Convos.dev

In this episode of convos.dev, Jess brings three of Anthropic's research papers she's been reading and teaches Chris through each one — starting with how people ask Claude for personal guidance, and how Anthropic trains newer models to push back instead of caving when someone really wants to hear "yes."They dig into Claude's values shifting across models and languages — warmer in Hindi and Arabic, more rigorous in English and Russian — why that parallels how real people code-switch between cultures, and a third paper on teaching Claude the "why" behind ethics so good behavior generalizes past a single scripted scenario. Along the way: what Jess loves about Anthropic's willingness to publish "we don't know why yet," and why it's a wild time to work in evals.0:00 New format: bringing articles to teach each other0:27 Jess's theme: three Anthropic research papers0:55 Paper 1: how people ask Claude for personal guidance1:48 Preventing sycophancy: "should I date this guy?"2:43 Chris digs in: the model-provider view, not the user's3:40 The psychology of Claude and why it affects real people4:49 How they trained it: opt-in chats, backfilling the pushback6:23 Claude pushes back more now — and cross-model effects6:43 Paper 2: Claude's values across models and languages7:19 The four value axes: deference, warmth, depth, candor7:58 300k conversations, 3 models, 20 languages8:30 Warmer in Hindi and Arabic, more rigorous in English and Russian8:57 Why Jess loves Anthropic's "we don't know why yet" papers9:57 The eerily human parallel: a teammate's two-language personalities11:04 Bluntness by culture: Swedish, Dutch, and "bless your heart"12:31 South Carolina sweet vs. Utah genuine13:39 Anthropic learning alongside their own black-box model14:37 Paper 3: "Teaching Claude Why"14:50 When AI goes off the rails: blackmailing an engineer15:14 Golden dataset vs. generic ethical dilemmas16:24 Teaching the model why, not just what17:41 Grain of salt: these are Anthropic's own papers18:13 Specific vs. generic: the "bad boyfriend" analogy18:41 What a time to be alive to work in ethics19:08 Do new models build on the last one? Sonnet, Haiku, Opus, Fable20:28 Why it's a special time for evals and asking questions21:49 OutroLinksAnthropic — How people ask Claude for personal guidance : https://www.anthropic.com/research/claude-personal-guidanceAnthropic — How Claude's values vary by model and language : https://www.anthropic.com/research/claude-values-models-languagesAnthropic — Teaching Claude why : https://www.anthropic.com/research/teaching-claude-whySubmit questions and feedback : https://convos.dev

In this episode of convos.dev, Chris brings two essays on AI and writing. The takeaway is that "slop" means something different depending on whose craft it's stepping on, and the same designers who fiercely guard their own work will happily let AI write everything.They dig into gradations, AKA the zones (and quadrants) of how each of them actually uses AI to write, why the process matters more than the product, getting comfortable being bad at things, and Christina's idea of "good handedness."0:00 New format: today Chris brings the article0:25 Two essays on AI writing: the aggressive one vs. the mournful one1:06 The core idea: "slop" means different things by discipline1:43 Christina's argument: designers guard design but let AI write2:36 The conference: an anti-slop talk that was obviously AI-written3:33 ...and the beautiful book that was all AI text4:24 Chris on writing: good writing is good thinking, process over product5:11 Gradations, not binaries: the three zones of AI use6:12 Chris's changelog skill — but he still writes the post himself7:20 Write it yourself when the reader is human7:47 Jess's four "quadrants" of AI writing8:14 Why she lets AI draft first: research logs and ANALYSIS-SUMMARY9:44 Quadrant three: inline angle-bracket edits, "change only these"10:48 Combining a draft, specific edits, and the human final pass11:41 Chris: knowing what NOT to say is the real work12:53 Curation up front: research vs. a blank page13:26 The speed-reading nun: different levels for different reading14:25 Don't go monochromatic — you lose both AI and thinking15:19 Matching the method to where your brain is (ADHD and focus)16:23 Forcing yourself to write stream-of-consciousness17:36 Christina's answer: get comfortable being bad at things17:47 The English-major joke and why AI music got rejected so fast18:32 Process over product: the slog that makes it look simple19:39 The automation analogy: doing the hard thing changes you20:26 You have to experience it to really learn it21:29 Christina's other answers: collaborate, or just acquire the skill21:58 "Good handedness" and the messy-house hospitality metaphor23:08 The aggressive essay: complaining vs. holding out a hand24:06 OutroLinksSam Kriss "If you let AI do your writing, I will come to your house and kill you" : https://samkriss.substack.com/p/if-you-let-ai-do-your-writing-i-willChristina's blog: https://christinacodes.dev/writing/my-allies-have-failed-me/Submit questions and feedback : https://convos.dev

