Jusso

Free form speech as input seems to be the next focus for the big labs

OpenAI's bidirectional voice model GPT-Live shows this

I recently used this technique to iterate and practice a conference talk for @aiDotEngineer 

I'd practice into codex and provide feedback as asides

💬1🔄5❤️16👀7740📊6

the talk is https://t.co/EXwuEL7Sbm for those reading along

AI Engineer (@aiDotEngineer) — Tue, 21 Jul 2026 17:28:59 GMT

the talk is youtube.com/watch?v=bRnoEp… for those reading along

Sid@sidhusmart

@iristenteije@threepointone Yeah, I listened to your talk at @aiDotEngineer and the vision for personalized software is very interesting. But I haven't tried your approach yet because it's custom work that you do with clients at the moment?

💬0🔄1❤️1👀3465📊1

"Cost is now a first-class engineering constraint." 🆕 @barrnanas returns for the third annual Stat...

AI Engineer (@aiDotEngineer) — Tue, 21 Jul 2026 16:25:27 GMT

"Cost is now a first-class engineering constraint."

🆕 @barrnanas returns for the third annual State of AI Engineering, this time supported by @NotionHQ and @vercel!
youtube.com/watch?v=RGe6Ej…i

Some findings:
- generative images has 2x'ed in adoption
- audio/voice AI is the next highest adoption target 
- 87% of AIEs use multiple models, mixing closed and open weight
- 95% of teams use agents, with write access tripling since last year
- 67% of AIEs expect AGI in 5 years

💬3🔄3❤️17👀3199📊7

🆕Now playing on the Local AI track: https://t.co/8hMc0VB9Nv The Desktop Frontier — Ahmad Osman, O...

AI Engineer (@aiDotEngineer) — Tue, 21 Jul 2026 02:34:34 GMT

🆕Now playing on the Local AI track:
youtube.com/watch?v=XV2oYi…v

The Desktop Frontier — Ahmad Osman, Osmantic

@theahmadosman explains the Densing Law, Impact per Parameter, and why hardware is getting MORE valuable over time as models become more efficient

💬0🔄1❤️13👀2498📊3

the wait is over: this is the year of frontier intelligence on the desktop

AI Engineer (@aiDotEngineer) — Tue, 21 Jul 2026 02:32:46 GMT

the wait is over:

this is the year of frontier intelligence on the desktop

Ahmad@TheAhmadOsman

@KyleHessling1@OsmanticAI Wait until you see my presentation on "The Desktop Frontier" from the Local AI Summit at @aiDotEngineer earlier this month 🔮

💬4🔄7❤️64👀21844📊16

@Steve_Yegge @mnair1 @eugeneyan @AnthropicAI @KimMaida @keyboardlabs @EthanSutin @bee__computer @dbt...

AI Engineer (@aiDotEngineer) — Tue, 21 Jul 2026 00:57:09 GMT

@Steve_Yegge@mnair1@eugeneyan@AnthropicAI@KimMaida@keyboardlabs@EthanSutin@bee__computer@dbt *  @KeycardAI instead of keyboard labs, thanks twitter autocomplete, sorry Kim <3

💬0🔄0❤️1👀1141📊1

🆕 Live now: our entire AI x Security Track! https://t.co/WcO6qG6Dye - @Steve_Yegge, Legendary AI ...

AI Engineer (@aiDotEngineer) — Mon, 20 Jul 2026 17:38:36 GMT

🆕 Live now: our entire AI x Security Track!
youtube.com/playlist?list=…e

- @Steve_Yegge, Legendary AI Engineer/Speaker
- @mnair1, CTO/CIO Snyk
- @eugeneyan, MTS @AnthropicAI
- @KimMaida, Founding GTEM @keyboardlabs
- @ethansutin, Head of AI, @bee__computer
- Aaron Stanley, CISO @DBT
- Lovina Dmello, NVIDIA
- Moritz Johner, Form3
- Ezra Tanzer, Snyk

thanks also Ethan Cha of @OneCarlyle for being our first Private Equity speaker

💬0🔄1❤️8👀1515📊2

🆕 Live now: our entire AI x Security Track! - @Steve_Yegge, Legendary AI Engineer/Speaker - @mnair...

