Like

Liked GitHub - gjtorikian/paty: The most human-like AI agent you'll ever use. It insists on manners, gets distracted mid-task, sometimes gives up entirely, occasionally claims it did something when it didn't, ignores its own output, and starts every session already feeling a bit off.
Post details
The most human-like AI agent you'll ever use. It insists on manners, gets distracted mid-task, sometimes gives up entirely, occasionally claims it did something when it didn't, ignores it...

by Jamie Tanna's profile image Jamie Tanna . #shitpost #ai.

 Listen

Listened to OpenAI and Codex with Thibault Sottiaux and Ed Bayes - Software Engineering Daily by SEDaily 
Post details
AI coding agents are rapidly reshaping how software is built, reviewed, and maintained. As large language model capabilities continue to increase, the bottleneck in software development is shifting away from code generation toward planning, review, deployment, and coordination. This shift is driving a new class of agentic systems that operate inside constrained environments, reason over

by Jamie Tanna's profile image Jamie Tanna .

 Listen

Listened to Raising An Agent: Episode 9
Post details
Quinn and Thorsten are back! It's been a while since they published a Raising An Agent episode and in this this episode, they discuss how everything seems to have changed again with Gemini 3 and Opus 4.5 and what comes after — the assistant is dead, long live the factory.

by Jamie Tanna's profile image Jamie Tanna .

 Listen

Listened to Raising An Agent: Episode 8
Post details
In this episode of Raising an Agent, Beyang and Camden dive into how the Amp team evaluates models for agentic coding. They break down why tool calling is the key differentiator, what went wrong with Gemini Pro, and why open models like K2 and Qwen are promising but not ready as main drivers. They share first impressions of GPT-5, explore the idea of alloying models, and explain why qualitative “vibe checks” often matter more than benchmarks. If you want to understand how Amp thinks about model selection, subagents, and the future of coding with agents, this episode has you covered.

by Jamie Tanna's profile image Jamie Tanna .

 Listen

Listened to Raising An Agent: Episode 7
Post details
In this episode, Beyang and Thorsten discuss strategies for effective agentic coding, including the 101 of how it's different from coding with chat LLMs, the key constraint of the context window, how and where subagents can help, and the new oracle subagent which combines multiple LLMs. 00:53 Intros 03:35 How coding with agents is very different from coding with prior AI tools that use chat LLMs 10:46 Example of an agentic coding run to fix a simple issue 14:28 Example of debugging an issue with an MCP server 22:05 Example of unifying two build scripts that share logic 25:24 How context window size has emerged as a key constraint on agentic automation 31:16 Why it's best to focus on one thing at a time per agentic thread 33:24 Subagents and how they help extend the effective context window 34:04 The Amp codebase search subagent 38:48 General-purpose subagents 44:20 When to use subagents 47:04 The oracle subagent and o3 51:47 Multi-model agents and using the best model for each job

by Jamie Tanna's profile image Jamie Tanna .

 Listen

Listened to Raising An Agent: Episode 5
Post details
In this episode, Beyang interviews Thorsten and Quinn to unpack what has happened in the world of Amp in the last five weeks: how predictions played out, how working with agents shaped how they write code, how agents are and will influence model development, and, of course, all the things that have been shipped in Amp.

by Jamie Tanna's profile image Jamie Tanna .

 Like

Liked Jade (@JadedBlueEyes@tech.lgbt)
Post details
Cloudflare just published a vibe coded blog post claiming they implemented Matrix on cloudflare workers. They didn't, their post and README is AI generated and the code doesn't do any of the core parts of matrix that make it secure and interoperable. Instead it's littered with 'TODO: Check authorisation' and similar https://blog.cloudflare.com/serverless-matrix-homeserver-workers/

by Jamie Tanna's profile image Jamie Tanna .

 Like

Liked Jan Lehnardt :couchdb: (@janl@narrativ.es)
Post details
Look, all of these can be true: - the fosdem organisers cannot be trusted to enforce a CoC violation - they have no covid safety concept that would allow at-risk folks to attend safely - open hard- and software is the only way forward in this increasingly enshittified and enclosed software world - the list of people I’d love to meet who are attending is a mile long - building communities is more important than ever while the forces in power enshrine divide and conquer into the fabric of our societies - meeting in-person is effective to forge new bonds and deepen existing relationships - we must continue to demand better from organisers - see you on Brussels

by Jamie Tanna's profile image Jamie Tanna . #fosdem.

 Like

Liked jb, sharkey edition (@jb)
Post details
Did someone post something? It's on mastodon.social. It's literally on booping.synth.download. It's maybe in wetdry.world. It's literally on gts.apicrim.es. You can probably find it on app.wafrn.net. Dude it's on shrimp.starlightnet.work. It's a infosec.exchange original. Check out mas.to for it. You'll find it on hachyderm.io. It's definitely on oomfie.city. Look for it on tech.lgbt. It's over on yeen.town. You can see it on waf.moe. It's been shared on akko.wtf. Go peek at fuzzies.wtf. It's trending on transfem.social. You can catch it on eepy.moe. Browse over to lethallava.land. It's on $INSTANCE$host$. You can read it on $INSTANCE$host$. You can go to $INSTANCE$host$ and like it. Log onto $INSTANCE$host$ right now. Go to $INSTANCE$host$. Dive into $INSTANCE$host$. You can $INSTANCE$host$ it. It's on $INSTANCE$host$. $INSTANCE$host$ has it for you. $INSTANCE$host$ has it for you.

by Jamie Tanna's profile image Jamie Tanna .

