#codingagents — Public Fediverse posts
Live and recent posts from across the Fediverse tagged #codingagents, aggregated by home.social.
-
Detailed plans can make coding agents look aligned while hiding guesses.
Architectural probes do the opposite: fake software that reveals structure before implementation, then evolves step by step.
https://amolnotes.substack.com/p/stop-planning-start-probing-and-evolving
#AI #CodingAgents #agenticengineering #vibe_coding #software #programming
-
Launch HN: Runtime (YC P26) – Sandboxed coding agents for everyone on a team
#HackerNews #LaunchHN #Runtime #SandboxedCoding #YC #P26 #CodingAgents
-
OpenClaw's $1.3M OpenAI Bill Highlights AI Cost Escalation
OpenClaw spent $1.3M on OpenAI API for coding agents. This shows high AI costs and impacts software development roles. What happens next?
#OpenAI, #AICosts, #CodingAgents, #TechNews, #SoftwareDevelopment
https://newsletter.tf/openai-api-costs-1-3m-for-coding-agents/
-
One project, OpenClaw, spent $1.3 million on OpenAI's API in just one month. This is a huge amount and shows how much AI is costing.
#OpenAI, #AICosts, #CodingAgents, #TechNews, #SoftwareDevelopment
https://newsletter.tf/openai-api-costs-1-3m-for-coding-agents/ -
The real bottleneck for AI coding agents isn’t model capability but your verification infrastructure. 🛠️
When your agents crash while humans cope, it is often a sign of ""AI slop"" caused by a lack of intent before implementation. 📉 💡
By adopting spec-driven development and the eight pillars of verification, you can finally make those coding agents reliable. 🎯
👉 https://developer.upsun.com/posts/ai/making-coding-agents-reliable
-
InsForge – Open-source Heroku for coding agents
https://github.com/InsForge/InsForge
#HackerNews #InsForge #OpenSource #Heroku #CodingAgents #CloudDevelopment
-
It turns out that stuffing your AGENTS.md file with every bit of info you can find might actually be hurting your coding agent performance. 📉
New research suggests that the redundancy problem is real and that building context files incrementally is a much smarter approach. 💡
Learn why less is more and how to build context files that actually work in our latest breakdown. 👉 https://developer.upsun.com/posts/ai/agents-md-less-is-more
-
It turns out that stuffing your AGENTS.md file with every bit of info you can find might actually be hurting your coding agent performance. 📉
New research suggests that the redundancy problem is real and that building context files incrementally is a much smarter approach. 💡
Learn why less is more and how to build context files that actually work in our latest breakdown. 👉 https://developer.upsun.com/posts/ai/agents-md-less-is-more
-
It turns out that stuffing your AGENTS.md file with every bit of info you can find might actually be hurting your coding agent performance. 📉
New research suggests that the redundancy problem is real and that building context files incrementally is a much smarter approach. 💡
Learn why less is more and how to build context files that actually work in our latest breakdown. 👉 https://developer.upsun.com/posts/ai/agents-md-less-is-more
-
It turns out that stuffing your AGENTS.md file with every bit of info you can find might actually be hurting your coding agent performance. 📉
New research suggests that the redundancy problem is real and that building context files incrementally is a much smarter approach. 💡
Learn why less is more and how to build context files that actually work in our latest breakdown. 👉 https://developer.upsun.com/posts/ai/agents-md-less-is-more
-
It turns out that stuffing your AGENTS.md file with every bit of info you can find might actually be hurting your coding agent performance. 📉
New research suggests that the redundancy problem is real and that building context files incrementally is a much smarter approach. 💡
Learn why less is more and how to build context files that actually work in our latest breakdown. 👉 https://developer.upsun.com/posts/ai/agents-md-less-is-more
-
"For the last decade, fast-to-ship beat fast-to-run. Not anymore. [...] AI got good at the hard languages." by Noah Mitchem
https://medium.com/@NMitchem/if-ai-writes-your-code-why-use-python-bf8c4ba1a055
#python #rustlang #golang #artificialintelligence #codingagents
-
"For the last decade, fast-to-ship beat fast-to-run. Not anymore. [...] AI got good at the hard languages." by Noah Mitchem
https://medium.com/@NMitchem/if-ai-writes-your-code-why-use-python-bf8c4ba1a055
#python #rustlang #golang #artificialintelligence #codingagents
-
"For the last decade, fast-to-ship beat fast-to-run. Not anymore. [...] AI got good at the hard languages." by Noah Mitchem
https://medium.com/@NMitchem/if-ai-writes-your-code-why-use-python-bf8c4ba1a055
#python #rustlang #golang #artificialintelligence #codingagents
-
"For the last decade, fast-to-ship beat fast-to-run. Not anymore. [...] AI got good at the hard languages." by Noah Mitchem
https://medium.com/@NMitchem/if-ai-writes-your-code-why-use-python-bf8c4ba1a055
#python #rustlang #golang #artificialintelligence #codingagents
-
"For the last decade, fast-to-ship beat fast-to-run. Not anymore. [...] AI got good at the hard languages." by Noah Mitchem
https://medium.com/@NMitchem/if-ai-writes-your-code-why-use-python-bf8c4ba1a055
#python #rustlang #golang #artificialintelligence #codingagents
-
Is building a SKILL actually better than writing an LLM enabled CLI? 🤔
Pure Java gives you total control and performance, but it’s often highly opinionated. Now that I’m building a code tutorial SKILL, the "coding agent" takes the wheel.