AI Engineer (@aiDotEngineer) — Mon, 20 Jul 2026 17:38:07 GMT

🆕 Live now: our entire AI x Security Track!

- @Steve_Yegge, Legendary AI Engineer/Speaker
- @mnair1, CTO/CIO Snyk
- @eugeneyan, MTS @AnthropicAI 
- @KimMaida, Founding GTEM @keyboardlabs 
- @ethansutin, Head of AI, @bee__computer
- Aaron Stanley, CISO @DBT
- Lovina Dmello, NVIDIA
- Moritz Johner, Form3
- Ezra Tanzer, Snyk

thanks also Ethan Cha of @OneCarlyle for being our first Private Equity speaker

full track drop below

💬4🔄5❤️34👀12182📊12

🆕In the Land of AI Agents, the Verifiers Are King https://t.co/XAesWQUMEn @tariqshaukat, CEO of @...

AI Engineer (@aiDotEngineer) — Mon, 20 Jul 2026 15:40:18 GMT

🆕In the Land of AI Agents, the Verifiers Are King
youtube.com/watch?v=VrpEyg…n

@tariqshaukat, CEO of @SonarSource, takes to the keynote stage to answer @trq212's challenge of extracting AI utility from slop! Backed by CMU and Sonar productivity studies, he proposes a 3-stage framework

- Stage 1: Guide (Providing context and constraints)
- Stage 2: Verify (Zero-trust, multi-layered verification)
- Stage 3: Solve (Maintenance loops and technical debt control)

Echoing @headinthebox and @varun_pant_'s talks - he is keen on systems thinking and code verification as the key to success with AI. When done right, they have been seeing as much as 92% reduction in issues with disciplined verification with an agent centric development cycle (yes, the ACDC). Closing the full loop is not just needed for the software factory, but for AI Engineering to progress from tokenmaxxing to provably useful code.

💬6🔄3❤️37👀4345📊14

🗽 AI Engineer returns to NYC! Oct 12-14, a beautiful time to visit. Tickets go on sale soon, but ...

AI Engineer (@aiDotEngineer) — Sat, 18 Jul 2026 15:30:00 GMT

🗽 AI Engineer returns to NYC!

Oct 12-14, a beautiful time to visit.

Tickets go on sale soon, but the Call for Speakers is now open!
ai.engineer/cfpg

If you do leading AI work in NYC, especially for AI x Finance, speaker applications for AIE NYC 2026 opened today.

For mainstage keynotes, we are actively soliciting the top AI native companies and AI transformations in:

- Investment Banking
- Commercial Banking
- Consumer Banking
- Hedge Funds
- Private Equity
- Financial Data
- Insurance
- Venture Capital
- Agentic Commerce
- Accounting
- Payments
- Compliance
- Mid/Back Office

If you are NOT in Finance, don't worry, we will still be running our regular AI Engineering and AI Leadership tracks, covering all the latest in coding, generative media, evals, infra, and more. But if you want to meet some of the largest AI native banks and financial institutions in the world, this will be the #1 place to be this fall!

💬1🔄4❤️44👀8336📊11

🆕 The Great Loops Debate! https://t.co/J15hrMVpqi Team No Delta - @ianlivingstone - @GeoffreyHun...

AI Engineer (@aiDotEngineer) — Fri, 17 Jul 2026 22:05:57 GMT

🆕 The Great Loops Debate!
youtu.be/c35YoMdnI78i

Team No Delta
- @ianlivingstone 
- @GeoffreyHuntley 

Team Delta
- @dexhorthy 
- @grichadev 

led by the inimitable @vtahowe!

Our first ever Oxford Style Debate: There is, or is not, a delta between the hype behind loops and what actually works in practice.

💬1🔄4❤️26👀21265📊16

@benoitschilling also congrats to Philipp - he was a rare double speaker at WF26 first talk publis...

AI Engineer (@aiDotEngineer) — Fri, 17 Jul 2026 18:04:54 GMT

@benoitschilling also congrats to Philipp - he was a rare double speaker at WF26 

first talk published now youtube.com/watch?v=0vphxN…

and next coming up soon!

x.com/_philschmid/st…

Philipp Schmid@_philschmid

🫪🫪🫪

💬0🔄2❤️3👀1527📊1

🆕 Research to Reality with Google DeepMind https://t.co/WR4PAkU730 Way back in the ancient times ...

