shakedown.social is one of the many independent Mastodon servers you can use to participate in the fediverse.
A community for live music fans with roots in the jam scene. Shakedown Social is run by a team of volunteers (led by @clifff and @sethadam1) and funded by donations.

Administered by:

Server stats:

264
active users

#githubcopilot

0 posts0 participants0 posts today
Joel Martinez<p>Anyone else out there looking at <a href="https://mastodon.social/tags/NLWeb" class="mention hashtag" rel="nofollow noopener" target="_blank">#<span>NLWeb</span></a> yet? I added support for it on my site ... all using <a href="https://mastodon.social/tags/GithubCopilot" class="mention hashtag" rel="nofollow noopener" target="_blank">#<span>GithubCopilot</span></a> 👊🏼</p><p><a href="https://codecube.net/2025/7/nlweb/" rel="nofollow noopener" translate="no" target="_blank"><span class="invisible">https://</span><span class="">codecube.net/2025/7/nlweb/</span><span class="invisible"></span></a></p>
IT News<p>Why GitHub Copilot Isn’t Your Coding Partner - These days ‘AI’ is everywhere, including in software development. Coming hot on th... - <a href="https://hackaday.com/2025/07/04/why-github-copilot-isnt-your-coding-partner/" rel="nofollow noopener" translate="no" target="_blank"><span class="invisible">https://</span><span class="ellipsis">hackaday.com/2025/07/04/why-gi</span><span class="invisible">thub-copilot-isnt-your-coding-partner/</span></a> <a href="https://schleuss.online/tags/artificialintelligence" class="mention hashtag" rel="nofollow noopener" target="_blank">#<span>artificialintelligence</span></a> <a href="https://schleuss.online/tags/softwaredevelopment" class="mention hashtag" rel="nofollow noopener" target="_blank">#<span>softwaredevelopment</span></a> <a href="https://schleuss.online/tags/largelanguagemodel" class="mention hashtag" rel="nofollow noopener" target="_blank">#<span>largelanguagemodel</span></a> <a href="https://schleuss.online/tags/githubcopilot" class="mention hashtag" rel="nofollow noopener" target="_blank">#<span>githubcopilot</span></a></p>
kurtsh<p>Azure cost reduction/optimization for hosted applications using Artificial Intelligence. And it's REPEATABLE. Interested? Read on...<br>✅ Daniel Meppiel's Project Post<br><a href="https://www.linkedin.com/posts/danielmeppiel_enterpriseai-ai-devops-ugcPost-7338909052267061248-DmG4" rel="nofollow noopener" translate="no" target="_blank"><span class="invisible">https://www.</span><span class="ellipsis">linkedin.com/posts/danielmeppi</span><span class="invisible">el_enterpriseai-ai-devops-ugcPost-7338909052267061248-DmG4</span></a><br>✅ Azure Cost Optimization Workflow<br><a href="https://github.com/danielmeppiel/agentic-hike-planner/blob/main/.github/prompts/az-cost-optimize.prompt.md" rel="nofollow noopener" translate="no" target="_blank"><span class="invisible">https://</span><span class="ellipsis">github.com/danielmeppiel/agent</span><span class="invisible">ic-hike-planner/blob/main/.github/prompts/az-cost-optimize.prompt.md</span></a><br><a href="https://mastodon.social/tags/AI" class="mention hashtag" rel="nofollow noopener" target="_blank">#<span>AI</span></a> <a href="https://mastodon.social/tags/Azure" class="mention hashtag" rel="nofollow noopener" target="_blank">#<span>Azure</span></a> <a href="https://mastodon.social/tags/githubcopilot" class="mention hashtag" rel="nofollow noopener" target="_blank">#<span>githubcopilot</span></a> <a href="https://mastodon.social/tags/CostOptimization" class="mention hashtag" rel="nofollow noopener" target="_blank">#<span>CostOptimization</span></a></p>
