Lincoln Nguyen

CEO of Karuna Labs | Agentic engineer | Dzogchen practitioner

[Andrej Karpathy @karpathy]

This is a super exciting release - Claude Fable 5 is the same underlying model as Mythos but with added safeguards. The benchmarks are great and it's SOTA on everything by a margin but I'll add that *qualitatively* also, this is a major-version-bump-deserving step change forward (imo of the same order as Claude 4.5 was in November), peaking especially for long problem-solving sessions on very difficult problems. You can give it a lot more ambitious tasks than what you're used to, the model "gets it" and it will just go, and it's never felt this tempting to stop looking at the code at all (but don't do this in prod!). The model still has quirks that people will run into and the safeguards are configured to be a little too trigger happy for launch, which can hopefully be tuned over time.

I feel a lot of things changing as working software increasingly comes out on a tap. The Jevon's paradox kicks in and I feel my own demand for software growing substantially. You can ask for anything - explainers, visualizers, dashboards, bespoke single-use apps (e.g. a full wandb that is hyper-specific just for your project), you can 10X your test suite, auto-optimize code, run giant research projects with custom HTML for the results, anything! "Free your mind" (Matrix ref). Really looking forward to all the things people build!

[Caspar Broekhuizen @caspar_br]

We're building this at LangChain

Fleet lets you create and manage a fleet of agents. Each agent specializes in a workflow, e.g. inbox management, blog writing, competitor research, candidate recruiting. These are Deep Agents with custom instructions, skills, tools, subagents, and memory. They continually improve with feedback. You can share them with your coworkers. You can configure them to run on a schedule. You can export their context files should you ever want to host them yourself

I think Fleet strikes a great balance: easy to use and still highly capable

We've put an inordinate amount of thought into the UX patterns that make that possible. For example, I love our 'channels' concept: you can configure your agent's communication channel (e.g. Slack, Teams, email, etc.) so it meets you where you work instead of forcing you into Fleet's UI

It's free to try out so give it a spin and share feedback: https://t.co/TRYcK32IBB

[François Chollet @fchollet]

A mental model for working with coding agents is that they're blind squirrels running into a maze and bumping into walls. You must place the walls (verifiable constraints) strategically so that they end up in the general region you want them in.

[Lincoln Nguyen @lincolnn]

@dabit3 @OpenAI @cognition @AnthropicAI @Google Were building out a FDE team at ClearCycle for healthcare

[Lincoln Nguyen @lincolnn]

@levie We're doing an FDE model with healthcare practices. Tons of opportunity out there

[Aaron Levie @levie]

The need and opportunity for professional services and FDEs to deploy agents right now is massive.

Every tech wave offers a new era of consulting and tech services requirements. Moving from analog to digital led to a massive wave in the 90s. Moving from on-prem to cloud did the same in the 2000s. But this is going to be at a scale far greater than the others.

The reason is that agents fundamentally change the underlying workflows of an organization. Unlike most prior eras of technology, where it was a change in medium of the service being delivered (on-prem CRM to cloud CRM), agents rewire the business process itself. And unlike upgrading a tech system, business processes are full of idiosyncrasies.

Every industry will have its own variants, and every department within those industries will have variants as well. Not to mention the bespoke difference between firms. Bringing agents to marketing in CPG will look different from marketing in healthcare. Bringing agents to sales in a B2B software company will look different from a car dealership.

And none of the change is easy technically. You need to first modernize your infrastructure and data and make sure it’s ready for agents; access controls, entitlements, and permissions need to be mapped in a way that works for agents and people; you need to make sure agents have the right context to work with; you need to consistently eval and maintain the agents when there are model upgrades; and you need to drive the change management of the process itself to figure out which parts the people do and what agents do.

That’s an insane amount of technical and domain-specific process work to be done to make this all happen. Huge opportunity for new service providers, as well as internally teams and roles to emerge, to help drive this change.

[kennethlou @kenneth_lou]

the AI loop that's been rewiring how i think about company design.

sat in a @ycombinator talk this week where the framing finally clicked on what's reeally happening.

old pitch: make engineers 20% more productive. add copilots. ship more software with AI. all true. all also a faster-horse upgrade.

actual move: one person more powerful than old structures. Building a queryable company. agent-native software. different category entirely.

5 layers:

1/ sensors + data. every signal from the outside world. customer emails, support tickets, cancellations, product events, code changes. if it's not captured, it didn't happen to the company.

2/ policy layer. the rules. what the system can do alone, what needs human sign-off, what must be logged. guardrails that make the loop trustworthy.

3/ tool layer. the deterministic stuff. SQL, API calls, calendar lookups. things that live in code, not english. @garrytan 's framing: figuring out what belongs in markdown vs what belongs in code is 90% of the battle.

4/ quality gates. safety checks. human review for high-stakes calls. the escape hatch back into judgment.

5/ learning mechanism. the unlock. Monitoring agent watches every query, sees where it fails, writes the fix overnight, opens the merge request, ships it. The same query that failed yesterday works tomorrow. company gets better while you sleep.

most teams have 1 through 4. almost nobody is running 5 across every function yet.

that's the next 6 months. we're 5 people at @usemitohealth across two cities. everyone touches code. revenue per employee at a level i wouldn't have believed in my fintech days. headcount as a feature, not a bug.

humans aren't getting replaced. we're going deeper. the orchestration, the taste, the high-stakes calls - that layer is expanding.

the middle is what's compressing... if you're operating today, the question isn't whether to use AI but around whether the shape of your company makes sense.

