Latent Space: The AI Engineer Podcast
- Épisodes
- 297
- Parution
- quotidienne
- Dernier épisode
- 10 Nov 2026
À propos du podcast
The main Latent Space podcast: AI engineering, Forward Deployed Engineering, AI for science, and ⚡ Lightning episodes. Other feeds: Engineering and FDE: https://podcast.latent.space/eng.xml; Science: https://podcast.latent.space/science.xml; Misc (Lightning and other shows): https://podcast.latent.space/misc.xml; Firehose (all available shows): https://podcast.latent.space/firehose.xml. Feed directory: https://latent.space/pods
Épisodes 297
Designing for Agents — Zeno Rocha, Resend
swyx had already connected Cloudflare email. Then a coding agent opened a pull request that quietly chose Resend for him. Zeno Rocha, Resend’s founder and CEO, explains what answer engine optimization (AEO) …
Notes de l’épisode
swyx had already connected Cloudflare email. Then a coding agent opened a pull request that quietly chose Resend for him. Zeno Rocha, Resend’s founder and CEO, explains what answer engine optimization (AEO) looks like from the receiving end of that rec...
What Frontier Labs Buy: A Data Deep Dive with Handshake AI — Garrett Lord & Team
Our first deep dive with an AI data company. In roughly a year, Handshake built an AI training business doing nearly $1 billion in gross annualized revenue. What are frontier labs buying? Garrett Lord joins us …
Notes de l’épisode
Our first deep dive with an AI data company. In roughly a year, Handshake built an AI training business doing nearly $1 billion in gross annualized revenue. What are frontier labs buying? Garrett Lord joins us with the people building reinforcement lea...
[One Million AI Engineer Special] How Stanford Teaches AI-Native Engineering — Mihail Eric, Monaco
What do you assign when a coding agent can finish last year’s homework in one prompt? In the second run of Stanford’s CS146S, Mihail Eric brought open-source maintainers into the course. Students have to learn …
Notes de l’épisode
What do you assign when a coding agent can finish last year’s homework in one prompt? In the second run of Stanford’s CS146S, Mihail Eric brought open-source maintainers into the course. Students have to learn an unfamiliar repo, propose a change, and ...
Deep Dive: Anthropic S-1 Myths and Mythos — Jamin Ball, Altimeter
Watch the full show on YouTube: https://www.youtube.com/watch?v=P735f1xlpL0Full show notes and links
Controlling Biology - Fabian Theis, Helmholtz Munich
Fabian Theis has been one of the key players in the various iterations of the Virtual Cell concept and initiatives. It is not hyperbole at all to say that his lab has been pushing the frontier of algorithms to …
Notes de l’épisode
Fabian Theis has been one of the key players in the various iterations of the Virtual Cell concept and initiatives. It is not hyperbole at all to say that his lab has been pushing the frontier of algorithms to understand multi-scale, multi-modal (”mult...
⚡ Behind Latent Space: A Rare Look Inside the Pod | AIEi Shanghai
Watch the full show on YouTube: https://www.youtube.com/watch?v=QmDLDy3ZSNEFull show notes and links
⚡️ The 2026 Software Factory Standard — Zach Lloyd, Warp.dev
Watch the full show on YouTube: https://www.youtube.com/watch?v=LL0YmIyBKSUFull show notes and links
Building Legal Agents When You Can't See the Data - Jacob Lauritzen, CTO of Legora
Legora can’t read a single trace of what its agent does for a lawyer. The data belongs to the law firm’s clients. How do you build and test an agent when you can’t see its work? Jacob Lauritzen is the CTO of …
Notes de l’épisode
Legora can’t read a single trace of what its agent does for a lawyer. The data belongs to the law firm’s clients. How do you build and test an agent when you can’t see its work?