 Repost

Reposted jb, sharkey edition (@jb)
Post details
Did someone post something? It's on mastodon.social. It's literally on booping.synth.download. It's maybe in wetdry.world. It's literally on gts.apicrim.es. You can probably find it on app.wafrn.net. Dude it's on shrimp.starlightnet.work. It's a infosec.exchange original. Check out mas.to for it. You'll find it on hachyderm.io. It's definitely on oomfie.city. Look for it on tech.lgbt. It's over on yeen.town. You can see it on waf.moe. It's been shared on akko.wtf. Go peek at fuzzies.wtf. It's trending on transfem.social. You can catch it on eepy.moe. Browse over to lethallava.land. It's on $INSTANCE$host$. You can read it on $INSTANCE$host$. You can go to $INSTANCE$host$ and like it. Log onto $INSTANCE$host$ right now. Go to $INSTANCE$host$. Dive into $INSTANCE$host$. You can $INSTANCE$host$ it. It's on $INSTANCE$host$. $INSTANCE$host$ has it for you. $INSTANCE$host$ has it for you.

by Jamie Tanna's profile image Jamie Tanna .

 Listen

Listened to Raising An Agent: Episode 4
Post details
Thorsten and Quinn talk about the future of programming and whether code will still be as valuable in the future, how maybe the GitHub contribution graph is already worthless, how LLMs can free us from the tyranny of input boxes, and how conversations with an agent might be a better record of how a code change came to be than git commit tools. They also share where it works and simply doesn't work.

by Jamie Tanna's profile image Jamie Tanna .

 Listen

Listened to Raising An Agent: Episode 3
Post details
Quinn and Thorsten start by sharing how reviews are still very much needed when using AI to code and how it changes the overall flow you're in when coding with an agent. They also talk about a very important question they face: how important is code search, in its current form, in the age of AI agents?

by Jamie Tanna's profile image Jamie Tanna .

 Listen

Listened to Raising An Agent: Episode 2
Post details
Thorsten and Quinn talk about how different agentic programming is from normal programming and how the mindset has to adapt to it. One thing they discuss is that having a higher-level architectural understanding is still very important, so that the agent can fill in the blanks. They also talk about how, surprisingly, the models are really, really good when they have inputs that a human would normally get. Most importantly, they share the realization that subscription-based pricing might make bad agentic products.

by Jamie Tanna's profile image Jamie Tanna .

 Listen

Listened to Raising An Agent: Episode 1
Post details
In the first episode of Raising an Agent, Quinn and Thorsten kick things off by sharing a lot of wow-moments they experienced after getting the agent at the heart of Amp into a working state. They talk about how little is actually needed to create an agent and how magical the results are when you give a model the right tools, unlimited tokens, and feedback. That might be the biggest surprise: how many previous assumptions feel outdated when you see an agent explore a codebase on its own.

by Jamie Tanna's profile image Jamie Tanna .

 Listen

Listened to Ep. 5 | The ethics of AI for software engineers by Overcommitted | Software Engineering and Tech Careers Insights
Post details
The crew gets philosophical about the ethics of building Artificial Intelligence systems. Are software engineers going to be replaced? Is it ethical to build AI systems?Links⁠SuperintelligenceBlog: Less WrongZizian cultThinking in SystemsDwarkesh Patel podChatGPT Medical Diagnosis StudyMCP Server Claude Desktop TutorialMCP Podcast⁠Overcommitted on Bluesky⁠Hosts⁠Overcommitted.dev⁠Brittany Ellich: ⁠https://brittanyellich.com⁠Eggyhead: ⁠https://github.com/eggyhead⁠Jonathan Tamsut: ⁠https://jtamsut.substack.com⁠

by Jamie Tanna's profile image Jamie Tanna .

 Listen

Listened to Ep. 4 | How we use AI as software engineers by Overcommitted | Software Engineering and Tech Careers Insights
Post details
The crew chat about our experience using AI right now as software engineers (which is subject to change even by the time this episode airs). Including an overview of our current thoughts on the AI landscape, what tools we use for which tasks, and our thoughts on what we are excited about for the future!LinksThe S in MCP Stands for SecurityBook: The Scaling EraOvercommitted on BlueskyHostsOvercommitted.devBethany Janos: https://github.com/bethanyj28Brittany Ellich: https://brittanyellich.comEggyhead: https://github.com/eggyheadJonathan Tamsut: https://jtamsut.substack.com

by Jamie Tanna's profile image Jamie Tanna .

 Like

Liked Hugo bloggin' with Obsidian like a boss by Jerod Santo 
Post details
One of my goals when I refreshed my blog was to publish with Hugo, but write with Obsidian. Turns out that was as simple as: ln -s ~/src/jerodsanto/net/content/posts ~/Dropbox/obsidian/Jerod/blog That’s a good start, but once I’m writing in Obsidian
 I don’t exactly want to leave. There’s friction when managing various Hugo tasks from a separate terminal session. So, I had Claude Code write me an Obsidian plugin to add those features. It’s called Hugo Boss1 and I submitted it to the Obsidian community plugins list, so hopefully you’ll be able to install it from there soon2. The plugin adds a button that has four features today:

by Jamie Tanna's profile image Jamie Tanna .