[Garry Tan @garrytan]

The secret to an articulate agent like mine isn't one file. It's three:

SOUL.md — Who the agent IS. Voice, values, operating principles, what good output looks like, what bad output looks like. Not a system prompt, a constitution. Mine says things like "brevity is mandatory," "humor is mandatory," "never open with 'Great question,'" "swearing is allowed when it lands." The more specific and opinionated this is, the less your agent sounds like a chatbot. Write it like you're briefing your smartest friend on how to be you, not like you're configuring software.

USER.md — Who YOU are. Not a bio — a deep model. How your mind works, what you're building, your strengths, your blind spots, your family, your temperament, what triggers you, what you care about. The more the agent understands about you, the better it can serve you. Mine is ~4000 words.

AGENTS.md — Operational rules. What to check on every message, what to never do, how to handle failures, lookup chains, path rules, brain-first protocols. This is the playbook for how it works, not who it is.

The articulation comes from SOUL.md being brutally specific about voice. Generic instructions → generic output. If you write "be helpful and concise" you get ChatGPT. If you write "speak like a peer with taste, one sentence when one sentence works, uncomfortable truths welcome if actually true, language with voltage" — you get something alive.

[Lincoln Nguyen @lincolnn]

Wow..

[Peter Steinberger 🦞 @steipete]

Built clawsweeper, which runs 50 codex in parallel around the clock, scans issues/prs deep and closes what is already implemented or what makes no sense.

Closed around 4000 issues today, a few thousand are in the pipeline. (rate limits are rough) https://t.co/AiNNDcvGke

[Chris Bakke @ChrisJBakke]

Running a company:

2020: can you survive a pandemic?

2021: still here? we’re going to give all of your competitors $100m series A rounds.

2022: wow, you made it? okay, all engineers cost $600,000/year now.

2023: nice job! okay, SVB failed and we’re going to take away your bank account.

2024: a survivor I see. but can you pivot from ai to crypto to defense tech back to ai-enabled defense tech in a 12 month period to stay relevant?

2025: unfortunately all of your competitors have raised $2b series B rounds. oh and only 500 engineers are relevant and they cost $100m/yr each.

2026: well, well, well. you’re still in business? let’s deploy the thunderclap of godlike LLMs from the heavens so all of your customers can rebuild your app in 2 hours. can you survive?

[Lincoln Nguyen @lincolnn]

@Jason Im in

[Lincoln Nguyen @lincolnn]

Boris coding tutorial

[Peter Steinberger 🦞 @steipete]

MCPorter 🧳 0.9.0 is out.
Call MCPs from TypeScript or as CLI

- per-server tool filtering
- sturdier stdio shutdowns
- Windows OAuth URL quoting fix
- OAuth config docs
- schema-declared string coercion for tool calls
https://t.co/aywv0xs0Hf

[Vaibhav Sisinty @VaibhavSisinty]

Did xAI just mass-murder the entire voice AI industry? 🤯

Grok just launched two voice APIs. Speech-to-Text and Text-to-Speech.

Built on the same stack powering Tesla cars and Starlink support.

And priced at 10x cheaper than ElevenLabs.

Speech-to-Text: $0.10/hr batch. $0.20/hr streaming.

Text-to-Speech: $4.20 per million characters.

25+ languages. Real-time streaming. Speaker diarization.

Already outperforming ElevenLabs, Deepgram, and AssemblyAI on word error rate.

TTS ships with expressive tags like [laugh], [sigh], <whisper>, <emphasis>.

Voices that don't sound like robots reading a script.

ElevenLabs spent years building a voice AI company.

xAI built voice AI for cars and satellites.

[Lincoln Nguyen @lincolnn]

Check this out if youre creating a headless AI agent system

[Matt Ronge @mronge]

https://t.co/x0j9UUGx7p

[Matt Ronge @mronge]

https://t.co/x0j9UUGx7p

[Garry Tan @garrytan]

If you are in startups or tech

It is literally cook or be cooked

[Lincoln Nguyen @lincolnn]

@gregisenberg Were building #9 at utilreview. Glad to see it surface here!

[Lincoln Nguyen @lincolnn]

Combine OpenClaw 4.12's dreaming with Obsidian.. and your memory system becomes flawless

[Tak 🦞 @cherry_mx_reds]

A few more OpenClaw 2026.4.12 changes that didn’t make the first tweet 🦞

🏠 Better local models with bundled LM Studio integration, onboarding, model discovery, and memory-search embeddings
🤖 Better Codex support with the bundled Codex provider, native threads, model discovery, and compaction support
🛡️ Better operator ergonomics with `openclaw exec-policy`, smarter plugin loading, and cleaner remote command discovery
🛠️ Better day-to-day reliability across startup, cron, chat, WhatsApp, Telegram, transcription, and Dreaming

Docs:
LM Studio https://t.co/9XX2S4vf8w
Codex https://t.co/ygSXf9CkSE
exec-policy https://t.co/kqybEkBhyn
plugins https://t.co/9R8h1qI3VB