Jan :rust: :ferris:<p>The Copilot Delusion - by Jj</p><p><a href="https://deplet.ing/the-copilot-delusion/" rel="nofollow noopener" translate="no" target="_blank"><span class="invisible">https://</span><span class="ellipsis">deplet.ing/the-copilot-delusio</span><span class="invisible">n/</span></a></p><p>Pure poetry!</p><p><a href="https://floss.social/tags/AI" class="mention hashtag" rel="nofollow noopener" target="_blank">#<span>AI</span></a> <a href="https://floss.social/tags/GithubCopilot" class="mention hashtag" rel="nofollow noopener" target="_blank">#<span>GithubCopilot</span></a> <a href="https://floss.social/tags/ArtificialIntelligence" class="mention hashtag" rel="nofollow noopener" target="_blank">#<span>ArtificialIntelligence</span></a> <a href="https://floss.social/tags/SoftwareDevelopment" class="mention hashtag" rel="nofollow noopener" target="_blank">#<span>SoftwareDevelopment</span></a> <a href="https://floss.social/tags/SoftwareEngineering" class="mention hashtag" rel="nofollow noopener" target="_blank">#<span>SoftwareEngineering</span></a></p>
Terence Tao<p>A third video in my occasional series on <a href="https://mathstodon.xyz/tags/Lean4" class="mention hashtag" rel="nofollow noopener" target="_blank">#<span>Lean4</span></a> formalization workflows, this time focusing on how relying extensively on <a href="https://mathstodon.xyz/tags/GitHubCopilot" class="mention hashtag" rel="nofollow noopener" target="_blank">#<span>GitHubCopilot</span></a> fares against standard "epsilon delta" type problems in analysis. <a href="https://www.youtube.com/watch?v=c1ixXMtmfS8" rel="nofollow noopener" translate="no" target="_blank"><span class="invisible">https://www.</span><span class="ellipsis">youtube.com/watch?v=c1ixXMtmfS</span><span class="invisible">8</span></a></p>
Europe Says<p><a href="https://www.europesays.com/2081543/" rel="nofollow noopener" translate="no" target="_blank"><span class="invisible">https://www.</span><span class="">europesays.com/2081543/</span><span class="invisible"></span></a> Allpay Says AI Boosts Productivity, Software Releases <a href="https://pubeurope.com/tags/AdamWheater" class="mention hashtag" rel="nofollow noopener" target="_blank">#<span>AdamWheater</span></a> <a href="https://pubeurope.com/tags/AdrianMichalowski" class="mention hashtag" rel="nofollow noopener" target="_blank">#<span>AdrianMichalowski</span></a> <a href="https://pubeurope.com/tags/AI" class="mention hashtag" rel="nofollow noopener" target="_blank">#<span>AI</span></a> <a href="https://pubeurope.com/tags/AllPay" class="mention hashtag" rel="nofollow noopener" target="_blank">#<span>AllPay</span></a> <a href="https://pubeurope.com/tags/ArtificialIntelligence" class="mention hashtag" rel="nofollow noopener" target="_blank">#<span>ArtificialIntelligence</span></a> <a href="https://pubeurope.com/tags/CloudComputing" class="mention hashtag" rel="nofollow noopener" target="_blank">#<span>CloudComputing</span></a> <a href="https://pubeurope.com/tags/GenAI" class="mention hashtag" rel="nofollow noopener" target="_blank">#<span>GenAI</span></a> <a href="https://pubeurope.com/tags/GenerativeAI" class="mention hashtag" rel="nofollow noopener" target="_blank">#<span>GenerativeAI</span></a> <a href="https://pubeurope.com/tags/GitHubCopilot" class="mention hashtag" rel="nofollow noopener" target="_blank">#<span>GitHubCopilot</span></a> <a href="https://pubeurope.com/tags/MicrosoftAzure" class="mention hashtag" rel="nofollow noopener" target="_blank">#<span>MicrosoftAzure</span></a> <a href="https://pubeurope.com/tags/News" class="mention hashtag" rel="nofollow noopener" target="_blank">#<span>News</span></a> <a href="https://pubeurope.com/tags/NickWoolley" class="mention hashtag" rel="nofollow noopener" target="_blank">#<span>NickWoolley</span></a> <a href="https://pubeurope.com/tags/PaymentsProvider" class="mention hashtag" rel="nofollow noopener" target="_blank">#<span>PaymentsProvider</span></a> <a href="https://pubeurope.com/tags/PYMNTSNews" class="mention hashtag" rel="nofollow noopener" target="_blank">#<span>PYMNTSNews</span></a> <a href="https://pubeurope.com/tags/SoftwareDevelopment" class="mention hashtag" rel="nofollow noopener" target="_blank">#<span>SoftwareDevelopment</span></a></p>