Jacob Lauritzen is the CTO of Legora, one of the fastest-growing companies in legal tech history. The team started in a Stockholm basement with ChatGPT, Swedish law, and a search tool. Today, a lawyer can use Legora to draft and edit Word documents, review 10,000 contracts in a single table, or run due diligence. The agent also coordinates work between lawyers, clients, and other agents. When Legora made its own acquisitions, the team used it for diligence.
What we talked about
• Why Legora resisted adding a model picker for years, and why it finally added one
• Jacob’s estimate that models already do about 60% of legal work well, and why the rest takes a smarter model
• How three engineers and three lawyers build test environments modeled on customers’ work, much like the “worlds” used in reinforcement learning
• A citation problem where the model got it right 70% of the time, then 99% after one release. Legora didn’t have to change anything.
• Why Legora runs everything on Azure and why it doesn’t use ElevenLabs
• Tabular Review, the million-cell spreadsheet the industry copied down to the name
• How intake works, how agents create lists, and how a list can start another agent
• What legal engineers and forward-deployed engineers each do, and who gets to write code
• The 300 Spartans slide Jacob used to argue that 20 engineers would be enough forever. Now there are 100, and he still feels short-handed.
• Why Jacob finds Fable and Opus too chatty for drafting and likes Astra’s concise writing
• Why drafting a long contract is a search problem
• Whether model labs will cut off legal tools the way they cut off coding tools
• What happens to law firm partnerships, the billable hour, and jobs for junior lawyers
Legora is hiring engineers in New York, Stockholm, and London.
Chapters
0:00 Cold open
0:40 Meet Jacob Lauritzen, CTO of Legora
1:05 Starting out as underdogs in a Stockholm basement
1:54 How Legora grew from ChatGPT with Swedish law into a legal agent
4:12 The switch from assistant to agent
5:23 Which models Legora uses and why it added a model picker
7:48 Are today’s models good enough for lawyers?
8:20 What agents couldn’t do nine months ago
9:18 Testing the agent in simulated worlds and a 10,000-file data room
10:07 The evals team and Legora’s 100 legal engineers
11:03 When evals didn’t seem worth it and one release took citations from 70% to 99%
12:18 What legal practice could look like in five to ten years
14:18 Will the law firm partnership model survive?
16:40 What happens to paralegals and junior lawyers?
18:00 The billable hour and why earlier legal tech fell short
19:39 Where the money goes now
22:44 How Legora used its own product for acquisition diligence
23:59 How Swedish and American law firms differ
26:12 Product metrics when you can’t read the traces
27:41 Paraphrasing traces and narrowing failures down to 10 or 20 types
28:42 Why data privacy led Legora to run everything on Azure
30:04 Open-weight models and model arbitrage
30:55 Transcription models and why Legora doesn’t use ElevenLabs
33:33 The agent, Tabular Review, projects, and the Word add-in
34:24 How a lawyer uses Tabular Review
35:51 Why a spreadsheet works and what you learn from the first 10 rows
37:53 How the legal intake bot works in Slack
39:11 How agents create lists and lists start agents
40:15 Building products on those same pieces and acquiring Wexler
42:37 What forward-deployed engineers do at Legora
43:52 How legal engineers and forward-deployed engineers onboard a big client
46:43 What’s next for the forward-deployed team over the coming year
47:24 Why Legora resisted building APIs
49:26 Can the agent be the API?
50:12 The 300 Spartans slide and the plan to stay at 20 engineers
51:32 The bets nobody asked Legora to make
53:05 Post-training open-weight models for legal research
54:05 Search, retrieval, and late interaction
54:51 What makes a good legal agent harness and why drafting depends on search
56:25 Which model writes the best draft?
57:03 Hallucinations and Legora’s citation system
57:41 Do lawyers check the citations?
58:19 MapReduce or one big context window for a million-token contract?
1:00:16 Getting anonymized examples and the idea of buying a law firm for its data
1:01:53 Why Jacob advises against default embeddings
1:02:44 Will lawyers work in Legora or through Claude?
1:03:26 Will the model labs cut Legora off?