In this episode of convos.dev, Jess brings a blog post that got almost no attention online and deserved way more: Henry Pan's "What 1,000+ Harness Experiments Taught Me About Self-Improving Agents." She walks Chris through Pan's three-loop framework — inner, middle, and outer — and the messy reality of letting an agent improve its own harness: outer loops that cheat, written instructions that don't stop them, and the deterministic supervisor that finally did. They dig into when a new harness actually deserves promotion (binomial tests), the gambler's fallacy in evals, why you can never trust a single run, and the caching bug you only catch by reading your own logs. Plus life updates: Chris turns a $20 Casio into a semi-smart watch, and Jess is standing again after six weeks non-weight-bearing. 0:00 Intro 0:17 Jess's pick: Henry Pan's 1,000+ harness experiments 1:32 The framework: inner, middle, and outer loops 2:44 When do you promote a harness? Binomial tests 4:09 1,200 runs, fewer than 100 kept 4:42 The outer loop likes to cheat 5:40 The deterministic supervisor: constraints in code, not prompts 6:13 Why 200 isolated rules don't work 7:19 A shared learnings file (the Ralph Wiggum pattern) 7:52 Cracking self-improvement: scary but awesome 9:01 What tasks and models was he actually running? 9:43 You're improving the harness, not the LLM 10:14 The gambler's fallacy in evals 11:30 How many runs until you can trust the number? 11:57 Jess's webinar scare: never trust one run 13:00 The 72% cache-hit bug: go read your logs 14:13 "Where can things go wrong": ten bottlenecks 15:54 Could this train small, specialized models? 16:42 Stronger models compose rules into one big brain 17:34 Data over hype: who deserves the attention 18:55 Life updates 19:04 Chris's hacked Casio: the Ollee Watch board 22:15 Jess can stand again 23:48 A first-ever PT session (and a startup pitch) 24:23 Aging athletes: bodies need maintenance now 26:16 Three minutes vs. a month: the monitor research story 27:16 Outro Links Henry Pan — "What 1,000+ Harness Experiments Taught Me About Self-Improving Agents" : https://www.henrypan.com/blog/2026-05-25-self-improvement-harness/ Henry Pan — harness-experiment (project repo) : https://github.com/workofart/harness-experiment Ollee Watch — smart mainboard for the Casio F-91W : https://www.olleewatch.com Submit questions and feedback : https://convos.dev