AI Engineer (@aiDotEngineer) — Fri, 17 Jul 2026 15:35:26 GMT

🆕 Research to Reality with Google DeepMind
youtu.be/1P1hJ36rxM00

Way back in the ancient times of 2018, Google X started a skunkworks project exploring how ML could improve coding. @benoitschilling was CTO, and many people were incredible skeptical.

Benoit now leads the Gemini Thinking, Reasoning, and Coding teams at @GoogleDeepMind, and still sees more potential for AI to solve software - even now that coding has moved from machine-constrained to design-constrained: The challenge is no longer writing the code itself, but ensuring the code aligns with specific, complex requirements, shifting the role of the developer toward architecture, verification, and high-level reasoning.

💬7🔄2❤️11👀4829📊10

i guess this is a great time to note that @cormacb's talks and workshops were some of the most popul...

AI Engineer (@aiDotEngineer) — Fri, 17 Jul 2026 15:23:44 GMT

i guess this is a great time to note that @cormacb's talks and workshops were some of the most popular @GoogleDeepMind sessions EVER! 

we're so glad to work with @osanseviero and @vadiamit in presenting AIE Europe, including a super well received keynote from @RaiaHadsell.

Cormac returned with @benoitschilling for the World's Fair - videos launching today, see below 👇

h100envy@h100envy

Google engineer explained how to fine-tune a tiny LLM from 46% to 90% accuracy on your phone in 21 minutes - better than $1500 on-device AI bootcamps.

pick Gemma 270M -> generate synthetic task data -> fine-tune with LoRA -> quantize to int4 -> deploy to Pixel and hit 2000 tokens per second.

That loop is how a 270M model beats a 70B one on your task, running fully offline in your pocket.

Gemma 270M + synthetic data + LoRA + int4 quantization + on-device runtime - that's the stack.

Watch and save it, then fine-tune your own tiny agent tonight.

Your browser does not support the video tag.

💬3🔄4❤️44👀6720📊12

🆕 We're so excited to release special double header talks with @ycombinator leaders: @garrytan on ...

AI Engineer (@aiDotEngineer) — Fri, 17 Jul 2026 02:06:41 GMT

🆕 We're so excited to release special double header talks with @ycombinator leaders:

@garrytan on Gbrain, Gstack, and the new Physics of Business:youtube.com/watch?v=eBUyTS…k

@eve_bouff on Imagination Engineering:youtube.com/watch?v=Z2Erdi…U

enjoy!

💬1🔄5❤️28👀26193📊9

🆕 "Increasingly we find that you have a human working with a team of agents, and then the agents ca...

AI Engineer (@aiDotEngineer) — Thu, 16 Jul 2026 18:19:39 GMT

🆕 "Increasingly we find that you have a human working with a team of agents, and then the agents can start working with the other agents."
youtube.com/watch?v=q4Tr-D…m

@leerob's excellent keynote on how @cursor_ai is building the third era of software development is now live, covering the inner and outer training loops (outer - user feedback and AB testing,  inner - refining evals, reward shaping, and training ambitious tasks), Cursor Bench, the new Colossus infra, and how models are starting to train models.

💬4🔄4❤️21👀6492📊11

🆕This Year In Claude https://t.co/y3nAq7wjL1 @simonw chats with @_catwu and @trq212 about the sta...

AI Engineer (@aiDotEngineer) — Wed, 15 Jul 2026 17:46:49 GMT

🆕This Year In Claude
youtube.com/watch?v=uU5Gv2…1

@simonw chats with @_catwu and @trq212 about the state of:

- @claudeai Code
- Claude Fable
- @anthropicai culture & product strategy 
- Claude Tag & multiplayer collaboration
- The surprising succcess of Remote control
- HTML artifacts for code review
- Why Anthropic uses Auto Mode as the standard for long-running tasks at Anthropic, not --dangerously-skip-permissions
- using Claude for Video editing
- how to be more ambitious as a developer:  refusing to "negotiate against oneself"