James Montemagno<p>Agent mode and MCP server support is here in the latest update of Visual Studio and it is absolutely delightful! I give you a full breakdown of everything you need to know:</p><p><a href="https://www.youtube.com/watch?v=oPFecZHBCkg&amp;feature=youtu.be" rel="nofollow noopener" translate="no" target="_blank"><span class="invisible">https://www.</span><span class="ellipsis">youtube.com/watch?v=oPFecZHBCk</span><span class="invisible">g&amp;feature=youtu.be</span></a></p><p><a href="https://mastodon.social/tags/dotnet" class="mention hashtag" rel="nofollow noopener" target="_blank">#<span>dotnet</span></a> <a href="https://mastodon.social/tags/visualstudio" class="mention hashtag" rel="nofollow noopener" target="_blank">#<span>visualstudio</span></a> <a href="https://mastodon.social/tags/githubcopilot" class="mention hashtag" rel="nofollow noopener" target="_blank">#<span>githubcopilot</span></a> <a href="https://mastodon.social/tags/agentmode" class="mention hashtag" rel="nofollow noopener" target="_blank">#<span>agentmode</span></a></p>
Terence Tao<p>I recently set myself the exercise of using modern automated tools - in particular, a combination of the <a href="https://mathstodon.xyz/tags/GithubCopilot" class="mention hashtag" rel="nofollow noopener" target="_blank">#<span>GithubCopilot</span></a> large language model and the dependent type matching tactic <a href="https://mathstodon.xyz/tags/canonical" class="mention hashtag" rel="nofollow noopener" target="_blank">#<span>canonical</span></a> - to try to semi-automatically formalize in <a href="https://mathstodon.xyz/tags/Lean" class="mention hashtag" rel="nofollow noopener" target="_blank">#<span>Lean</span></a> a one-page proof provided by a collaborator of the <a href="https://mathstodon.xyz/tags/EquationalTheoriesProject" class="mention hashtag" rel="nofollow noopener" target="_blank">#<span>EquationalTheoriesProject</span></a> (Bruno Le Floch). With these tools, I was able to more or less blindly do the formalization in 33 minutes, withou any real high level conception of how the proof proceeded. It was a very different style to how I usually formalize results, but was workable for this type of technical, non-conceptual argument where the main issue is to get the details correct rather than the "big picture".</p><p>I recorded my attempt at <a href="https://www.youtube.com/watch?v=cyyR7j2ChCI" rel="nofollow noopener" translate="no" target="_blank"><span class="invisible">https://www.</span><span class="ellipsis">youtube.com/watch?v=cyyR7j2ChC</span><span class="invisible">I</span></a> . See also additional discussion at <a href="https://leanprover.zulipchat.com/#narrow/channel/458659-Equational/topic/Alternative.20proofs.20of.20E1689.E2.8A.A2E2" rel="nofollow noopener" translate="no" target="_blank"><span class="invisible">https://</span><span class="ellipsis">leanprover.zulipchat.com/#narr</span><span class="invisible">ow/channel/458659-Equational/topic/Alternative.20proofs.20of.20E1689.E2.8A.A2E2</span></a> . The final proof (which is far from optimized, but got the job done) can be found at <a href="https://github.com/teorth/estimate_tools/blob/master/EstimateTools/test/equational.lean" rel="nofollow noopener" translate="no" target="_blank"><span class="invisible">https://</span><span class="ellipsis">github.com/teorth/estimate_too</span><span class="invisible">ls/blob/master/EstimateTools/test/equational.lean</span></a></p>