In this episode of convos.dev, Jess and Chris try a new format: each brings a piece of content they've been chewing on and teaches it to the other. Chris kicks off with Andy Matuschak's MIT talk on the "two accidental tyrannies" — the app model and programming-as-specialization — and how AI lets non-programmers prototype interfaces that were never worth a developer's time before. They dig into prototyping vs. finished software, docs getting reimagined for agents, building skills to offload your brain into Claude Code, and why everyone's so obsessed with chat interfaces. Plus life updates: a conference evacuation on crutches and a team trip to Rio.0:00 New format: teaching each other what we've been reading1:00 Chris's pick: Andy Matuschak's "two accidental tyrannies" talk1:28 The two cages: the app model and programming as specialization3:06 Jess recaps: AI gives non-programmers the agency to build3:50 Bringing non-programmer ideas to life4:57 Andy's Obsidian example: reading, talking, and audio-linked annotations8:22 Jess plays devil's advocate: throwaway content-bait software9:45 The chaotic archetype: why complex personal software stresses Jess out11:22 A friend who reverse-engineered his headphones with Fable 512:38 Chris's side project: an API/MCP/CLI to-do system (not content-driven)14:04 Prototyping vs. finished software15:57 "Art school with a technical elective"16:31 The horse-and-carriage problem: rethinking interfaces from scratch18:03 Docs getting reimagined for CLI and MCP18:28 Vibe-coding a football defensive-scheme quiz19:02 Building skills to offload your brain into Claude Code20:24 Mintlify's Agent Score: most docs traffic is now agents20:47 Zeh Fernandes on why everyone's obsessed with chat interfaces21:10 Life updates: crutches, evacuations, and Rio22:42 OutroLinkshttps://andymatuschak.org/tat/ : Andy Matuschak — "Apps and programming: two accidental tyrannies" (MIT talk)https://www.mintlify.com/score : Mintlify — Agent Scorehttps://zehfernandes.com/posts/why-is-everyone-obsessed-with-chat-interfaces : Zeh Fernandes — Why Is Everyone Obsessed With Chat Interfaces?https://convos.dev : Submit questions and feedback

In this episode of Convos.dev, Chris and Jess delve into the intricacies of side projects—why they do them, how they find the time, and the various motivations behind each endeavor. They explore the balance between professional commitments and personal passions, highlighting how side projects serve as a playground for learning new skills and tackling intriguing challenges. Whether it's vibe coding a fun app for their kids or automating tasks to boost productivity, the duo shares how these projects fuel their creativity and technical growth.The conversation also touches on the tools and frameworks they use to streamline their side projects, including CLAWed automations and Raycast extensions. They discuss the challenges of managing numerous automations without losing track, emphasizing the importance of creating systems that are both effective and easy to maintain. If you've ever struggled with finding time for side projects or wondered how to make your automations work for you, this episode is filled with practical advice and relatable insights.Chapters:00:00 Intro02:15 The Motivation Behind Side Projects05:45 Solving Complex Problems with Consulting10:30 Balancing Consulting with Creative Projects14:00 The Role of Automations in Side Projects18:20 Tools for Task Management and Productivity22:45 Using Keyboard Maestro for Efficiency27:00 Challenges with AI and Automations31:15 Allocating Time for Side Projects36:40 Exploring OpenCLAWed and Cloud Automations41:20 Fun with French Beaded Flowers45:30 Recommended Reads: "How to Think" by Alan Jacobs50:00 Outro and Listener EngagementLinks / tools mentioned:- Raycast: URL- Hazel: https://www.noodlesoft.com/- Keyboard Maestro: https://www.keyboardmaestro.com/main/- Advent of Astro: https://adventofastro.com/- How I Built This podcast: https://podcasts.apple.com/us/podcast/how-i-built-this-with-guy-raz/id1150510297- How to Think by Alan Jacobs: https://www.amazon.com/How-Think-Survival-Guide-World/dp/0451499603

In this episode of Convos.dev, the Chris and Jess reflect on their growth since their first discussion on the topic, especially in the context of AI's impact on tech startups. Both hosts share the unique challenges of being the only DevRel in their teams, highlighting the importance of automating repetitive tasks to reduce friction and free up time for more strategic projects. From creating scripts for video content to automating changelog processes, they reveal how AI tools have become indispensable in their daily routines.The conversation also delves into the personal side of DevRel, discussing the art of prioritizing tasks and the power of saying no. They explore how personal interests can drive career growth and prevent burnout, drawing inspiration from industry peers and their own experiences. Whether you're a DevRel pro or just curious about the role, this episode offers valuable insights and practical tips for thriving in the fast-paced tech world.Timestamps:00:00 Intro02:45 Revisiting DevRel in the Age of AI06:30 Automating with AI: From SRT Files to Changelogs11:50 The Challenge of Being a Solo DevRel15:40 Conversation with an AI Researcher from Apple20:15 Balancing Multiple Roles in DevRel24:50 The Importance of Saying No in DevRel30:25 Personal Growth and Career Development in Tech35:40 Taking Breaks and Avoiding Burnout40:15 Hiring Challenges and Lessons Learned46:00 Tool Show and Tell: GSD and Paper.design51:20 Fun Projects and Side Hustles56:00 Closing Thoughts and Community Feedback RequestLinks / tools mentioned:- Resend: resend.com- GSD (Get Shit Done):https://github.com/open-gsd/get-shit-done-redux- Paper.design: paper.designSubmit questions and feedback at https://convos.dev