Timestamps
0:00 Introductions and Claude Code overview
1:22 How coding agents have changed daily workflows
3:51 Shifting focus: Product sense over manual implementation
5:09 Why modern rewrites are now beneficial
6:37 Introducing Claude Tag and team collaboration
11:38 Prioritization and internal "dog-fooding" culture
13:06 The surprise success of remote control features
14:17 Evolving code review processes and automation
17:16 Building trust in new model generations
19:18 Optimizing for capability and user experience
21:23 Reducing system prompts for frontier models
28:05 The philosophy of tool design
30:57 Safety, security, and using Auto Mode
37:53 The human element and developer ambition
41:50 Surprising use cases for Claude (e.g., video editing)
43:35 Limitations and future design aspirations
45:09 Cultural hacks for productivity
46:42 Absurd, fun projects built with Claude
49:03 Audience Q&A

💬8🔄9❤️62👀92275📊34

@prukalpa 🆕 WTF Is the Context Layer? The Missing Infrastructure for Production Agents — Prukalpa S...

AI Engineer (@aiDotEngineer) — Tue, 14 Jul 2026 23:29:10 GMT

@prukalpa 🆕 WTF Is the Context Layer? The Missing Infrastructure for Production Agents — Prukalpa Sankar
youtube.com/watch?v=8G_1-3…y

💬0🔄0❤️7👀1716📊1

"At the dawn of the internet era, Bill Gates had written this very famous blog post and it said cont...

AI Engineer (@aiDotEngineer) — Tue, 14 Jul 2026 23:28:49 GMT

"At the dawn of the internet era, Bill Gates had written this very famous blog post and it said content is king. And as we see the dawn of the agentic era, context will be king." 

— @prukalpa explains Context Layers to a packed Context Engineering track last week. Premiering now, link in reply!

💬2🔄3❤️23👀8021📊8

secondaryslogan.jpg

AI Engineer (@aiDotEngineer) — Tue, 14 Jul 2026 22:16:37 GMT

secondaryslogan.jpg

sarah@sarahfim

@browserbase@KaranVaidya6@composio@aiDotEngineer AX is the new UX

💬0🔄0❤️2👀1491📊1

🆕Don't Build Agents You Can't Answer For https://t.co/fW7jeNznL5 @addyosmani's closing keynote on...

AI Engineer (@aiDotEngineer) — Tue, 14 Jul 2026 17:30:09 GMT

🆕Don't Build Agents You Can't Answer For
youtu.be/n97BCfyFIvw5

@addyosmani's closing keynote on:
- roles/titles < system ownership
- on @mitchellh: "Taste is the ability to make high-quality qualitative judgments where no objective metric exists yet."
- "if generation scales faster than comprehension, the scarce resource becomes judgment backed by evidence."

His new rule: "Explain it or don't ship it."

💬3🔄8❤️30👀7088📊13

@solomonstre @simonw @headinthebox live now: the closing keynote from the one and only @headinthebox...

AI Engineer (@aiDotEngineer) — Mon, 13 Jul 2026 19:41:41 GMT

@solomonstre@simonw@headinthebox live now: the closing keynote from the one and only @headintheboxyoutube.com/watch?v=-CnA2l…

💬1🔄2❤️10👀6990📊5

🆕 In Code They Act, In Proof We Trust — Erik Meijer last year, @solomonstre defined agents as "an ...

AI Engineer (@aiDotEngineer) — Mon, 13 Jul 2026 19:41:35 GMT

🆕 In Code They Act, In Proof We Trust — Erik Meijer

last year, @solomonstre defined agents as "an LLM that's wrecking its environment in a loop", and @simonw coined the Lethal Trifecta for agents, that remains unsolved.

our closing keynote @headinthebox introduces the main motivations behind Automind and the Universalis interpreter - agents that carry their own verifiable proof of safety! link to talk below

💬3🔄3❤️21👀9514📊10

@abshkbh @gdb 🆕From fork() to Fleet: Designing an Agent Sandbox Cloud https://t.co/sNEeuAaxZg

AI Engineer (@aiDotEngineer) — Mon, 13 Jul 2026 19:13:56 GMT

@abshkbh@gdb 🆕From fork() to Fleet: Designing an Agent Sandbox Cloud
youtube.com/watch?v=OqM67Q…g

💬1🔄2❤️3👀1952📊3

🆕From fork() to Fleet: Designing an Agent Sandbox Cloud https://t.co/qA8g9FtJeS @abshkbh spoke at...