1:04:24 Law schools and scholarships for computer science majors
1:05:28 Hiring in New York, Stockholm, and London
1:06:09 Why most work eventually becomes legal work
Guest — Jacob Lauritzen, CTO of Legora
Co-host — swyx, Latent Space
Host — Basil Chatha, Forward Deployed
Building Legal Agents When You Can't See the Data - Jacob Lauritzen, CTO of Legora
Legora can’t read a single trace of what its agent does for a lawyer. The data belongs to the law firm’s clients. How do you build and test an agent when you can’t see its work? Jacob Lauritzen is the CTO of …
Notes de l’épisode
Legora can’t read a single trace of what its agent does for a lawyer. The data belongs to the law firm’s clients. How do you build and test an agent when you can’t see its work? Jacob Lauritzen is the CTO of Legora, one of the fastest-growing companies...
Using Agents for Long-Horizon Financial Work — Aman Singh, Arca
Arca head of AI Aman Singh joins Latent Space head of editorial Richard MacManus at AI Engineer New York, to discuss how Arca is building an AI-native wealth management firm. Singh explains Arca's architecture …
Notes de l’épisode
Arca head of AI Aman Singh joins Latent Space head of editorial Richard MacManus at AI Engineer New York, to discuss how Arca is building an AI-native wealth management firm. Singh explains Arca's architecture, which includes a custom harness and persi...
⚡ Building ChatGPT for Finance — Joseph Kim, OpenAI's Head of Financial Services
Watch the full show on YouTube: https://www.youtube.com/watch?v=v-d1WTqIULsFull show notes and links
Why Agents Love Supabase
AI agents are creating more software—and that changes what a backend needs to do. Supabase co-founders Paul Copplestone and Ant Wilson join swyx to discuss running long-lived workloads alongside the database …
Notes de l’épisode
AI agents are creating more software—and that changes what a backend needs to do. Supabase co-founders Paul Copplestone and Ant Wilson join swyx to discuss running long-lived workloads alongside the database, making schemas easier for agents to underst...
How Anthropic ships the #1 LLM in the World safely: Separating the Brain from the Hands
Katelyn Lesse and Angela Jiang join Latent Space to explain the engineering behind the Claude Platform: launching Opus 5.5, separating the model’s “brain” from the agent’s “hands,” scaling APIs, and building …
Notes de l’épisode
Katelyn Lesse and Angela Jiang join Latent Space to explain the engineering behind the Claude Platform: launching Opus 5.5, separating the model’s “brain” from the agent’s “hands,” scaling APIs, and building reliable managed agents. A new introduction ...
⚡ An Eval for AI Scientists That Knows the Answer Key - Ian Quigley, Leash Bio
Watch the full show on YouTube: https://www.youtube.com/watch?v=vhPCo-8K78UFull show notes and links
Why AI Compute Comes in Rectangles — Erik Bernhardsson, Modal CEO
Warm welcome to Basil Chatha, our newest cohost from the Forward Deployed side of the AI Engineering world! We’ll be ramping up a new show with him and couldn’t pass up an interview with Modal’s CEO Eric on the …
Notes de l’épisode
Warm welcome to Basil Chatha, our newest cohost from the Forward Deployed side of the AI Engineering world! We’ll be ramping up a new show with him and couldn’t pass up an interview with Modal’s CEO Eric on the occasion of their monster Series D! Two y...
The Recommendation Engine for Commodity Traders — Anekha Sokhal, Moshi
Anekha Sokhal, CEO of Moshi, joins swyx to discuss building a recommendation engine for commodity traders, turning market data into useful signals, and designing AI that fits users’ workflows. Watch: YouTube · …
Notes de l’épisode
Anekha Sokhal, CEO of Moshi, joins swyx to discuss building a recommendation engine for commodity traders, turning market data into useful signals, and designing AI that fits users’ workflows. Watch: YouTube · Moshi · Anekha 0:00 AI Engineer New York a...
