AI Engineer (@aiDotEngineer) - Twitter Profili | Zamantika Mersobahis Locabet

Sabitlenmiş Tweet

AI Engineer@aiDotEngineer·16 May

All @aiDotEngineer SG talks kick off in 22 mins! Tune in live: youtube.com/watch?v=_xQnSN… - @VivianBala, NanoClaw power user & Cabinet Minister - @Gavriel_Cohen, creator of NanoClaw - @thsottiaux, Eng lead Codex @OpenAI - @ryolu_, Head of Design @cursor_ai - @dmsobol, Head Research Scientist $CBRS - @feedthejim, @Nextjs Lead @Vercel - @ZixuanLi_, Head of @Zai_org - @ktoya_me, Growth @ElevenLabs - @Stefania_druga, RS, @SakanaAILabs - Jacky Mok, Head of Applied @RekaAILabs - @JukicVedran, CTO @daytonaio - @JanLiphardt, Founder OpenMind - @picocreator, CEO @FeatherlessAI - @lihautan, Lead @SimularAI - @jackminong, RL @PrimeIntellect - @vaishaaant, Cofounder @greptile - @howdymj, Cofounder Bluelabs - @PhilHedayatnia, CEO Airfoil - @linhkid91, Head of AI @Obello - @vamonke, Founding Voltade - @GokulKrishnaSr1, President, Antim - Nibblepuff, Tech Lead @usebland - @swyx and too many others to count! join in!

YouTube

English

7

34

154

177.4K

AI Engineer@aiDotEngineer·2h

RAG retrieves documents. Context graphs retrieve relationships. @steveonjava from Neo4j shows why graph-based context is the next unlock for agentic systems. youtube.com/watch?v=eW_vxr…

YouTube

English

0

3

49

2K

AI Engineer@aiDotEngineer·1d

Most agents die after a few seconds. @AnthropicAI's workshop shows how to build agents that run for hours. full 75-min session with Ash Prabaker & Andrew Wilson. youtube.com/watch?v=mR-WAv…

YouTube

English

17

31

160

9.7K

AI Engineer@aiDotEngineer·2d

Something that just became practical: taste. Generate 15 variations of a component in the time a slow model generates one. Five sub agents generating 15 versions each = 75 options. Pick the best. Context management also changes. What used to take 10 minutes to fill now takes 30 seconds. A four file system (agents, plan, progress, verify) keeps each new session from starting over.

English

0

1

1.2K

AI Engineer@aiDotEngineer·2d

Things that become basically free at 1200 tps: - Validation and linting after every task, not just before you commit - Diff reviews at every step - Continuous refactoring built into the workflow At this speed, there's no excuse not to run all of it.

English

2

0

7

1.8K

AI Engineer@aiDotEngineer·2d

Codex Spark generates code at 1,200 tokens per second. Sonnet and Opus run at 40 to 60. At 20x the speed, the habits you built around slow generation don't go away. They start shipping bad code 20 times faster. @MilksandMatcha from @cerebras with the practical playbook. youtube.com/watch?v=TeGsFF…

YouTube

English

2

13

75

5.1K

AI Engineer retweetledi

Raspberry Pi@Raspberry_Pi·4d

"My most daily used agent is running off a Raspberry Pi which is at least two or three years old; all that it has is 8GB of RAM. You see my point about accessibility, personalisation, relevance, use. [...] This is my point: the barriers have fallen." 🫶 Singapore's Minister for Foreign Affairs, Dr Vivian Balakrishnan, built his own agentic AI tool running on a Raspberry Pi (inc appropriate security measures!)

AI Engineer@aiDotEngineer

"You cannot govern a technology you have only been briefed on." Singapore Minister for Foreign Affairs, Dr. @VivianBala, echoing @karpathy and @yacineMTB on why he runs NanoClaw: "you can outsource memory and computation, but you cannot outsource your understanding" x.com/VivianBala/sta… He also shared his tech stack for running his second brain for Singapore's Foreign Affairs Ministry and parliamentary affairs: - @AnthropicAI Claude Agent SDK - Baileys + WhatsApp - Mnemon (Graph Memory) - @ollama + @nomic_ai - @ggerganov Whisper.cpp + OneCLI With special notes on how he handles security and isolation, and what implications he sees for Singapore Inc.

