{"id":1050,"date":"2026-08-10T09:29:15","date_gmt":"2026-08-10T08:29:15","guid":{"rendered":"https:\/\/metrics.blogg.gu.se\/?p=1050"},"modified":"2026-08-10T09:29:15","modified_gmt":"2026-08-10T08:29:15","slug":"software-engineering-with-agents-there-is-a-need-for-more-humanity-in-se-and-beyond","status":"publish","type":"post","link":"https:\/\/metrics.blogg.gu.se\/?p=1050","title":{"rendered":"Software Engineering with Agents – there is a need for more humanity in SE and beyond"},"content":{"rendered":"\n

Alternatively: do not trust the big tech on how good the AI is – humans are still needed to point it to the right direction<\/p>\n\n\n\n

\"\"<\/a><\/figure>\n\n\n\n

Image by\u00a0Michael Kauer<\/a>\u00a0from\u00a0Pixabay<\/a><\/p>\n\n\n\n

My summer is getting dangerously close to its finish line, despite my strong protests. I’ve spent the summer working on non-software-engineering tasks, but before I went on vacation, I managed to make a trip to Montreal for FSE (Foundations of Software Engineering) conference. Here are my thoughts based on what I’ve seen.<\/p>\n\n\n\n

The figure below shows the topics that were discussed on the main FSE conference, with the categories based on the session titles. 179 papers were presented, excluding co-located events and non-research tracks. I would guess that the entire event gathered about 300-350 papers and equal number of researchers. <\/p>\n\n\n\n

\"\"<\/a><\/figure>\n\n\n\n

<\/p>\n\n\n\n

First, I see an increasing trend for non-empirical research in software engineering. LLM for SE or testing are very much about new technologies, with very few papers that provide empirical backing. It is not a problem per se, but can lead to strange conclusions. But, it does lead to situations where studies are great for benchmarks, but they are completely useless in practice. <\/p>\n\n\n\n

An example of one study. The goal was to generate functions that would solve a task in C. Current approach – use a prompt. Their approach was to augment the prompt with downstream and upsteam function calls, like this: <code that calls this function> <prompt\/description> <code that is called by this function>. The performance was almost 100% correct, but… Yes, but it is unusable in practice, because when we generate code, we do not know what functions the generated code will call, we “maybe” know what should call this function. So, great idea, but without empirical evaluation it is not really useful. BTW: already got a lot of citations that paper. <\/p>\n\n\n\n

Second, the number of papers and tracks is just huge, with presentations becoming shorter and shorter. 5-15 minutes with 1-5 minutes for questions. It’s hard to have any scientific discussion about studies in such a short period of time. Another anecdote – there was one person who had like 10-15 badges and presented as many papers. He was an author of some, but not of the others. Sometimes he even did not know what he was presenting, let alone answer questions.<\/p>\n\n\n\n

Third, there was some empirical research, but it was in minority. I guess it is so much simpler to take a dataset, existing methods, run Claude to improve them and publish a paper. Asking practitioners? Getting out in the field? Risking being wrong? Learning something? – that seems to be secondary in today’s science. Or maybe I’m just cynical… <\/p>\n\n\n\n

Finally, and that really rattled my cage, was the lack of transparency of which presentations were online. Although the conference was IRL, there were some pre-recorded presentations with speakers online (if we were lucky). So, going through the program beforehand and selecting papers to listen to was a losing strategy (trust me, I did it). A better strategy was to go between 2-3 rooms, ask the session chairs which presentations are online and just switch to another room. <\/p>\n\n\n\n

Well, maybe I’m just a bit cranky, but I expected more. <\/p>\n\n\n\n

Anyways, what I wanted to get to is that I see a lot of potential for humanity in today’s software engineering. <\/p>\n\n\n\n

    \n
  1. I see that AI will not be able to replace human judgement and experience. Regardless of what the tech giants are telling us, there is just no way they can create an entire project on its on, the AIs. <\/li>\n\n\n\n
  2. I see that writing is still a human domain. AI-written papers are really hard to read and should be rejected directly. As they are so easy to write by AI, and AI has no feelings, this should be no problem. <\/li>\n\n\n\n
  3. I see that there is a lot of AI-augmentation potential, but we should limit the number of tools that we release. Do we really need a tool for code review for embedded software written in C in Gothenburg? how would it be different from the embedded software written in C in Copenhagen? You get my idea: more generic tools, better processes, better education. <\/li>\n\n\n\n
  4. I also see that we need to be better in communicating. AI-generated memes – yes, but AI-generated education videos? maybe not so much. A teacher is still a teacher, they know where to look to see if the student knows what he\/she should know. <\/li>\n<\/ol>\n\n\n\n

    To summarize, humanity is on the rise, despite what people are telling us. We are still dominant and we will be dominant because we think outside the box, we can have a small talk that will give us an idea and we are humans. We have feelings and we know if something is fishy – we can smell it. <\/p>\n","protected":false},"excerpt":{"rendered":"

    Alternatively: do not trust the big tech on how good the AI is – humans are still needed to point it to the right direction Image by\u00a0Michael Kauer\u00a0from\u00a0Pixabay My summer is getting dangerously close to its finish line, despite my strong protests. I’ve spent the summer working on non-software-engineering tasks, but before I went on … Continue reading “Software Engineering with Agents – there is a need for more humanity in SE and beyond”<\/span><\/a><\/p>\n","protected":false},"author":68,"featured_media":0,"comment_status":"closed","ping_status":"open","sticky":false,"template":"","format":"standard","meta":{"footnotes":""},"categories":[5],"tags":[],"_links":{"self":[{"href":"https:\/\/metrics.blogg.gu.se\/index.php?rest_route=\/wp\/v2\/posts\/1050"}],"collection":[{"href":"https:\/\/metrics.blogg.gu.se\/index.php?rest_route=\/wp\/v2\/posts"}],"about":[{"href":"https:\/\/metrics.blogg.gu.se\/index.php?rest_route=\/wp\/v2\/types\/post"}],"author":[{"embeddable":true,"href":"https:\/\/metrics.blogg.gu.se\/index.php?rest_route=\/wp\/v2\/users\/68"}],"replies":[{"embeddable":true,"href":"https:\/\/metrics.blogg.gu.se\/index.php?rest_route=%2Fwp%2Fv2%2Fcomments&post=1050"}],"version-history":[{"count":1,"href":"https:\/\/metrics.blogg.gu.se\/index.php?rest_route=\/wp\/v2\/posts\/1050\/revisions"}],"predecessor-version":[{"id":1053,"href":"https:\/\/metrics.blogg.gu.se\/index.php?rest_route=\/wp\/v2\/posts\/1050\/revisions\/1053"}],"wp:attachment":[{"href":"https:\/\/metrics.blogg.gu.se\/index.php?rest_route=%2Fwp%2Fv2%2Fmedia&parent=1050"}],"wp:term":[{"taxonomy":"category","embeddable":true,"href":"https:\/\/metrics.blogg.gu.se\/index.php?rest_route=%2Fwp%2Fv2%2Fcategories&post=1050"},{"taxonomy":"post_tag","embeddable":true,"href":"https:\/\/metrics.blogg.gu.se\/index.php?rest_route=%2Fwp%2Fv2%2Ftags&post=1050"}],"curies":[{"name":"wp","href":"https:\/\/api.w.org\/{rel}","templated":true}]}}