-
Dealing with github copilot errors
Dealing with github copilot errors is pretty irritating. Especially when dosing some more complex stuff and suddenly „Bam”. Red message. Easiest thing to do ? Switching the model family often works because some models have different capacity pools or stricter preview limits. GitHub documents vaguely that if you are rate limited, you can wait and try again. Just type „continue” and keep your fingers crossed. Otherwise check usage patterns, change the model, or contact support. Common github copilot errors Some run of the mill You probably know already, just put them together as a 'review’ : Why changing the model helps ? Changing from one model family (vendor) to another…
-
Markmap vs Mermaid for Spec-Driven Development (SDD)
Markmap vs Mermaid for Spec-Driven Development You will consider sooner or later. When You have to go „full on AI” documentation stops being a nice-to-have and becomes a must be part of the product. We need to convey a lot of information, with hopefully as little text as possible so we can easily read it and digest the information. Two popular options for Markdown documentation features are Markmap and Mermaid. They solve different problems, and the best choice depends on whether you want fast idea mapping or more structured diagrams for flows. When to use Markmap Markmap turns Markdown headings and bullet points into an interactive mind map. Useful for…
-
Jevons paradox in AI workplace
Jevons paradox in AI workplace Jevons paradox in AI workplace is introduced at work with a simple promise: do more in less time. In practice, the result are messy and stack the work. Jevons paradox is the idea that when something becomes more efficient, people and organizations often end up using more of it. In the AI workplace that can mean faster tools, automated work that do not always reduce workload. They can also expand expectations, volume, and ambition to utilize the improved (AIed ?) processes. Be aware At first glance, this sounds contradictory and just wrong. If a team can draft emails, summarize meetings, and generate reports in minutes,…
-
WebExtension Manifest.json permissions options list
WebExtension Manifest.json permissions options list is quite long. Let us see what we can access with our plugin for FF. This hsould inspire You to write Your own for quality of life and ease of doing things… or avoid them all together. For avoidance i would highly recommend to look into prper ad block filter and creating / adding your own. Rule : Do not scare users Remember when Your app requires and asks for access. You either explain to user in every detail what for and go with bare minimum. Just as a rule of thumb of not beeing accused of getting and selling info. It is always scary…
-
Protect your work with poison ?
Protect your work with poison ? Is there no other way around. Robots.txt ? Nobody cares. Copyrights ? LOL. Fair use policy ? As long as i don`t get caught. Protect your work with poison is the oldest trick in the book, especially by plants. Most of them have to be cooked, to be eaten and digested with benefit for us. Why not doing it with our work ?I am thinking about healthy amount of protecting our work. Does it mean anyone making a rembrandt style photo should pay the author of that style ? For 70 years ? How much and how long ? Why money at all ?…
-
Deeplearning.ai text-embedding model error. Change to text-embedding-005
Deeplearning.ai text-embedding model error for „textembedding-gecko@001” requires You to simply change it to another one. Instead of the original pretrained models we should use the newer ones. Those models are succeeding the gecko series in Vertex AI. Google Vertex AI Options OpenAI Options Those are just some of the available models. Usage Comparison Model Provider Dims Max Tokens Best For text-embedding-005 Google 768 2048 English/code gemini-embedding-001 Google 3072 Varies High quality text-embedding-3-small OpenAI 1536 8191 General/RAG Summary Once upon a time, and still we can find many many things thanks to start overflow and people willing to share knowledge… let us hope the next time you google something…
-
Statics VS AI code analysis ~13 tools
Statics VS AI code analysis works best using the pros from both words. Go hybrid ! Static tools understand the syntext, hardcoded parameters and are very strict. On the other hand AI understands context, can figure out business logic, adapt the codebase. Logic flaws or performance bottlenecks rule-based scanners might miss, AI will put more effort into that. Static analysis limits Static tools scan for syntax errors, style violations, and basic security patterns using fixed rules. Always consistenst, very fast but might generate false positives, ignore business logic, and require manual rule overrides. How often did You use @typescript-error 🙂 Do You code for the linter to pass, logic to…
-
Losada coefficient at life and work
The Losada coefficient at life and work is pretty much the same theory. Also known as Losada ratio or critical positivity ratio. Proposes a fixed ration between positive and negative interactions / emotions. Supposedly distinguishes positive from negative individuals or teams.We should have proportionally MORE POSITIVE INTERACTIONS so in the long run we will be happy.Originated in 2005 paper by psychologists Barbara Fredrickson and Marcial Losada, who calculated a threshold of ~2.9:1 and upper? limit around 11.6:1 Losada ratio in coportate In highly skilled IT software development teams ( or any other team for that matter) this balance shows up in code reviews, stand‑ups, meetings, emails, design discussions and production…
-
Code mode for mcp servers and llms
Code mode for mcp servers is about LLM writing and calling the code to use a proper MCP instead of calling it directly with the whole context. It makes the call a lot smaller, no overhead is passed, just the basics that are required to call the proper MCP method. Just as You do in code, method or a function, proper parameters, everything validated and… BAM ! We are returning a context that LLM uses in further stages. Anthropics wrote… This is really nice looking but only for a huge models with a 1kk tokens of a context. We need to remember that this is not possible on any kind…
-
97 Things Every Data Engineer Should Know – book review
97 Things Every Data Engineer Should Know review will be a positive one. This style of books is currently my favorite. Might get another one from the series 🙂 It is bits and pieces of knowledge You can digest easily. Scattered across multiple disciplines teachings are of a principle design. Book is technologically agnostic, meaning rules, law, principles and methodologies presented You can use with any framework or system. It is like the design principles. Great read, would recommend. 97 lessons to pick from The book is all about best practices, system design, queues, asynchronouse communication and many more. You can easily read it day by day when You „meditate”…