Christos Argyropoulos MD PhD<p>Watching <a href="https://mastodon.social/tags/GithubCopilot" class="mention hashtag" rel="nofollow noopener" target="_blank">#<span>GithubCopilot</span></a> repeatedly failing to generate a functional LinuxSysadmin 101 Perl utility to track peak memory usage of a process, makes me think we are not far from the day one undertrained employee FAFOs, deletes the file systems in a NORAD cluster releasing the nukes</p>
Nick Taylor<p>Wrote up a post about building a Ollama <span class="h-card" translate="no"><a href="https://hachyderm.io/@github" class="u-url mention" rel="nofollow noopener" target="_blank">@<span>github</span></a></span> Copilot extension.</p><p>It leverages the CodeLlama model and lets you use files, via Copilot extensions new context-passing capabilities, in your Ollama prompts 🚀 </p><p><a href="https://buff.ly/402RB32" rel="nofollow noopener" translate="no" target="_blank"><span class="invisible">https://</span><span class="">buff.ly/402RB32</span><span class="invisible"></span></a> <a href="https://hachyderm.io/tags/ai" class="mention hashtag" rel="nofollow noopener" target="_blank">#<span>ai</span></a> <a href="https://hachyderm.io/tags/ollama" class="mention hashtag" rel="nofollow noopener" target="_blank">#<span>ollama</span></a> <a href="https://hachyderm.io/tags/CopilotExtension" class="mention hashtag" rel="nofollow noopener" target="_blank">#<span>CopilotExtension</span></a> <a href="https://hachyderm.io/tags/GithubCopilot" class="mention hashtag" rel="nofollow noopener" target="_blank">#<span>GithubCopilot</span></a></p>
David Chisnall (*Now with 50% more sarcasm!*)<p>I finally turned off GitHub Copilot yesterday. I’ve been using it for about a year on the ‘free for open-source maintainers’ tier. I was skeptical but didn’t want to dismiss it without a fair trial.</p><p>It has cost me more time than it has saved. It lets me type faster, which has been useful when writing tests where I’m testing a variety of permutations of an API to check error handling for all of the conditions.</p><p>I can recall three places where it has introduced bugs that took me more time to to debug than the total time saving:</p><p>The first was something that initially impressed me. I pasted the prose description of how to communicate with an Ethernet MAC into a comment and then wrote some method prototypes. It autocompleted the bodies. All very plausible looking. Only it managed to flip a bit in the MDIO read and write register commands. MDIO is basically a multiplexing system. You have two device registers exposed, one sets the command (read or write a specific internal register) and the other is the value. It got the read and write the wrong way around, so when I thought I was writing a value, I was actually reading. When I thought I was reading, I was actually seeing the value in the last register I thought I had written. It took two of us over a day to debug this. The fix was simple, but the bug was in the middle of correct-looking code. If I’d manually transcribed the command from the data sheet, I would not have got this wrong because I’d have triple checked it.</p><p>Another case it had inverted the condition in an if statement inside an error-handling path. The error handling was a rare case and was asymmetric. Hitting the if case when you wanted the else case was okay but the converse was not. Lots of debugging. I learned from this to read the generated code more carefully, but that increased cognitive load and eliminated most of the benefit. Typing code is not the bottleneck and if I have to think about what I want and then read carefully to check it really is what I want, I am slower.</p><p>Most recently, I was writing a simple binary search and insertion-deletion operations for a sorted array. I assumed that this was something that had hundreds of examples in the training data and so would be fine. It had all sorts of corner-case bugs. I eventually gave up fixing them and rewrote the code from scratch.