AI Engineer (@aiDotEngineer) — Mon, 13 Jul 2026 19:13:51 GMT

🆕From fork() to Fleet: Designing an Agent Sandbox Cloud
youtube.com/watch?v=OqM67Q…S

@abshkbh spoke at AIEWF Online last year about Arrakis, his open source MicroVM-based secure sandboxes. @gdb hired him immediately for his expertise and passion - and now, after a year at OpenAI and recent release of @ChatGPTApp Work, he makes his onstage debut covering the three pillars of agent cloud engineering - Runtime, Persistence, and Orchestration - and ends with a surprising conclusion on why storage and filesystems are an integral part of agent clouds!

Abhishek Bhardwaj@abshkbh

For the past year I’ve been building Arrakis on a single thesis: with the right tools and secure environments, LLMs can reliably do complex work.

This journey started two years ago when I left a stable role at Google to work on early coding agents. While still at Google, I wrote a long email to @gdb  about how a systems engineer could break into AI.

Arrakis opened doors and has led to a full-circle moment: I’ve joined @OpenAI  to work on Agent Infrastructure in the Scaling org.

It’s a privilege to help people through smarter models and agents. I’m especially excited about our coding initiatives. Thank you @gdb and @paulashbourne  for the opportunity.

Looking back, the biggest risk was not taking one!

💬2🔄5❤️46👀24205📊13

Key Components of the @PrimeIntellect Stack: https://t.co/QmC6EShB4N Environment & Verification (0...

AI Engineer (@aiDotEngineer) — Mon, 13 Jul 2026 15:38:58 GMT

Key Components of the @PrimeIntellect Stack:

youtube.com/watch?v=V-EDrh…

Environment & Verification (0:50): Prime Intellect has overhauled their Verifiers library to create a modular, task-based system. It decomposes environments into task sets (data/rules), harnesses (agent logic), and runtimes (execution environments), allowing for greater flexibility when evaluating models.

Asynchronous RL Framework (PrimeRL) (29:20): The core training framework is built to be fully asynchronous. By decoupling training from inference, they can handle long-horizon agentic rollouts without stalling the entire system, making it more efficient for complex coding tasks.

Modern Post-Training Algorithms (38:00): The stack is designed to support a wide array of training recipes, including Supervised Fine-Tuning (SFT), On-Policy Distillation, and Self-Distillation. The system abstracts the loss functions and algorithms, allowing users to swap methods without changing their infrastructure.

The Lab Platform (42:35): Prime Intellect offers a hosted platform that handles the underlying compute, providing multi-tenant LoRA training today and full fine-tuning capabilities soon, while keeping the developer experience consistent from local prototyping to cloud-scale runs.

💬0🔄2❤️10👀2643📊4

Congrats to PI on the unicorn round and $100M ARR! we were proud to have @willccbb introduce verifi...

AI Engineer (@aiDotEngineer) — Mon, 13 Jul 2026 15:37:00 GMT

Congrats to PI on the unicorn round and $100M ARR!

we were proud to have @willccbb introduce verifiers at the first AIE NYC a year ago and now... it is v1!

Will joins a rare list of three-time AIE speakers, and his talk on the full PI stack  is linked below!

Prime Intellect@PrimeIntellect

Today, we are releasing verifiers v1 — an overhaul of our environment stack for the modern era of agentic RL and evals.

We decompose environments into a taskset, a harness, and a runtime. 

Run complex agentic tasks like coding and computer use at scale, in any harness.

💬10🔄12❤️215👀51057📊46

"I think it's important for people to understand how code works." Geoffrey Litt's Design Eng track ...

AI Engineer (@aiDotEngineer) — Fri, 10 Jul 2026 22:18:26 GMT

"I think it's important for people to understand how code works."

Geoffrey Litt's Design Eng track keynote is live now:

youtube.com/watch?v=WkBPX-…

Thank you @NotionHQ for supporting his incredible work and thank you Geoff for kicking off WF26 for our Design Engineers!

Geoffrey Litt@geoffreylitt

Hot take: I think it's still important to understand the code that our agents write!

