Not exactly like that, but something similar :)

No, you are wrong. IBMer here. I was at first agains it, my background is for 2 decades startup(s) before I joined IBM, and I started slowly using IBM Bob and I must say it is really good and helping. With many integrations that works :)

Is it true that employees have to earn Bobcoins before they can use Bob?

You get more bobcoins by using your old allowance and running out, then submitting GitHub issues that get ignored.

No.

No

When people say they have been in startups for long periods, does this mean they worked at a chain of failed companies?

No no no :) They want(ed) just change :)

What is good about it then? What model do you use? Which integration are we talking about? Is it open source? How much the "transparent pricing" "bobcoin" is worth?

It's not good, they hide the model (their whole thing is hidden model routing to keep costs low, but predictably yields bad results), there are no novel integrations not available in any other harness, it's closed source, and bobcoin is worthless because it's only usable with Bob.

And what? IDK about BOB that is available for IBM customers, but closed source? As someone wrote in different thread is based on VScode, calling BOB's API. Also do you know how chatgpt works? same for claude? Agents? Governance? You know nothing and now just hating here :)

the bob team aggressively blocks you from calling the bob api and is constantly finding new ways to thwart calling the api directly

It uses hidden models, mostly Claude and open ai models. They try to check the prompt and route to the model that is capable of it, thus saving money.

I think this is it ^^^ Routing and optimizations :)

Are you allowed to use Cursor, Codex, Claude, or OpenCode or is Bob all they allow?

Official policy is to only use Bob. All of the best people I work with are using other tools because Bob is trash.

I have been told only Bob is allowed but not 100% on that.

Also copilot and MS365 copilot, many local models etc... Many haters (companies, etc...) can only dream about availability of models we usually have here.

is bob helping with ur writing too? ;p

lol, I've used it and Bob is a dumpster fire.

Do you have to have experience with AWS Kiro? I'd be interested in a comparision between them. :)

rlly? cs it is IMHO based on anthropic / openai models. Perhaps they identified BFU and gave you some

so it tops out at sonnet 4.5 as the largest model it will use. the harness gives you no choice in the model so you have to hope it doesn't decide your task isn't complex enough and auto-route you to a smaller/weaker model which you then go round and round in circles with where a larger model would've 1 shotted it

Lol

I have similar project like this: https://hostbeat.info/ More like t uptime robot and sure, I was really surprised yesterday how many alerts I have got and how many notifications were sent yesterday for this system users. Good work anyway

I built https://milliondollarllm.com, a pixel-style public board inspired by the old “Million Dollar Homepage,” but focused on LLM and AI projects.

The idea:

Companies can pay for space for their LLM/AI product (1 USD = 1 pixel) and get a logo + link on the public board.

Each paying “sponsor” can choose one free/open project to endorse publicly.

Free projects get a small logo and description for free, and can be highlighted via a sponsor endorsement.

The goal is to make a simple, transparent way for companies to get a bit of visibility for their LLM/AI products, and at the same time, shine some light on smaller or open projects that deserve attention.

:) Oh, this is neat! Python 3.12.0 has brought some cool features to the table. I'm particularly keen on the flexible f-string parsing and the performance improvements. The new type annotation syntax for generic classes is a nice touch too. It's always good to see Python getting refined with each release. Looking forward to exploring these new additions...

Robots.txt Analysis for GPT Bots API running here: https://dataguard.hostbeat.info/

Ivy is both an ML transpiler and a framework, currently supporting JAX, TensorFlow, PyTorch and Numpy.

Ivy unifies all ML frameworks enabling you not only to write code that can be used with any of these frameworks as the backend, but also to convert any function, model or library written in any of them to your preferred framework!

I find myself in a bit of a quandary over the upcoming Nintendo Switch release slated for this fall. Having navigated my way from the Switch Lite to the standard Switch, and now being confronted with the OLED model, I can't help but feel a sense of continuity, rather than any groundbreaking advancement. I revel in the games, no doubt about it, but the purported 'improvements' haven't sparked any significant eureka moments for me. Each upgrade has cost me an additional 100-150 euros, yet the experience, albeit slightly enhanced, doesn't seem to justify the price tag. I'm left questioning, is the elusive "it's better" worth it? What are your thoughts, fellow gamers?

Depends on what you expect. I've got an almost launch day original Switch and have played dozens of games on it and feel I'm still getting my money's worth. The Lite and OLED models are just slight variations on the same machine so why would you expect groundbreaking advancements?

A Switch won't play 100Gb+ AAA titles, but everytime I see video's from 'next gen' games I still see 'uncanny valley' effects and about the same gameplay. While it could look better, Mario Kart with realistic water reflections and raytraced shadows still would be Mario Kart (and probably no longer run on a portable console).

The difference between standard and OLED wasn't enough for me to upgrade. In general, I think console revisions are better as a first purchase than as an upgrade - the nicer screen or bigger battery helps sell people on the slower processors and limited future software support of a console that first released a few years ago.

The OLED version had the stick drift too, I had to return it.

My expectations for this new model are zero. Nintendo hardware sucks nowadays.

All mainstream console controllers experience more or less stick drift. Nintendo still replaces Joy-cons (even out of warranty) for free in the EU.

> All mainstream console controllers experience more or less stick drift

Yet my two xbox controllers that I've had for 5 years have not experienced this, and nor have my PS4 controller (4 years old at this point).

I've had to replace the joycon twice. And the third one still has drift. I gave up and just use a Nintendo Switch Pro controller with it now.

You shouldn't have to do this, but you can buy replacement Joycon joysticks with hall effect sensors that won't drift

The Pro controller has drift issues as well (although less often)

Did you use/abuse the xbox/ps4 controllers as much as the Switch controllers? My guess is the amount of hours played is a big factor in wear and tear. Since the Switch is portable you have a lot more opportunity to play.

Switch: Barely used, and gently used. PS4/Xbox: Gets tossed around, used as a media center as well as for gaming.

After the first joycon replacement, we were even more gentle with it.

My Xbox controllers never did it either. Never once had my character walked himself off a cliff after I stopped giving input.

Nice article! Thank you Martin :) I didn't know about Date and Time Formatting or Nested F-Strings.

Maybe a SW upgrade by Elon / Tesla will suffice :)

def power_up(battery_pover_in): voltage_in = abs(battery_pover_in) voltage_up = battery_pover_in * 1.5 return voltage_up