</p><p>Last week I did some work on a remote machine where I hadn’t set up Copilot and I felt much more productive. Autocomplete was either correct or not present, so I was spending more time thinking about what to write. I don’t entirely trust this kind of subjective judgement, but it was a data point. Around the same time I wrote some code without clangd set up and that <em>really</em> hurt. It turns out I really rely on AST-aware completion to explore APIs. I had to look up more things in the documentation. Copilot was never good for this because it would just bullshit APIs, so something showing up in autocomplete didn’t mean it was real. This would be improved by using a feedback system to require autocomplete outputs to type check, but then they would take much longer to create (probably at least a 10x increase in LLM compute time) and wouldn’t complete fragments, so I don’t see a good path to being able to do this without tight coupling to the LSP server and possibly not even then.</p><p>Yesterday I was writing bits of the CHERIoT Programmers’ Guide and it kept autocompleting text in a different writing style, some of which was obviously plagiarised (when I’m describing precisely how to implement a specific, and not very common, lock type with a futex and the autocomplete is a paragraph of text with a lot of detail, I’m confident you don’t have more than one or two examples of that in the training set). It was distracting and annoying. I wrote much faster after turning it off.</p><p>So, after giving it a fair try, I have concluded that it is both a net decrease in productivity and probably an increase in legal liability.</p><p>Discussions I am not interested in having:</p><ul><li>You are holding it wrong. Using Copilot with this magic config setting / prompt tweak makes it better. At its absolute best, it was a small productivity increase, if it needs more effort to use, that will be offset.</li><li>This other LLM is <em>much</em> better. I don’t care. The costs of the bullshitting far outweighed the benefits when it worked, to be better it would have to <em>not bullshit</em>, and that’s not something LLMs can do.</li><li>It’s great for boilerplate! No. APIs that require every user to write the same code <em>are broken</em>. Fix them, don’t fill the world with more code using them that will need fixing when the APIs change.</li><li>Don’t use LLMs for autocomplete, use them for dialogues about the code. Tried that. It’s worse than a rubber duck, which at least knows to stay silent when it doesn’t know what it’s talking about.</li></ul><p>The one place Copilot was vaguely useful was hinting at missing abstractions (if it can autocomplete big chunks then my APIs required too much boilerplate and needed better abstractions). The place I thought it might be useful was spotting inconsistent API names and parameter orders but it was actually very bad at this (presumably because of the way it tokenises identifiers?). With a load of examples with consistent names, it would suggest things that didn't match the convention. After using three APIs that all passed the same parameters in the same order, it would suggest flipping the order for the fourth.</p><p><a href="https://infosec.exchange/tags/GitHubCopilot" class="mention hashtag" rel="nofollow noopener" target="_blank">#<span>GitHubCopilot</span></a> <a href="https://infosec.exchange/tags/CHERIoT" class="mention hashtag" rel="nofollow noopener" target="_blank">#<span>CHERIoT</span></a></p>
AliveDevil<p>No thanks, <a href="https://tauri.earth/tags/GitHub" class="mention hashtag" rel="nofollow noopener" target="_blank">#<span>GitHub</span></a>, and now gtfo.</p><p><a href="https://tauri.earth/tags/GitHubCoPilot" class="mention hashtag" rel="nofollow noopener" target="_blank">#<span>GitHubCoPilot</span></a></p>