In this mega thread (based on my AIE talk today), I will explain why that's the case, and show some ideas for how to efficiently understand code. Alright, let's dive in. 1/

💬11🔄12❤️37👀13023📊20

At AI Engineer Europe, two talks gave opposite advice. Zechner: read every f***ing line. Lopopolo: c...

AI Engineer (@aiDotEngineer) — Fri, 10 Jul 2026 18:14:52 GMT

At AI Engineer Europe, two talks gave opposite advice. Zechner: read every f***ing line. Lopopolo: code is free, delete your IDE. Opposite advice. Standing ovations for both.

@altryne built a framework on the ride home.

youtube.com/watch?v=ZpK5PW…

The Z/L Continuum is real but the framing was wrong. It's not about the person. It's about the task.

Meanwhile, the data: 861% increase in code deletion per PR. 242% increase in incidents. Bugs per developer up 6x from 2025. 31% of PRs merged with no review at all.

Karpathy says: "It's never felt so tempting to stop looking at code at all — but don't do this in production."

Maybe not every line in 2026 needs your eyes. Every system still needs your judgment.

💬0🔄2❤️19👀2772📊4

Three constraints, in order: Tokens: fixed. Compute: fixed by test boxes (agents run tests on a sep...

AI Engineer (@aiDotEngineer) — Fri, 10 Jul 2026 00:33:37 GMT

Three constraints, in order:

Tokens: fixed.
Compute: fixed by test boxes (agents run tests on a separate machine while you continue work)
Attention: can't add more.

"The most important skill today is deciding where to spend it."

💬2🔄0❤️2👀1987📊3

The product framing from OpenAI: models now ship every 6 weeks. GPT 5.6 on Cerebras runs at 750 toke...

AI Engineer (@aiDotEngineer) — Fri, 10 Jul 2026 00:33:37 GMT

The product framing from OpenAI: models now ship every 6 weeks. GPT 5.6 on Cerebras runs at 750 tokens per second — a substantial PR in 10 seconds.

2025 was token maxing. 2026 is value maxing.

💬1🔄0❤️3👀1566📊2

In January, juggling 10 terminal windows felt like peak productivity. By April it felt silly. @stei...

AI Engineer (@aiDotEngineer) — Fri, 10 Jul 2026 00:33:36 GMT

In January, juggling 10 terminal windows felt like peak productivity. By April it felt silly.

@steipete, @embirico, and @romainhuet on what actually changed.

youtube.com/watch?v=pMggiO…

💬3🔄1❤️16👀4976📊7

🆕 Congrats to @OpenAI on the highly anticipated launch of GPT 5.6 Sol, Terra, and Luna! https://t....

AI Engineer (@aiDotEngineer) — Thu, 09 Jul 2026 18:55:48 GMT

🆕 Congrats to @OpenAI on the highly anticipated launch of GPT 5.6 Sol, Terra, and Luna!
youtu.be/pMggiOb18tcl

Here's @romainhuet, @embirico, and @steipete on why this is the dawn of the Golden Age of AI Engineering:

💬8🔄7❤️70👀23645📊26

@theo tune in tomorrow for the big @OpenAI keynote on GPT 5.6 launch day! https://t.co/3qa07h9AYB ...

AI Engineer (@aiDotEngineer) — Wed, 08 Jul 2026 20:27:42 GMT

@theo tune in tomorrow for the big @OpenAI keynote on GPT 5.6 launch day!

youtube.com/watch?v=pMggiO…

ft. @embirico@romainhuet and special guest @steipete !

💬0🔄0❤️4👀1949📊2

For the closing keynote of WF26, @theo provokes you to think bigger: https://t.co/WMhvSzpWGz In a...

AI Engineer (@aiDotEngineer) — Wed, 08 Jul 2026 20:22:32 GMT

For the closing keynote of WF26, @theo  provokes you to think bigger:

youtube.com/watch?v=xUnRQ9…

In an age where most startups are just a markdown file running on a cron job now, the barrier for building platforms has collapsed.

Be more ambitious.

💬3🔄1❤️36👀18195📊11

live now: Startup Battlefield at @aiDotEngineer World's Fair. 18 AI-native founders. top 3 about to...

AI Engineer (@aiDotEngineer) — Fri, 03 Jul 2026 00:30:23 GMT

live now: Startup Battlefield at @aiDotEngineer World's Fair.