Is the flexibility worth the trade-off? Documenting my journey here:
-
Is building a SKILL actually better than writing an LLM enabled CLI? 🤔
Pure Java gives you total control and performance, but it’s often highly opinionated. Now that I’m building a code tutorial SKILL, the "coding agent" takes the wheel.
Is the flexibility worth the trade-off? Documenting my journey here:
-
Is building a SKILL actually better than writing an LLM enabled CLI? 🤔
Pure Java gives you total control and performance, but it’s often highly opinionated. Now that I’m building a code tutorial SKILL, the "coding agent" takes the wheel.
Is the flexibility worth the trade-off? Documenting my journey here:
-
Is building a SKILL actually better than writing an LLM enabled CLI? 🤔
Pure Java gives you total control and performance, but it’s often highly opinionated. Now that I’m building a code tutorial SKILL, the "coding agent" takes the wheel.
Is the flexibility worth the trade-off? Documenting my journey here:
-
Is building a SKILL actually better than writing an LLM enabled CLI? 🤔
Pure Java gives you total control and performance, but it’s often highly opinionated. Now that I’m building a code tutorial SKILL, the "coding agent" takes the wheel.
Is the flexibility worth the trade-off? Documenting my journey here:
-
🤖 Coding agents assume silently, overengineer, and touch code you never asked them to. These aren't bugs — it's their nature.
I break down Karpathy's 4 principles (107k ⭐) to keep them in check: think before coding, simplicity first, surgical changes, and goal-driven execution.
https://www.cosmoscalibur.com/en/blog/2026/guia-de-comportamiento-para-agentes-de-codigo
-
🤖 Coding agents assume silently, overengineer, and touch code you never asked them to. These aren't bugs — it's their nature.
I break down Karpathy's 4 principles (107k ⭐) to keep them in check: think before coding, simplicity first, surgical changes, and goal-driven execution.
https://www.cosmoscalibur.com/en/blog/2026/guia-de-comportamiento-para-agentes-de-codigo
-
🤖 Coding agents assume silently, overengineer, and touch code you never asked them to. These aren't bugs — it's their nature.
I break down Karpathy's 4 principles (107k ⭐) to keep them in check: think before coding, simplicity first, surgical changes, and goal-driven execution.
https://www.cosmoscalibur.com/en/blog/2026/guia-de-comportamiento-para-agentes-de-codigo
-
🤖 Coding agents assume silently, overengineer, and touch code you never asked them to. These aren't bugs — it's their nature.
I break down Karpathy's 4 principles (107k ⭐) to keep them in check: think before coding, simplicity first, surgical changes, and goal-driven execution.
https://www.cosmoscalibur.com/en/blog/2026/guia-de-comportamiento-para-agentes-de-codigo
-
🤖 Coding agents assume silently, overengineer, and touch code you never asked them to. These aren't bugs — it's their nature.
I break down Karpathy's 4 principles (107k ⭐) to keep them in check: think before coding, simplicity first, surgical changes, and goal-driven execution.