AI for the Fortune 2000: How Tenex Builds an AI-Native SDLC — Alex Lieberman & CJ Hess
Alex Lieberman and CJ Hess join swyx at AI Engineer New York to discuss Tenex’s approach to AI-native engineering, paying for outcomes, MetaHarness, enterprise AI adoption and rebuilding SaaS. Show notes …
Notes de l’épisode
Alex Lieberman and CJ Hess join swyx at AI Engineer New York to discuss Tenex’s approach to AI-native engineering, paying for outcomes, MetaHarness, enterprise AI adoption and rebuilding SaaS. Show notes: Tenex: https://www.tenex.co/ Building an AI-nat...
The Programmable Data Center — Evan Conrad, SF Compute
This was recorded on the sidelines of the new Compute Trading track at AIE NYC. Catch us next at AIE CODE, our last flagship for the top agentic engineers in the world. In the early days of cloud, former guest …
Notes de l’épisode
This was recorded on the sidelines of the new Compute Trading track at AIE NYC. Catch us next at AIE CODE, our last flagship for the top agentic engineers in the world. In the early days of cloud, former guest Martin Casado made something so disruptive...
🔬 Lab-in-the-Loop at Compute Speed — Ian Quigley, Leash Bio
A few years ago I stumbled upon Leash Bio’s Substack, and was hooked. Be it their Kaggle competition that showed that no, we really haven’t solved protein-ligand binding, or their crazy discovery that knowing a …
Notes de l’épisode
A few years ago I stumbled upon Leash Bio’s Substack, and was hooked. Be it their Kaggle competition that showed that no, we really haven’t solved protein-ligand binding, or their crazy discovery that knowing a molecule’s author is perhaps all you need...
Dyna-2: General Purpose Physical Agents with Hour-Long Autonomy — Jason Ma, Dyna Robotics
Watch along AIE NYC and join us at AIE CODE in SF next month! This episode includes a live demo of the Taku robot that is best enjoyed on YouTube. Last month, Dyna made waves by announcing Dyna-2, a …
Notes de l’épisode
Watch along AIE NYC and join us at AIE CODE in SF next month! This episode includes a live demo of the Taku robot that is best enjoyed on YouTube. Last month, Dyna made waves by announcing Dyna-2, a world-action model pre-trained on one million hours o...
🔬 Why AlphaFold Didn't Solve Protein Folding — Pushmeet Kohli, Google DeepMind & Sal Candido, Biohub
From the Bitter Lesson of AI scaling to the unsolved mysteries of protein folding, Google DeepMind’s Pushmeet Kohli and Biohub’s Sal Candido are rethinking what it takes to build AI that truly understands …
Notes de l’épisode
From the Bitter Lesson of AI scaling to the unsolved mysteries of protein folding, Google DeepMind’s Pushmeet Kohli and Biohub’s Sal Candido are rethinking what it takes to build AI that truly understands biology. In this special panel moderated by Bra...
🔬 Synthesis Superintelligence: from Semiconductors to Superconductors — Periodic Labs’ Liam Fedus and Ekin Dogus Cubuk
It’s hard to believe that Periodic was only launched last September: One year later, it is considered one of the pre-eminent AI scientist labs, with dizzying talent density and astonishing progress in the …
Notes de l’épisode
It’s hard to believe that Periodic was only launched last September: One year later, it is considered one of the pre-eminent AI scientist labs, with dizzying talent density and astonishing progress in the autonomous lab buildout: Most people are famili...
⚡️ Which GPU Clouds Are Actually Good? | ClusterMAX 3.0
Watch the full show on YouTube: https://www.youtube.com/watch?v=MWX36ZYnsm0Full show notes and links
Academia is for Ambition — Alex Zhang, MIT
Last call for regular tickets for AI Engineer NYC! As an exclusive for Latent Space subscribers, the first 30 of you can take a 30% off code if it helps - for new tickets only, no refunds! See you in 2 weeks! …
Notes de l’épisode
Last call for regular tickets for AI Engineer NYC! As an exclusive for Latent Space subscribers, the first 30 of you can take a 30% off code if it helps - for new tickets only, no refunds! See you in 2 weeks! While we tend to cover industry on the pod,...