18 AI-native founders. top 3 about to hit main stage. $100k on the line.

no decks, no theory: working demos, technical judges, and the next generation of AI companies.

tune in: youtube.com/watch?v=I2cbIw…

💬1🔄2❤️18👀4240📊4

who's gonna tell him

AI Engineer (@aiDotEngineer) — Thu, 02 Jul 2026 19:15:23 GMT

who's gonna tell him

harsh@devloperhs

@sarahfim@composio@aiDotEngineer Is AI Engineer a big thing?, all I see them on yt is doing postcast / events recordings.

Is it a community of some sort that  I am missing on?

💬4🔄0❤️51👀9208📊8

Last chance to stop by the Startup Battlefield - 3rd floor of Moscone West. Almost 20 startups going...

AI Engineer (@aiDotEngineer) — Thu, 02 Jul 2026 18:55:34 GMT

Last chance to stop by the Startup Battlefield - 3rd floor of Moscone West. Almost 20 startups going head to head.

💬1🔄1❤️5👀1638📊2

@AnthropicAI @GoogleDeepMind @amazon for the last day of AIE Keynotes, @barrnanas returns to give th...

AI Engineer (@aiDotEngineer) — Thu, 02 Jul 2026 16:17:09 GMT

@AnthropicAI@GoogleDeepMind@amazon for the last day of AIE Keynotes, @barrnanas returns to give the annual State of AI Engineering, @JohnOusterhout has a special appearance introducing the hardware/inference track, @mikeyk and @garrytan  gives advice to founders, and @theo gets roasted!

youtube.com/live/I2cbIws9j…

💬0🔄0❤️3👀1198📊1

Three days in one building and it still doesn't feel like enough. Day 3 of World's Fair.

AI Engineer (@aiDotEngineer) — Thu, 02 Jul 2026 11:11:00 GMT

Three days in one building and it still doesn't feel like enough. Day 3 of World's Fair.

Your browser does not support the video tag.

💬1🔄1❤️42👀6650📊7

Launched at AIE!

AI Engineer (@aiDotEngineer) — Thu, 02 Jul 2026 06:38:11 GMT

Launched at AIE!

Z.ai@Zai_org

Introducing ZCode, the official development environment for GLM-5.2

- GLM Coding Plan subscribers: now 1.5x usage quota in ZCode
- BYOK supported: works with your existing subscriptions and APIs
- Available on macOS, Windows, and Linux

Download now: zcode.z.ai/en

💬0🔄1❤️40👀8106📊5

we need a thread of all the INCREDIBLE costume and out of home advertising game you guys pulled at A...

AI Engineer (@aiDotEngineer) — Thu, 02 Jul 2026 06:37:37 GMT

we need a thread of all the INCREDIBLE costume and out of home advertising game you guys pulled at AIE this year because HOLY SHIT

Gabriel Chua@gabrielchua

🙈

💬1🔄0❤️4👀2818📊1

every day there are surprises planned in the Expo! OpenAI's big rate limit reset will be done LIVE ...

AI Engineer (@aiDotEngineer) — Wed, 01 Jul 2026 19:16:03 GMT

every day there are surprises planned in the Expo!

OpenAI's big rate limit reset will be done LIVE at the OAI booth in 40 minutes - come meet the team and celebrate the biggest cheers from the @jxnlco codexmaxxing community!

OpenAI Developers@OpenAIDevs

As agents take on longer-running work, engineering shifts to setting direction, reviewing work, and designing better systems around the models.

@steipete at @aiDotEngineer

Your browser does not support the video tag.

💬1🔄1❤️24👀6061📊4

for everyone asking, yes, the Claude session (Fable/Claude Code/Claude Tags etc) will be in 19 mins ...

AI Engineer (@aiDotEngineer) — Wed, 01 Jul 2026 19:11:25 GMT

for everyone asking, yes, the Claude session (Fable/Claude Code/Claude Tags etc) will be in 19 mins downstairs in Expo Stage 2!!!!

swyx @aiDotEngineer WF@swyx

so proud to host my friend @trq212 to give the world’s first Fable talk on Fable return day!

find him with @simonw and @_catwu  in Expo Stage 2 for an extra EXTRA special lunch session at 12.30 today!!