English

7

17

136

23.6K

AI Engineer retweetledi

Bilge@bilgeycl·4d

🥳 My talk from @aiDotEngineer Europe is live on YT!! this was my first ever talk on sovereignty so I'm quite excited to share 💗 I broke down AI sovereignty into 4 pillars to make it clearer and I shared a sovereign @Haystack_AI architecture + a checklist for AI systems

English

8

13

82

5.8K

AI Engineer retweetledi

Ben Burtenshaw@ben_burtenshaw·4d

If you're scaling AI/ML experiments with agent and autoresearch, check out this presentation I gave last month at @aiDotEngineer It walks through 3 progressively more intense ways of doing ML with agents, starting off with low level AI Sys and working up to multi-agent ai labs.

English

3

9

71

3.5K

AI Engineer retweetledi

Harsha@khurdula·3d

Presenting at AI Engineer in Singapore Broke down how Interfaze works and the evolution of AI The audience was great and Singapore was amazing

English

4

6

62

5.9K

AI Engineer retweetledi

Marijan Cipcic@CipcicMarijan·3d

Last week I was in Singapore 🇸🇬 for @aiDotEngineer conference and side events with @JukicVedran and @ivanda_mislav representing @daytonaio. Big week for us: • Ran a Daytona booth at AI Engineer SG • Vedran gave a main stage talk • Hosted an AI Builders meetup • Vedran and I joined the @ATPinsights podcast Huge takeaway from the week: the AI builder community in Singapore is thriving. So many thoughtful conversations around agents, infrastructure, and how to grow strong communities around the ecosystem. Huge congrats to the organizers: @agrimsingh, @SherryYanJiang and the entire @65labslah team, and of course @swyx for bringing the leading AI engineering conference franchise to Singapore. The event and hospitality were top-notch! SG, we’re just getting started, stay tuned for what’s next.

English

9

5

33

2.5K

AI Engineer@aiDotEngineer·3d

TLMs: Tiny LLMs and Agents on Edge Devices with @cormacb youtube.com/watch?v=-TiET_… Function Gemma ships at 270 million parameters and runs nearly 2,000 tokens per second prefill on a Pixel 7. Out of the box, it hits 46% accuracy on a fixed set of app intents. Fine tune on a synthetically generated dataset and that clears 90% on eight of ten functions. Cormac walks through the two paths developers have for on device AI: a skill harness built on Gemma 4 with a restaurant roulette demo running fully on device. Then Eloquent, a production transcription app built by chaining two sub billion parameter models together. cc @osanseviero

YouTube

English

5

93

596

29.7K

AI Engineer@aiDotEngineer·4d

#tickets" target="_blank" rel="nofollow noopener">ai.engineer/worldsfair#tic… The discount happens automatically in the cart, and the purchase must include at least one "Workshop + Engineering" ticket to receive the discount.

English

0

2

1.2K

AI Engineer@aiDotEngineer·4d

Group discounts for AI Engineer World's Fair are now live! Bring 5 and save 10%. Bring 10 and save 15%. Bring 15+ and save 20%. June 29 to July 2, San Francisco.

English

2

17

5K

AI Engineer@aiDotEngineer·5d

PFF ran a 3-month case study: 2 engineers vs a team of 10 The 2 shipped 5 times a day The 10 shipped once every 5 days youtube.com/watch?v=VMemht… Output weighted by ticket complexity: 10x. Customer satisfaction went from around 7 to 8.6 out of 10 CTO @mikespitz_uk explains what it actually took.

YouTube

English

1

7

39

2.6K

AI Engineer@aiDotEngineer·5d

@serj_mig tyy

0

1

522

Sérgio Miguel Silva@serj_mig·5d

Credit where it's due. @aiDotEngineer has a lot of amazing content on anything related to AI Engineering, including complete workshops. Highly recommend

swyx@swyx

we do not post AIE videos with bullshit brainrot hype lingo, and this is the consequence: the entire AIE back catalog is being reposted by "influence operators" almost daily, without credit to speakers like @trq212 or @aidotengineer if you see these just do a small favor of tagging and giving credit. community note not needed, let them make their bags, but i just request that the right accounts that produced the content be tagged. this wont go anywhere as much as this guy's automated repost campaign, but just making a small call out. actual video link: youtube.com/watch?v=TqC1qO… (h/t @raoufcode )

English

1

0

3

806

AI Engineer retweetledi

Barr Yaron@barrnanas·18 May

It’s the most wonderful time of the year 🎶 The 2026 AI Engineering Survey is live, this year in partnership with @NotionHQ and @vercel. If you’re an engineer working on AI products, we’d love you to fill it out. We're raffling off fantastic prizes too.