https://www.cosmoscalibur.com/en/blog/2026/guia-de-comportamiento-para-agentes-de-codigo
-
Oh, rejoice! 🎉 The age-old dream of turning coding agents into glorified cloud hamsters has arrived! Just when we thought laptops couldn't live without them, Mistral Medium 3.5 boldly sends them into the cloud abyss, where they valiantly notify you upon completing their inscrutable magic. 🚀✨
https://mistral.ai/news/vibe-remote-agents-mistral-medium-3-5 #cloudcomputing #codingagents #Mistral3.5 #techinnovation #AIadventure #HackerNews #ngated -
Oh, rejoice! 🎉 The age-old dream of turning coding agents into glorified cloud hamsters has arrived! Just when we thought laptops couldn't live without them, Mistral Medium 3.5 boldly sends them into the cloud abyss, where they valiantly notify you upon completing their inscrutable magic. 🚀✨
https://mistral.ai/news/vibe-remote-agents-mistral-medium-3-5 #cloudcomputing #codingagents #Mistral3.5 #techinnovation #AIadventure #HackerNews #ngated -
Oh, rejoice! 🎉 The age-old dream of turning coding agents into glorified cloud hamsters has arrived! Just when we thought laptops couldn't live without them, Mistral Medium 3.5 boldly sends them into the cloud abyss, where they valiantly notify you upon completing their inscrutable magic. 🚀✨
https://mistral.ai/news/vibe-remote-agents-mistral-medium-3-5 #cloudcomputing #codingagents #Mistral3.5 #techinnovation #AIadventure #HackerNews #ngated -
Oh, rejoice! 🎉 The age-old dream of turning coding agents into glorified cloud hamsters has arrived! Just when we thought laptops couldn't live without them, Mistral Medium 3.5 boldly sends them into the cloud abyss, where they valiantly notify you upon completing their inscrutable magic. 🚀✨
https://mistral.ai/news/vibe-remote-agents-mistral-medium-3-5 #cloudcomputing #codingagents #Mistral3.5 #techinnovation #AIadventure #HackerNews #ngated -
Oh, rejoice! 🎉 The age-old dream of turning coding agents into glorified cloud hamsters has arrived! Just when we thought laptops couldn't live without them, Mistral Medium 3.5 boldly sends them into the cloud abyss, where they valiantly notify you upon completing their inscrutable magic. 🚀✨
https://mistral.ai/news/vibe-remote-agents-mistral-medium-3-5 #cloudcomputing #codingagents #Mistral3.5 #techinnovation #AIadventure #HackerNews #ngated -
Am 11. Mai haben wir wieder zwei Knallerthemen bei der MTUG:
💡 Visual Editing in TYPO3: wird das jetzt endlich der große Wurf für Frontend Editing in TYPO3? @kanti
💡 Vibecoding ohne Blutvergießen — Sicherheit bei AI Coding Agents: Werkzeuge im Agentur-Alltag @kkugelmannhttps://www.meetup.com/de-de/munich-typo3-user-group/events/314541079/
-
Am 11. Mai haben wir wieder zwei Knallerthemen bei der MTUG:
💡 Visual Editing in TYPO3: wird das jetzt endlich der große Wurf für Frontend Editing in TYPO3? @kanti
💡 Vibecoding ohne Blutvergießen — Sicherheit bei AI Coding Agents: Werkzeuge im Agentur-Alltag @kkugelmannhttps://www.meetup.com/de-de/munich-typo3-user-group/events/314541079/
-
Am 11. Mai haben wir wieder zwei Knallerthemen bei der MTUG:
💡 Visual Editing in TYPO3: wird das jetzt endlich der große Wurf für Frontend Editing in TYPO3? @kanti
💡 Vibecoding ohne Blutvergießen — Sicherheit bei AI Coding Agents: Werkzeuge im Agentur-Alltag @kkugelmannhttps://www.meetup.com/de-de/munich-typo3-user-group/events/314541079/
-
Am 11. Mai haben wir wieder zwei Knallerthemen bei der MTUG:
💡 Visual Editing in TYPO3: wird das jetzt endlich der große Wurf für Frontend Editing in TYPO3? @kanti
💡 Vibecoding ohne Blutvergießen — Sicherheit bei AI Coding Agents: Werkzeuge im Agentur-Alltag @kkugelmannhttps://www.meetup.com/de-de/munich-typo3-user-group/events/314541079/
-
DeepSeek-V4: Low-Cost Logic via Hybrid Attention Architectures Presentational View Introduction There is an evident inclination toward novel innovations that incorporate unique structural modificat...
#open-weight-model #agentic-search #deepseek-v4 #hybrid-attention #coding-agents
Origin | Interest | Match -
Bridging ArcGIS Pro and AI: Danny McVey’s arcgispro-cli gives #ArcGISPro a #CLI bridge to #AI #codingAgents, exporting project structure including maps, layers, toolboxes, and geodatabases to a machine-readable format. The open-source tool enables working with real GIS...
https://spatialists.ch/posts/2026/04/19-bridging-arcgis-pro-and-ai/ #GIS #GISchat #geospatial #SwissGIS -
Bridging ArcGIS Pro and AI: Danny McVey’s arcgispro-cli gives #ArcGISPro a #CLI bridge to #AI #codingAgents, exporting project structure including maps, layers, toolboxes, and geodatabases to a machine-readable format. The open-source tool enables working with real GIS...