Roni Laukkarinen<p>GitHub today: "Now in GitHub Copilot, you can choose Anthropic’s Claude 3.5 Sonnet to perform a variety of tasks—like refactoring code. 💻"</p><p>This is funny, it's exactly what Cursor does.</p><p><a href="https://mementomori.social/tags/GitHub" class="mention hashtag" rel="nofollow noopener" target="_blank">#<span>GitHub</span></a> <a href="https://mementomori.social/tags/Microsoft" class="mention hashtag" rel="nofollow noopener" target="_blank">#<span>Microsoft</span></a> <a href="https://mementomori.social/tags/VSCode" class="mention hashtag" rel="nofollow noopener" target="_blank">#<span>VSCode</span></a> <a href="https://mementomori.social/tags/Cursor" class="mention hashtag" rel="nofollow noopener" target="_blank">#<span>Cursor</span></a> <a href="https://mementomori.social/tags/AI" class="mention hashtag" rel="nofollow noopener" target="_blank">#<span>AI</span></a> <a href="https://mementomori.social/tags/Coding" class="mention hashtag" rel="nofollow noopener" target="_blank">#<span>Coding</span></a> <a href="https://mementomori.social/tags/GitHubCopilot" class="mention hashtag" rel="nofollow noopener" target="_blank">#<span>GitHubCopilot</span></a></p>
Alvin Ashcraft 🐿️<p>Introducing GitHub Copilot in Xcode w/ Christina Warren.</p><p><a href="https://buff.ly/3ZstH1P" rel="nofollow noopener" translate="no" target="_blank"><span class="invisible">https://</span><span class="">buff.ly/3ZstH1P</span><span class="invisible"></span></a> <br><a href="https://hachyderm.io/tags/xcode" class="mention hashtag" rel="nofollow noopener" target="_blank">#<span>xcode</span></a> <a href="https://hachyderm.io/tags/ios" class="mention hashtag" rel="nofollow noopener" target="_blank">#<span>ios</span></a> <a href="https://hachyderm.io/tags/swift" class="mention hashtag" rel="nofollow noopener" target="_blank">#<span>swift</span></a> <a href="https://hachyderm.io/tags/mobiledev" class="mention hashtag" rel="nofollow noopener" target="_blank">#<span>mobiledev</span></a> <a href="https://hachyderm.io/tags/ai" class="mention hashtag" rel="nofollow noopener" target="_blank">#<span>ai</span></a> <a href="https://hachyderm.io/tags/githubcopilot" class="mention hashtag" rel="nofollow noopener" target="_blank">#<span>githubcopilot</span></a> <a href="https://hachyderm.io/tags/aiassistant" class="mention hashtag" rel="nofollow noopener" target="_blank">#<span>aiassistant</span></a></p>
Scripter :verified_flashing:<p>GitHub Copilot learns new tricks | InfoWorld<br><a href="https://www.infoworld.com/article/3600418/github-copilot-learns-new-tricks.html" rel="nofollow noopener" translate="no" target="_blank"><span class="invisible">https://www.</span><span class="ellipsis">infoworld.com/article/3600418/</span><span class="invisible">github-copilot-learns-new-tricks.html</span></a> <a href="https://social.tchncs.de/tags/GitHub" class="mention hashtag" rel="nofollow noopener" target="_blank">#<span>GitHub</span></a> <a href="https://social.tchncs.de/tags/GitHubCopilot" class="mention hashtag" rel="nofollow noopener" target="_blank">#<span>GitHubCopilot</span></a></p>