English

5

7

46

10.8K

AI Engineer retweetledi

Uzi@uzairansar·6d

Anyone else addicted to these AI Engineer videos?

English

8

4

33

2.5K

AI Engineer@aiDotEngineer·18 May

Harnesses in AI: A Deep Dive @TejasKumar_ builds a browser agent on GPT-3.5 Turbo that has one job: upvote a post on Hacker News. Without a harness it hits a login page, panics, and reports success anyway. The upvote never happened. youtube.com/watch?v=C_GG5g… He fixes it without touching the prompt once. Guardrails cap the iteration count and compact context when it bloats. A verify step reads the actual tool call history to catch the lie. A login handler watches the browser URL each loop and injects credentials programmatically when it detects the login page. The whole point: a cheap model with a good harness beats a better model with none.

YouTube

English

6

20

139

6.4K

AI Engineer retweetledi

agrim singh@agrimsingh·17 May

underrated part of @aiDotEngineer singapore - our breaks are designed as decompression sessions where our facilitator keziah quek explores our relationship with ai through a meditation. much in the spirit of the conference, she vibe coded the entire audio-visual journey on her own! this is what ai engineer is about

English

4

6

61

20.8K

AI Engineer@aiDotEngineer·17 May

@VivianBala @karpathy @yacineMTB link to Mnemon creator x.com/grivn_eth/stat…

𝗚𝗥𝗜𝗩𝗡.𝗛𝗟 🌎-'@grivn_eth

As the creator of Mnemon, it’s an honor to see Dr. Vivian Balakrishnan (@VivianBala) exploring it as part of his personal AI stack for persistent knowledge and second-brain workflows. Mnemon started as a memory system, but our long-term direction is a memory-driven harness layer for durable and self-evolving agents. We believe future agents need more than context windows. They need persistent state, evolution loops, orchestration, and runtime continuity around the host agent. Our goal is simple: make it possible for any agent to plug into Mnemon and gain persistent cognition. Still early. Still building. Feel free to try it out and explore the future of persistent agents with us. github.com/mnemon-dev/mne…

English

1

0

4

4K

AI Engineer@aiDotEngineer·16 May

"You cannot govern a technology you have only been briefed on." Singapore Minister for Foreign Affairs, Dr. @VivianBala, echoing @karpathy and @yacineMTB on why he runs NanoClaw: "you can outsource memory and computation, but you cannot outsource your understanding" x.com/VivianBala/sta… He also shared his tech stack for running his second brain for Singapore's Foreign Affairs Ministry and parliamentary affairs: - @AnthropicAI Claude Agent SDK - Baileys + WhatsApp - Mnemon (Graph Memory) - @ollama + @nomic_ai - @ggerganov Whisper.cpp + OneCLI With special notes on how he handles security and isolation, and what implications he sees for Singapore Inc.

English

6

81

347

87K

AI Engineer@aiDotEngineer·16 May

All @aiDotEngineer SG talks kick off in 22 mins! Tune in live: youtube.com/watch?v=_xQnSN… - @VivianBala, NanoClaw power user & Cabinet Minister - @Gavriel_Cohen, creator of NanoClaw - @thsottiaux, Eng lead Codex @OpenAI - @ryolu_, Head of Design @cursor_ai - @dmsobol, Head Research Scientist $CBRS - @feedthejim, @Nextjs Lead @Vercel - @ZixuanLi_, Head of @Zai_org - @ktoya_me, Growth @ElevenLabs - @Stefania_druga, RS, @SakanaAILabs - Jacky Mok, Head of Applied @RekaAILabs - @JukicVedran, CTO @daytonaio - @JanLiphardt, Founder OpenMind - @picocreator, CEO @FeatherlessAI - @lihautan, Lead @SimularAI - @jackminong, RL @PrimeIntellect - @vaishaaant, Cofounder @greptile - @howdymj, Cofounder Bluelabs - @PhilHedayatnia, CEO Airfoil - @linhkid91, Head of AI @Obello - @vamonke, Founding Voltade - @GokulKrishnaSr1, President, Antim - Nibblepuff, Tech Lead @usebland - @swyx and too many others to count! join in!

YouTube

English

7

34

154

177.4K

AI Engineer

Keşfet