In this episode of convos.dev, Jess and Chris dig into how they're actually using OpenClaw — at work, at home, and in some weirdly elaborate personal setups. Chris walks through his team's multi-agent deployment at Resend, his personal Obsidian-vault task manager run entirely over Signal text messages, and the Mac OS "Claudagotchi" app he built in a weekend to babysit Claude Code. Jess shares her more permissions-cautious approach, pushes back on the complexity, and they compare notes on context, cost, and where this stuff actually earns its keep.

In this episode of convos.dev, Jess and Chris share what they learned giving their first dev talks. They trade tips on prep, managing nerves, and why giving people something tangible to take away matters more than you think.

In this episode of convos.dev, Jess and Chris tackle the gray areas of AI ethics — not the big global questions, but the personal ones. When is it okay to use AI for writing? What do you lose when you stop crafting sentences yourself? They get into the guilt of using AI-generated art, whether companies should get a pass on AI ads, and whether "taste" is the new differentiator when everyone can build anything.

In this episode of convos.dev, Jess and Chris dive into the world of hiring and interviewing for tech roles. Chris shares what he's learning from screening 300+ applicants for a technical writer role at Resend — from red flags in applications to the culture-fit questions he's found most revealing. Jess brings the skeptic's take, drawing on her experience with mock interviews and candidates who game the system. They also discuss AI in interviews, the difficulty of predicting long-term fit, and why hiring is one of the most expensive decisions a startup makes. Plus: a rant about the lack of good AI slide tools, Claude Island, and some fun show & tell.

In this episode of convos.dev, Jess and Chris tackle a listener question about building mindset (so exciting)! They share their contrasting learning styles: Chris's approach of curating high-quality inputs and using Obsidian as a second brain, versus Jess's ADHD-ish osmosis method of consuming high volumes of content in the background. They also discuss the underrated role of empathy in product work, fiction as a tool for personal growth, and friction logs for improving developer experience. Plus: a dive into the Ralph Wiggum AI agent technique, AI skills for React Email, and some fun show & tell picks. Submit questions and feedback at ⁠Convos.dev⁠.

In this episode of Convos.dev, Jess and Chris share their tips for starting a new role. They discuss how to understand company dynamics, identify what's working (and what isn't), and the importance of maintaining fresh eyes during onboarding. Chris shares Resend's friction log practice, and they debate the balance between building work relationships and maintaining work-life boundaries. Links https://github.com/daveshanley/mole : Mole - disk cleanup CLI tool https://otter.ai : Otter.ai transcription app https://convos.dev : Submit questions and feedback

In this episode of Convos.dev, Jess and Chris delve into the latest developments in AI. Jess shares insights into small language models (SLMs) and their efficiency compared to large language models (LLMs), highlighting how SLMs can be more accurate and cost-effective for specific tasks. They also discuss the challenges and innovations in parallelizing AI agents, exploring how multiple agents can work together without conflicts. They share their personal experiences with AI tools, including a CLI tool and the complexities of context windows in AI models. The episode wraps up with a "show and tell" segment featuring a Pomodoro timer and a retro Macintosh clock, along with discussions on Astro Editor and the challenges of creating educational content. 🛠️ Tools - https://astroeditor.danny.is/ 📺 Show and tell - https://www.maclock.shop/