https://spatialists.ch/posts/2026/04/19-bridging-arcgis-pro-and-ai/ #GIS #GISchat #geospatial #SwissGIS -
Bridging ArcGIS Pro and AI: Danny McVey’s arcgispro-cli gives #ArcGISPro a #CLI bridge to #AI #codingAgents, exporting project structure including maps, layers, toolboxes, and geodatabases to a machine-readable format. The open-source tool enables working with real GIS...
https://spatialists.ch/posts/2026/04/19-bridging-arcgis-pro-and-ai/ #GIS #GISchat #geospatial #SwissGIS -
FLOSS Weekly Episode 868: Remove the Noodles
https://fed.brid.gy/r/https://hackaday.com/2026/04/22/floss-weekly-episode-868-remove-the-noodles/
-
FLOSS Weekly Episode 868: Remove the Noodles
https://fed.brid.gy/r/https://hackaday.com/2026/04/22/floss-weekly-episode-868-remove-the-noodles/
-
Google DeepMind bündelt Forschung und Ingenieurswesen in einem spezialisierten Strike-Team für autonome KI-Coding-Modelle.
Das Ziel ist das Einholen von Anthropic. Sergey Brin verpflichtet alle Gemini-Ingenieure, ab sofort interne Agenten für Entwicklungsaufgaben zu nutzen. Langfristig soll so die KI-Grundlagenforschung automatisiert werden.
#GoogleDeepMind #Anthropic #CodingAgents #LLM #News
https://www.all-ai.de/news/news26/google-deepmind-spezialteam -
Google DeepMind bündelt Forschung und Ingenieurswesen in einem spezialisierten Strike-Team für autonome KI-Coding-Modelle.
Das Ziel ist das Einholen von Anthropic. Sergey Brin verpflichtet alle Gemini-Ingenieure, ab sofort interne Agenten für Entwicklungsaufgaben zu nutzen. Langfristig soll so die KI-Grundlagenforschung automatisiert werden.
#GoogleDeepMind #Anthropic #CodingAgents #LLM #News
https://www.all-ai.de/news/news26/google-deepmind-spezialteam -
Bridging ArcGIS Pro and AI: Danny McVey’s arcgispro-cli gives #ArcGISPro a #CLI bridge to #AI #codingAgents, exporting project structure including maps, layers, toolboxes, and geodatabases to a machine-readable format. The open-source tool enables working with real GIS...
https://spatialists.ch/posts/2026/04/19-bridging-arcgis-pro-and-ai/ #GIS #GISchat #geospatial #SwissGIS -
Bridging ArcGIS Pro and AI: Danny McVey’s arcgispro-cli gives #ArcGISPro a #CLI bridge to #AI #codingAgents, exporting project structure including maps, layers, toolboxes, and geodatabases to a machine-readable format. The open-source tool enables working with real GIS...
https://spatialists.ch/posts/2026/04/19-bridging-arcgis-pro-and-ai/ #GIS #GISchat #geospatial #SwissGIS -
Bridging ArcGIS Pro and AI: Danny McVey’s arcgispro-cli gives #ArcGISPro a #CLI bridge to #AI #codingAgents, exporting project structure including maps, layers, toolboxes, and geodatabases to a machine-readable format. The open-source tool enables working with real GIS...
https://spatialists.ch/posts/2026/04/19-bridging-arcgis-pro-and-ai/ #GIS #GISchat #geospatial #SwissGIS -
Most teams still treat system prompts like internal docs for humans.
That breaks fast with coding agents.
If the prompt is weak, the agent does not fail politely. It invents files, skips discovery, and makes risky edits with too much confidence.
I wrote down a practical way to review these prompts before they hit production: grounding, continuity, safety, decomposition, and efficiency.
https://www.the-main-thread.com/p/bob-meta-scorecard-agent-system-prompts-production
-
Most teams still treat system prompts like internal docs for humans.
That breaks fast with coding agents.
If the prompt is weak, the agent does not fail politely. It invents files, skips discovery, and makes risky edits with too much confidence.
I wrote down a practical way to review these prompts before they hit production: grounding, continuity, safety, decomposition, and efficiency.
https://www.the-main-thread.com/p/bob-meta-scorecard-agent-system-prompts-production
-
Most teams still treat system prompts like internal docs for humans.
That breaks fast with coding agents.
If the prompt is weak, the agent does not fail politely. It invents files, skips discovery, and makes risky edits with too much confidence.
I wrote down a practical way to review these prompts before they hit production: grounding, continuity, safety, decomposition, and efficiency.
https://www.the-main-thread.com/p/bob-meta-scorecard-agent-system-prompts-production
-
@lucasmeijer has given an introductory talk about pi.dev. The first half is a pretty good summary of what I've learned in the past 3 months about working with coding agents. The second half made me even more curious about pi.
Lucas' exasperated "Claude, the answer to question 16 is YES" cracked me up. 😆