IT News<p>Assessing Developer Productivity When Using AI Coding Assistants - We have all seen the advertisements and glossy flyers for coding assistants like G... - <a href="https://hackaday.com/2024/10/15/assessing-developer-productivity-when-using-ai-coding-assistants/" rel="nofollow noopener" translate="no" target="_blank"><span class="invisible">https://</span><span class="ellipsis">hackaday.com/2024/10/15/assess</span><span class="invisible">ing-developer-productivity-when-using-ai-coding-assistants/</span></a> <a href="https://schleuss.online/tags/artificialintelligence" class="mention hashtag" rel="nofollow noopener" target="_blank">#<span>artificialintelligence</span></a> <a href="https://schleuss.online/tags/softwaredevelopment" class="mention hashtag" rel="nofollow noopener" target="_blank">#<span>softwaredevelopment</span></a> <a href="https://schleuss.online/tags/githubcopilot" class="mention hashtag" rel="nofollow noopener" target="_blank">#<span>githubcopilot</span></a> <a href="https://schleuss.online/tags/ai" class="mention hashtag" rel="nofollow noopener" target="_blank">#<span>ai</span></a></p>
Kevin Karhan :verified:<p><em>"<a href="https://infosec.space/tags/AI" class="mention hashtag" rel="nofollow noopener" target="_blank">#<span>AI</span></a>"</em> does not replace real <a href="https://infosec.space/tags/intellect" class="mention hashtag" rel="nofollow noopener" target="_blank">#<span>intellect</span></a>! </p><p><a href="https://www.youtube.com/watch?v=khIFjdNTfdA" rel="nofollow noopener" translate="no" target="_blank"><span class="invisible">https://www.</span><span class="ellipsis">youtube.com/watch?v=khIFjdNTfd</span><span class="invisible">A</span></a></p><p><a href="https://infosec.space/tags/Github" class="mention hashtag" rel="nofollow noopener" target="_blank">#<span>Github</span></a> <a href="https://infosec.space/tags/Copilot" class="mention hashtag" rel="nofollow noopener" target="_blank">#<span>Copilot</span></a> <a href="https://infosec.space/tags/githubcopilot" class="mention hashtag" rel="nofollow noopener" target="_blank">#<span>githubcopilot</span></a> <a href="https://infosec.space/tags/github_copilot" class="mention hashtag" rel="nofollow noopener" target="_blank">#<span>github_copilot</span></a> <a href="https://infosec.space/tags/Bugs" class="mention hashtag" rel="nofollow noopener" target="_blank">#<span>Bugs</span></a></p>
Max Leibman<p>I've heard that using GitHub Copilot and ChatGPT isn't a good way to learn to code, but every time I use these tools, they show me some novel library or function that I've never heard of before. <br> <br>Occasionally, these are even real! <br> <br> <br> <br><a href="https://beige.party/tags/LLM" class="mention hashtag" rel="nofollow noopener" target="_blank">#<span>LLM</span></a> <a href="https://beige.party/tags/AmCoding" class="mention hashtag" rel="nofollow noopener" target="_blank">#<span>AmCoding</span></a> <a href="https://beige.party/tags/ChatGPT" class="mention hashtag" rel="nofollow noopener" target="_blank">#<span>ChatGPT</span></a> <a href="https://beige.party/tags/GitHubCopilot" class="mention hashtag" rel="nofollow noopener" target="_blank">#<span>GitHubCopilot</span></a></p>
Paul Jacobson<p><a href="https://digitalstuntfactory.com/tags/GitHubCopilot" class="mention hashtag" rel="nofollow noopener" target="_blank">#<span>GitHubCopilot</span></a> seems to still need its morning coffee today. I was working with it to edit a script and it kept introducing regressions in my code. I had to switch over to <a href="https://digitalstuntfactory.com/tags/Anthropic" class="mention hashtag" rel="nofollow noopener" target="_blank">#<span>Anthropic</span></a>'s <a href="https://digitalstuntfactory.com/tags/Claude" class="mention hashtag" rel="nofollow noopener" target="_blank">#<span>Claude</span></a> for a little helper sanity.</p>
Robert Buchberger<p>The <a href="https://spacey.space/tags/AI" class="mention hashtag" rel="nofollow noopener" target="_blank">#<span>AI</span></a> uprising is here and it starts with <a href="https://spacey.space/tags/githubcopilot" class="mention hashtag" rel="nofollow noopener" target="_blank">#<span>githubcopilot</span></a> throwing shade.</p><p>No seriously, every time I start a comment, copilot says "this is a hack". I don't know how to handle this disrespect.</p>