Why Dwarkesh is Wrong about Computer Use + How OpenAI shipped its Jev competitor in 1 Week
Three months ago Dwarkesh, who has been posting incredible blogs and episodes about RL, posted a framing question for his video essay on RLVR which upset a lot of Computer Use folks: We are no strangers to …
Notes de l’épisode
Three months ago Dwarkesh, who has been posting incredible blogs and episodes about RL, posted a framing question for his video essay on RLVR which upset a lot of Computer Use folks: We are no strangers to learning in public and are no strangers to the...
Claude Code’s Next Era — Thariq Shihipar, Anthropic
We are excited to have Anthropic share their latest AI x Finance work at AI Engineer New York ( https://ai.engineer/nyc/2026 ), coming up in 2 weeks! In case you’ve been under a rock, here’s a non-exhaustive …
Notes de l’épisode
We are excited to have Anthropic share their latest AI x Finance work at AI Engineer New York ( https://ai.engineer/nyc/2026 ), coming up in 2 weeks! In case you’ve been under a rock, here’s a non-exhaustive list of what Anthropic has been shipping sin...
OpenRouter: from Seed to Stripe — with OpenRouter’s Alex Atallah & AMP’s Anjney Midha
From the earliest days of open-weight models to becoming the neutral routing layer for more than 10 million developers, OpenRouter is one of the clearest bets that the future of AI will be multi-model. In this …
Notes de l’épisode
From the earliest days of open-weight models to becoming the neutral routing layer for more than 10 million developers, OpenRouter is one of the clearest bets that the future of AI will be multi-model. In this episode, OpenRouter co-founder & CEO Alex ...
Runway’s WorldPrompt and the Engineering of Real-Time Worlds
Earlier this month, world model company Runway introduced GWM Worlds 2, a research preview that “turns high-fidelity video and audio generation into real-time interactive simulation.” Runway calls this an …
Notes de l’épisode
Earlier this month, world model company Runway introduced GWM Worlds 2, a research preview that “turns high-fidelity video and audio generation into real-time interactive simulation.” Runway calls this an “autoregressive diffusion” model; with autoregr...
🔬 Bio-security is an AI Arms Race - Eric Nguyen (CEO, Radical Numerics)
The OpenAI → Hugging Face attack has people asking “what else do we need to worry about?” and Anthropic’s filters flag two things: cyber-security and biology. The natural question is: what about bio-security …
Notes de l’épisode
The OpenAI → Hugging Face attack has people asking “what else do we need to worry about?” and Anthropic’s filters flag two things: cyber-security and biology. The natural question is: what about bio-security, then? Clem Delangue argues that cyber-warfa...
🔬 An Oscar, Two Asteroids, and the Algorithm in Your sklearn: John Platt on AI for Science
How often do you get to talk to a guest who has both an Academy Award and who invented textbook machine learning algorithms? John Platt has an Oscar, two textbook algorithms, two named asteroids, and an …
Notes de l’épisode
How often do you get to talk to a guest who has both an Academy Award and who invented textbook machine learning algorithms? John Platt has an Oscar, two textbook algorithms, two named asteroids, and an Erdos-Bacon number of 6. This was easily the most...
Voici les 40 derniers épisodes sur 297. Les épisodes plus anciens se trouvent dans le flux du podcast.
Podcasts similaires
Plus de podcasts : Technologies
C’est votre podcast ?
Confirmez-le avec une entrée dans votre flux : vous recevez ici un code, vous l’ajoutez comme podcast:txt dans le canal de votre flux, et nous le vérifions. Votre podcast apparaît ensuite comme « vérifié » sur SoundNode.