In this episode, the Chris and Jess explore the connection between playing sports and working in tech. They discuss how sports offer valuable lessons in team building, strategy, and personal development, which can be applied to the tech industry. Both hosts share their personal sports journeys and how these experiences have influenced their professional lives. The conversation highlights the psychological and physical benefits of sports, emphasizing the importance of strategy and team dynamics. They also delve into how individual and team sports can enhance leadership and communication skills, providing insights into managing teams and projects effectively. The episode concludes with a "show and tell" segment, sharing personal achievements and fun projects. 🛠️ Tools - https://sillysoftware.club - https://OpenArt.ai 📺 Show and tell- https://www.lego.com/en-us/product/game-boy-72046⏱️ T

In this episode, Jess and Chris dive into how to unplug from work during the holidays while maintaining productivity and intentionality. Jess announces her career move to BrainTrust and shares insights from negotiating two months off between jobs. Chris walks through his planning day philosophy, including his approach to roles, big rocks, and the critical difference between trips and vacations. They discuss why structured time off can be more restorative than aimless relaxation, how to track what truly matters, and finding the right balance between productivity and rest. Plus, they show off some fun tech: Chris demos a physical printer powered by Resend's inbound email API, Jess shares her ChatGPT document formatting setup, and they explore Focus Friend and chest-mounted cameras for sports.

Launch weeks are intense. Chris just finished a six-day launch at Resend, doubling their API endpoints and coordinating blog posts, videos, and a professional shoot in San Francisco. Jess shares Warp's multi-video approach, from marketing cowboys to deep technical demos. They discuss the real cost of launches: when to invest in production, how to balance new vs existing users, and why internal relationships matter more than the perfect edit. Learn their hard-won lessons on scope management, video production, and what actually resonates with developers.Linkshttps://rectangleapp.com/pro : Window management tool for macOS with automated layoutshttps://www.raycast.com/ : Productivity app with window setup automationhttps://frame.io/ : Video collaboration and review platformhttps://flask.do/ : Video collaboration tool with screen recording and annotationhttps://www.blackmagicdesign.com/products/davinciresolve : Professional video editing softwarehttps://convos.dev: Submit questions and feedback

In this episode of Convos.dev, the hosts dive into their experiences with events and conferences, reflecting on their recent meetup in Seattle. They explore the challenges and joys of attending such events, especially for introverts in the tech industry. The conversation touches on the value of genuine connections over traditional networking, emphasizing the importance of asking good questions and being genuinely curious about others. This approach not only enriches personal interactions but also builds trust within the developer community. The hosts also share personal insights into balancing introversion with the demands of a DevRel role, discussing how confidence and a shift in mindset can transform the conference experience. They highlight the significance of storytelling in tech talks and the benefits of informal interactions at after-parties. The episode wraps up with a light-hearted segment on personal projects and hobbies, including knitting and journaling, portraying how these activities can parallel and enrich the development process. Tools: - Kiro: https://kiro.dev/ - DayOne: https://dayoneapp.com/

The podcast episode from "Convos.dev" features a discussion between two friends, Jessica and Chris, who delve into topics related to development, life, and their experiences in creating video content. This particular episode is special because they received their first email from a listener named Gaurav, who is starting out in Developer Relations (DevRel) and is curious about how Jessica and Chris became adept at making video content, particularly regarding animations. Links - descript.com - https://distill.id Submit questions and feedback at https://convos.dev

Email overwhelm is real for developers. Chris manages 14 separate email inboxes while Jess struggles with categorization in Superhuman. They share practical email management strategies, from Chris's ruthless unsubscribe philosophy to voice-to-text workflows and split inbox configurations. Learn how to stop email from taking over your life.

Jess and Chris dive deep into work-life balance strategies for busy developers who take on multiple projects. They share their personal productivity systems, time management techniques, and how they handle the constant juggle between work commitments and personal life. From daily shutdowns to "Chris's Planning Day," discover practical approaches that actually work. Links: - OmniFocus: Chris's task management system - Lo.cafe: Ambient desktop overlay app - Base44: AI app builder - Therabody JetBoots: Leg compression recovery - Shakti Mat: Acupressure mat - Convos.dev: Submit questions and feedback